diff --git a/.gitattributes b/.gitattributes index a6344aac8c09253b3b630fb776ae94478aa0275b..52373fe24473b1aa44333d318f578ae6bf04b49b 100644 --- a/.gitattributes +++ b/.gitattributes @@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text +tokenizer.json filter=lfs diff=lfs merge=lfs -text diff --git a/args.json b/args.json new file mode 100644 index 0000000000000000000000000000000000000000..b3d329964d3230a164efd9d027517f7718881d74 --- /dev/null +++ b/args.json @@ -0,0 +1,467 @@ +{ + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "zai-org/GLM-4.5-Air", + "model_type": "glm4_5", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": null, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "glm4_5", + "system": null, + "max_length": 10280, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_free": true, + "padding_side": "right", + "loss_scale": "default", + "sequence_parallel_size": 1, + "response_prefix": null, + "template_backend": "swift", + "dataset": [ + "/workspace/joined_dataset_cleaned_modified.jsonl" + ], + "val_dataset": [], + "split_dataset_ratio": 0.01, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": true, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "ckpt_dir": "/workspace/glm-4.5-air-mcore", + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "seed": 42, + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": true, + "packing_length": 10280, + "lazy_tokenize": false, + "cached_dataset": [], + "custom_register_path": [], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 256, + "lora_alpha": 16, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": true, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": 0.1, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "padded_vocab_size": 151552, + "initialize_embedding": false, + "mlp_padding_free": false, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 10, + "architectures": "Glm4MoeForCausalLM", + "llm_architectures": null, + "max_epochs": 2, + "enable_dft_loss": false, + "enable_channel_loss": false, + "original_max_position_embeddings": null, + "partial_rotary_factor": 0.5, + "use_shared_expert_gate": false, + "vit_gradient_checkpointing": true, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "mrope_interleaved": false, + "micro_batch_size": 4, + "global_batch_size": 32, + "recompute_granularity": "full", + "recompute_method": "uniform", + "recompute_num_layers": 1, + "recompute_modules": [ + "core_attn" + ], + "use_cpu_initialization": false, + "deterministic_mode": false, + "train_iters": null, + "log_interval": 5, + "tensorboard_dir": "/workspace/megatron_output/Iceblink-v3-SFT-1/v0-20251101-193922/runs", + "no_masked_softmax_fusion": false, + "no_bias_dropout_fusion": false, + "no_bias_swiglu_fusion": false, + "no_rope_fusion": false, + "no_gradient_accumulation_fusion": false, + "cross_entropy_loss_fusion": true, + "cross_entropy_fusion_impl": "native", + "calculate_per_token_loss": true, + "use_flash_attn": false, + "attention_backend": "flash", + "optimizer": "adam", + "optimizer_cpu_offload": false, + "optimizer_offload_fraction": 1.0, + "use_precision_aware_optimizer": false, + "main_grads_dtype": "fp32", + "main_params_dtype": "fp32", + "exp_avg_dtype": "fp32", + "exp_avg_sq_dtype": "fp32", + "dataloader_type": "cyclic", + "manual_gc": false, + "manual_gc_interval": 0, + "lr": 1e-05, + "lr_decay_style": "cosine", + "lr_decay_iters": null, + "lr_warmup_iters": 0, + "lr_warmup_fraction": 0.05, + "min_lr": 1e-06, + "weight_decay": 0.1, + "clip_grad": 1.0, + "adam_beta1": 0.9, + "adam_beta2": 0.95, + "adam_eps": 1e-08, + "sgd_momentum": 0.9, + "save": "/workspace/megatron_output/Iceblink-v3-SFT-1/v0-20251101-193922", + "save_interval": 25, + "save_retain_interval": null, + "no_save_optim": true, + "no_save_rng": true, + "load": "/workspace/glm-4.5-air-mcore", + "no_load_optim": false, + "no_load_rng": false, + "finetune": true, + "ckpt_format": "torch_dist", + "no_initialization": true, + "auto_detect_ckpt_format": true, + "exit_on_missing_checkpoint": true, + "async_save": false, + "use_persistent_ckpt_worker": false, + "ckpt_fully_parallel_load": false, + "ckpt_assume_constant_structure": false, + "distributed_backend": "nccl", + "local_rank": 0, + "use_distributed_optimizer": true, + "tensor_model_parallel_size": 8, + "pipeline_model_parallel_size": 1, + "decoder_first_pipeline_num_layers": null, + "decoder_last_pipeline_num_layers": null, + "sequence_parallel": true, + "context_parallel_size": 1, + "tp_comm_overlap": false, + "overlap_grad_reduce": false, + "overlap_param_gather": false, + "distributed_timeout_minutes": 300000, + "num_layers_per_virtual_pipeline_stage": null, + "num_virtual_stages_per_pipeline_rank": null, + "microbatch_group_size_per_virtual_pipeline_stage": null, + "pipeline_model_parallel_layout": null, + "num_layers": 46, + "hidden_size": 4096, + "ffn_hidden_size": 10944, + "num_attention_heads": 96, + "group_query_attention": true, + "num_query_groups": 8, + "max_position_embeddings": 131072, + "position_embedding_type": "rope", + "mrope_section": null, + "rotary_base": 1000000, + "rotary_percent": 1.0, + "rotary_interleaved": false, + "normalization": "RMSNorm", + "norm_epsilon": 1e-05, + "swiglu": true, + "untie_embeddings_and_output_weights": true, + "disable_bias_linear": true, + "add_qkv_bias": true, + "attention_dropout": 0.0, + "hidden_dropout": 0.0, + "kv_channels": 128, + "qk_layernorm": false, + "transformer_impl": "transformer_engine", + "num_experts": 128, + "moe_layer_freq": "[0]*1+[1]*45", + "moe_ffn_hidden_size": 1408, + "moe_shared_expert_intermediate_size": 1408, + "moe_router_topk": 8, + "moe_router_pre_softmax": false, + "moe_router_dtype": "fp32", + "moe_router_score_function": "sigmoid", + "moe_router_bias_update_rate": 0.001, + "moe_router_enable_expert_bias": true, + "moe_router_topk_scaling_factor": 1.0, + "moe_router_load_balancing_type": "aux_loss", + "expert_model_parallel_size": 8, + "expert_tensor_parallel_size": 1, + "moe_token_dispatcher_type": null, + "moe_enable_deepep": false, + "moe_grouped_gemm": true, + "moe_permute_fusion": true, + "moe_aux_loss_coeff": 0.0005, + "moe_z_loss_coeff": null, + "moe_shared_expert_overlap": true, + "moe_layer_recompute": false, + "moe_expert_capacity_factor": null, + "moe_pad_expert_input_to_capacity": false, + "moe_token_drop_policy": null, + "multi_latent_attention": false, + "q_lora_rank": null, + "kv_lora_rank": 32, + "qk_head_dim": 128, + "qk_pos_emb_head_dim": 64, + "fp8_format": null, + "fp8_recipe": "delayed", + "fp8_amax_history_len": 1024, + "fp8_amax_compute_algo": "max", + "fp8_param_gather": false, + "fp16": false, + "bf16": true, + "apply_query_key_layer_scaling": false, + "attention_softmax_in_fp32": true, + "log_params_norm": false, + "log_throughput": false, + "tensorboard_log_interval": 1, + "tensorboard_queue_size": 50, + "log_timers_to_tensorboard": true, + "no_log_learning_rate_to_tensorboard": false, + "log_validation_ppl_to_tensorboard": true, + "log_memory_to_tensorboard": true, + "logging_level": null, + "wandb_project": "Megatron-Air-SFT", + "wandb_exp_name": "Iceblink-v3-SFT-1", + "wandb_save_dir": null, + "eval_iters": -1, + "eval_interval": 20, + "seq_length": 10280, + "num_workers": 8, + "megatron_extra_kwargs": {}, + "add_version": true, + "rank": 0, + "global_world_size": 8, + "local_world_size": 8, + "model_suffix": "GLM-4.5-Air", + "model_info": "ModelInfo(model_type='glm4_5', model_dir='/root/.cache/modelscope/hub/models/ZhipuAI/GLM-4___5-Air', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='glm4_5', model_groups=[ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.5-Air-Base', hf_model_id='zai-org/GLM-4.5-Air-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air', hf_model_id='zai-org/GLM-4.5-Air', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air-FP8', hf_model_id='zai-org/GLM-4.5-Air-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Base', hf_model_id='zai-org/GLM-4.5-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5', hf_model_id='zai-org/GLM-4.5', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-FP8', hf_model_id='zai-org/GLM-4.5-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.6', hf_model_id='zai-org/GLM-4.6', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='glm4_5', get_function=, model_arch=None, architectures=['Glm4MoeForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.54'], tags=[])", + "model_dir": "/root/.cache/modelscope/hub/models/ZhipuAI/GLM-4___5-Air", + "hub": "", + "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=, convert_hf2mcore=, model_cls=, convert_hf_config=, get_transformer_layer_spec=None, model_provider=, visual_cls=None, extra_args_provider=None)", + "extra_args": { + "use_ray": false, + "ray_exp_name": null, + "device_groups": null, + "model": "ZhipuAI/GLM-4.5-Air", + "model_type": "glm4_5", + "model_revision": null, + "task_type": "causal_lm", + "torch_dtype": "bfloat16", + "attn_impl": null, + "new_special_tokens": [], + "num_labels": null, + "problem_type": null, + "rope_scaling": null, + "device_map": null, + "max_memory": {}, + "max_model_len": null, + "local_repo_path": null, + "init_strategy": null, + "template": "glm4_5", + "system": null, + "max_length": 10280, + "truncation_strategy": "delete", + "max_pixels": null, + "agent_template": null, + "norm_bbox": null, + "use_chat_template": true, + "padding_free": true, + "padding_side": "right", + "sequence_parallel_size": 1, + "response_prefix": null, + "template_backend": "swift", + "dataset": [ + "/workspace/joined_dataset_cleaned_modified.jsonl" + ], + "val_dataset": [], + "split_dataset_ratio": 0.01, + "data_seed": 42, + "dataset_num_proc": 8, + "load_from_cache_file": true, + "dataset_shuffle": true, + "val_dataset_shuffle": false, + "streaming": false, + "interleave_prob": null, + "stopping_strategy": "first_exhausted", + "shuffle_buffer_size": 1000, + "download_mode": "reuse_dataset_if_exists", + "columns": {}, + "strict": false, + "remove_unused_columns": true, + "model_name": null, + "model_author": null, + "custom_dataset_info": [], + "quant_method": null, + "quant_bits": null, + "hqq_axis": null, + "bnb_4bit_compute_dtype": "bfloat16", + "bnb_4bit_quant_type": "nf4", + "bnb_4bit_use_double_quant": true, + "bnb_4bit_quant_storage": null, + "max_new_tokens": null, + "temperature": null, + "top_k": null, + "top_p": null, + "repetition_penalty": null, + "num_beams": 1, + "stream": false, + "stop_words": [], + "logprobs": false, + "top_logprobs": null, + "ckpt_dir": "/workspace/glm-4.5-air-mcore", + "lora_modules": [], + "tuner_backend": "peft", + "train_type": "lora", + "adapters": [], + "external_plugins": [], + "model_kwargs": {}, + "load_args": false, + "load_data_args": false, + "packing": true, + "packing_length": 10280, + "lazy_tokenize": false, + "cached_dataset": [], + "custom_register_path": [], + "use_hf": false, + "hub_token": null, + "ddp_timeout": 18000000, + "ddp_backend": null, + "ignore_args_error": false, + "use_swift_lora": false, + "freeze_llm": false, + "freeze_vit": true, + "freeze_aligner": true, + "freeze_parameters": [], + "freeze_parameters_regex": null, + "freeze_parameters_ratio": 0.0, + "trainable_parameters": [], + "trainable_parameters_regex": null, + "adapter_load": null, + "target_modules": [ + "all-linear" + ], + "target_regex": null, + "modules_to_save": [], + "lora_rank": 256, + "lora_alpha": 16, + "lora_dropout": 0.05, + "lora_bias": "none", + "lora_dtype": null, + "use_rslora": true, + "rlhf_type": null, + "ref_load": null, + "ref_adapter_load": null, + "beta": 0.1, + "rpo_alpha": null, + "reference_free": false, + "label_smoothing": 0.0, + "f_divergence_type": "reverse_kl", + "loss_type": null, + "desirable_weight": 1.0, + "undesirable_weight": 1.0, + "calculate_KL": null, + "center_rewards_coefficient": null, + "padded_vocab_size": 151552, + "initialize_embedding": false, + "mlp_padding_free": false, + "dataloader_persistent_workers": true, + "dataloader_prefetch_factor": 10, + "architectures": "Glm4MoeForCausalLM", + "llm_architectures": null, + "max_epochs": 2, + "enable_dft_loss": false, + "enable_channel_loss": false, + "original_max_position_embeddings": null, + "partial_rotary_factor": 0.5, + "use_shared_expert_gate": false, + "vit_gradient_checkpointing": true, + "gradient_checkpointing_kwargs": null, + "linear_num_value_heads": null, + "linear_num_key_heads": null, + "linear_key_head_dim": null, + "linear_value_head_dim": null, + "linear_conv_kernel_dim": null, + "layer_types": null, + "mrope_interleaved": false, + "add_version": true, + "model_info": "ModelInfo(model_type='glm4_5', model_dir='/root/.cache/modelscope/hub/models/ZhipuAI/GLM-4___5-Air', torch_dtype=torch.bfloat16, max_model_len=131072, quant_method=None, quant_bits=None, rope_scaling=None, is_moe_model=True, config=None, task_type='causal_lm', num_labels=None)", + "model_meta": "ModelMeta(model_type='glm4_5', model_groups=[ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.5-Air-Base', hf_model_id='zai-org/GLM-4.5-Air-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air', hf_model_id='zai-org/GLM-4.5-Air', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Air-FP8', hf_model_id='zai-org/GLM-4.5-Air-FP8', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-Base', hf_model_id='zai-org/GLM-4.5-Base', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5', hf_model_id='zai-org/GLM-4.5', model_path=None, ms_revision=None, hf_revision=None), Model(ms_model_id='ZhipuAI/GLM-4.5-FP8', hf_model_id='zai-org/GLM-4.5-FP8', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[]), ModelGroup(models=[Model(ms_model_id='ZhipuAI/GLM-4.6', hf_model_id='zai-org/GLM-4.6', model_path=None, ms_revision=None, hf_revision=None)], ignore_patterns=None, requires=None, tags=[])], template='glm4_5', get_function=, model_arch=None, architectures=['Glm4MoeForCausalLM'], additional_saved_files=[], torch_dtype=None, is_multimodal=False, is_reward=False, is_reranker=False, task_type=None, ignore_patterns=None, requires=['transformers>=4.54'], tags=[])", + "megatron_model_meta": "MegatronModelMeta(megatron_model_type='gpt', model_types=['qwen2', 'qwen2_5', 'qwq', 'qwq_preview', 'qwen2_5_math', 'llama', 'llama3', 'llama3_1', 'llama3_2', 'longwriter_llama3_1', 'codefuse_codellama', 'marco_o1', 'deepseek', 'deepseek_r1_distill', 'yi', 'yi_coder', 'sus', 'skywork_o1', 'openbuddy_llama', 'openbuddy_llama3', 'megrez', 'reflection', 'numina', 'ziya', 'mengzi3', 'qwen3', 'qwen3_thinking', 'qwen3_nothinking', 'qwen2_moe', 'qwen3_moe', 'qwen3_moe_thinking', 'qwen3_coder', 'internlm3', 'mimo', 'mimo_rl', 'moonlight', 'deepseek_moe', 'deepseek_v2', 'deepseek_v2_5', 'deepseek_r1', 'dots1', 'ernie', 'glm4_5', 'deepseek_v3_1', 'ernie_thinking'], convert_mcore2hf=, convert_hf2mcore=, model_cls=, convert_hf_config=, get_transformer_layer_spec=None, model_provider=, visual_cls=None, extra_args_provider=None)" + } +} diff --git a/chat_template.jinja b/chat_template.jinja new file mode 100644 index 0000000000000000000000000000000000000000..41478957aca7a04b7321022e7d1f73de5badd995 --- /dev/null +++ b/chat_template.jinja @@ -0,0 +1,103 @@ +[gMASK] +{%- if tools -%} +<|system|> +# Tools + +You may call one or more functions to assist with the user query. + +You are provided with function signatures within XML tags: + +{% for tool in tools %} +{{ tool | tojson(ensure_ascii=False) }} +{% endfor %} + + +For each function call, output the function name and arguments within the following XML format: +{function-name} +{arg-key-1} +{arg-value-1} +{arg-key-2} +{arg-value-2} +... +{%- endif -%} +{%- macro visible_text(content) -%} + {%- if content is string -%} + {{- content }} + {%- elif content is iterable and content is not mapping -%} + {%- for item in content -%} + {%- if item is mapping and item.type == 'text' -%} + {{- item.text }} + {%- elif item is string -%} + {{- item }} + {%- endif -%} + {%- endfor -%} + {%- else -%} + {{- content }} + {%- endif -%} +{%- endmacro -%} +{%- set ns = namespace(last_user_index=-1) %} +{%- for m in messages %} + {%- if m.role == 'user' %} + {% set ns.last_user_index = loop.index0 -%} + {%- endif %} +{%- endfor %} +{% for m in messages %} +{%- if m.role == 'user' -%}<|user|> +{{ visible_text(m.content) }} +{{- '/nothink' if (enable_thinking is defined and not enable_thinking and not visible_text(m.content).endswith("/nothink")) else '' -}} +{%- elif m.role == 'assistant' -%} +<|assistant|> +{%- set reasoning_content = '' %} +{%- set content = visible_text(m.content) %} +{%- if m.reasoning_content is string %} + {%- set reasoning_content = m.reasoning_content %} +{%- else %} + {%- if '' in content %} + {%- set reasoning_content = content.split('')[0].rstrip('\n').split('')[-1].lstrip('\n') %} + {%- set content = content.split('')[-1].lstrip('\n') %} + {%- endif %} +{%- endif %} +{%- if loop.index0 > ns.last_user_index and reasoning_content -%} +{{ '\n' + reasoning_content.strip() + ''}} +{%- else -%} +{{ '\n' }} +{%- endif -%} +{%- if content.strip() -%} +{{ '\n' + content.strip() }} +{%- endif -%} +{% if m.tool_calls %} +{% for tc in m.tool_calls %} +{%- if tc.function %} + {%- set tc = tc.function %} +{%- endif %} +{{ '\n' + tc.name }} +{% set _args = tc.arguments %} +{% for k, v in _args.items() %} +{{ k }} +{{ v | tojson(ensure_ascii=False) if v is not string else v }} +{% endfor %} +{% endfor %} +{% endif %} +{%- elif m.role == 'tool' -%} +{%- if m.content is string -%} +{%- if loop.first or (messages[loop.index0 - 1].role != "tool") %} + {{- '<|observation|>' }} +{%- endif %} +{{- '\n\n' }} +{{- m.content }} +{{- '\n' }} +{%- else -%} +<|observation|>{% for tr in m.content %} + + +{{ tr.output if tr.output is defined else tr }} +{% endfor -%} +{% endif -%} +{%- elif m.role == 'system' -%} +<|system|> +{{ visible_text(m.content) }} +{%- endif -%} +{%- endfor -%} +{%- if add_generation_prompt -%} + <|assistant|>{{- '\n' if (enable_thinking is defined and not enable_thinking) else '' -}} +{%- endif -%} \ No newline at end of file diff --git a/config.json b/config.json new file mode 100644 index 0000000000000000000000000000000000000000..a6564e0411c83505312c49aee6445ee131ed0c83 --- /dev/null +++ b/config.json @@ -0,0 +1,43 @@ +{ + "architectures": [ + "Glm4MoeForCausalLM" + ], + "attention_bias": true, + "attention_dropout": 0.0, + "dtype": "bfloat16", + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "first_k_dense_replace": 1, + "head_dim": 128, + "hidden_act": "silu", + "hidden_size": 4096, + "initializer_range": 0.02, + "intermediate_size": 10944, + "max_position_embeddings": 131072, + "model_type": "glm4_moe", + "moe_intermediate_size": 1408, + "n_group": 1, + "n_routed_experts": 128, + "n_shared_experts": 1, + "norm_topk_prob": true, + "num_attention_heads": 96, + "num_experts_per_tok": 8, + "num_hidden_layers": 46, + "num_key_value_heads": 8, + "num_nextn_predict_layers": 1, + "pad_token_id": 151329, + "partial_rotary_factor": 0.5, + "rms_norm_eps": 1e-05, + "rope_scaling": null, + "rope_theta": 1000000, + "routed_scaling_factor": 1.0, + "tie_word_embeddings": false, + "topk_group": 1, + "transformers_version": "4.57.1", + "use_cache": true, + "use_qk_norm": false, + "vocab_size": 151552 +} diff --git a/generation_config.json b/generation_config.json new file mode 100644 index 0000000000000000000000000000000000000000..6bb9c9cef0d638ddd6e98ce0695d630c45acc6a5 --- /dev/null +++ b/generation_config.json @@ -0,0 +1,10 @@ +{ + "_from_model_config": true, + "eos_token_id": [ + 151329, + 151336, + 151338 + ], + "pad_token_id": 151329, + "transformers_version": "4.57.1" +} diff --git a/model-00001-of-00043.safetensors b/model-00001-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a16c1c6eace72b7549e41b048a06475d6d9b7a95 --- /dev/null +++ b/model-00001-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37639ec42fc97943ccf32767591cae3dc91e08acf7345fd34c40d8ec5118c879 +size 4991854888 diff --git a/model-00002-of-00043.safetensors b/model-00002-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8d0dc192aaa694bb4aa222063c8e672ff3b4f6eb --- /dev/null +++ b/model-00002-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e1939bfea34981074cb751a23833688193a692124ff4791b11f11cd16048e8e +size 4994465672 diff --git a/model-00003-of-00043.safetensors b/model-00003-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..69fe2620c49afcdd90703f247083b39606e1c890 --- /dev/null +++ b/model-00003-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306adc29236fec4e3fd8faf76adb83186753bab68e590e4bcecbd0f5e138401b +size 4994465696 diff --git a/model-00004-of-00043.safetensors b/model-00004-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..bc380769dda558459ca9cf89f2c721d3bdb3e5ee --- /dev/null +++ b/model-00004-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c122f3159e1cdd3d6f9d8ac038b27fcbf1ff7cd27d58cb6ca16664e42e60737a +size 4994465696 diff --git a/model-00005-of-00043.safetensors b/model-00005-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..89565cc68a5747ea2e649cbb25978a3db6f3061d --- /dev/null +++ b/model-00005-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7bd72817a2584a1befd52e547654c18c15dd541d4611cebe0bb3e1b128a04acc +size 4994465696 diff --git a/model-00006-of-00043.safetensors b/model-00006-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..106091f3c70caa25765fe83fd11bd32d58d007e6 --- /dev/null +++ b/model-00006-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad4e5941cfeeba9ca6d576675be5be2d2b3ba0bff5df1fda94ff4a1e629fe9cb +size 4974587952 diff --git a/model-00007-of-00043.safetensors b/model-00007-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48e8ecb377675a0ca194379a7c35051c19712837 --- /dev/null +++ b/model-00007-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fae46b20e23147bac48c74099e7d8e7ffcf088f763961cfa1bd0c86d532bc299 +size 4991318928 diff --git a/model-00008-of-00043.safetensors b/model-00008-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6dbeaf8e7c05bea2918851068d3a05570837ef9c --- /dev/null +++ b/model-00008-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6480fc83a8e8de6ed9864c7f5ff6082d00c9ed370ad438ad2dee96ec4978a2 +size 4994465664 diff --git a/model-00009-of-00043.safetensors b/model-00009-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..aa899a68944ff01f2171678edb0ec65a771df8b5 --- /dev/null +++ b/model-00009-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b69c78a10644794b5acea498179409aa7884ac0df573c3222d9e7d1d2ab1a90f +size 4994465784 diff --git a/model-00010-of-00043.safetensors b/model-00010-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9934a3fc9eb4f523fd843a4752eb082b7fb94abb --- /dev/null +++ b/model-00010-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:240b5d748bbd524acc23fadc1bd0abfe7a0a7ade9159d0fe4d74e54ca3ebe5a3 +size 4994466104 diff --git a/model-00011-of-00043.safetensors b/model-00011-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..cb96bba729b7d00d987755c0e24b8228c5249170 --- /dev/null +++ b/model-00011-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:348bd51624d1c015ba118fd6428d916b9eb37a2a661ad68c9541995c0191a8bc +size 4994466104 diff --git a/model-00012-of-00043.safetensors b/model-00012-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..774cdf05a34d6c2c9cef1593c9c58c3036f28f3a --- /dev/null +++ b/model-00012-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b133d39a2f249c53ae7c0cd92d745874fa012896c9233a5eb03378e32440229 +size 4994466104 diff --git a/model-00013-of-00043.safetensors b/model-00013-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..48fbbb53ff22a15bd1261212890ce28d23752512 --- /dev/null +++ b/model-00013-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1067ec336c66450a781d02d27cd266fb4522bfd7f3caae54d556b5e76415bbec +size 4994466104 diff --git a/model-00014-of-00043.safetensors b/model-00014-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9fd94c6258bfe3a91e73f0fa007ed15432b1a9b4 --- /dev/null +++ b/model-00014-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ae01e88f3f47c16356157499e051210ea26ae5bfb94554e0ec7375cf6369558 +size 4994466104 diff --git a/model-00015-of-00043.safetensors b/model-00015-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..948967cc90c5b2cf764df628047eaef592809ca6 --- /dev/null +++ b/model-00015-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb240a8c63c072cdbe9e0d0fe4bb21dd5bd69097e2f5d533bb296f802de4a5c8 +size 4994466104 diff --git a/model-00016-of-00043.safetensors b/model-00016-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..8a6913235ba71e0a73eb4ecc7bff24d3b21bc293 --- /dev/null +++ b/model-00016-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae8f780a4e98896a5cdec39476173faa9146850801d175a74025aedd76a8bba2 +size 4994466104 diff --git a/model-00017-of-00043.safetensors b/model-00017-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1806241c018c5d4f93c25475d4986c1ba6cc7b65 --- /dev/null +++ b/model-00017-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c33ac6b45306e75dc3dd41014517343a3a6d1fd9aa1ac17dc85776d23650b9e +size 4994466104 diff --git a/model-00018-of-00043.safetensors b/model-00018-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..5830d67565ba9a1d11c7bc4b071601dbc085d8a2 --- /dev/null +++ b/model-00018-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1effe91c6c53ef0e7b30b4e6bd00bce3dabcb770ae905cefbbef636a7390c8 +size 4994466112 diff --git a/model-00019-of-00043.safetensors b/model-00019-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..46e1542ef0b7ae89eaef54eecb79186649f5c8a4 --- /dev/null +++ b/model-00019-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99d3aab8293ef8e98eeeed7f4d418dd233b4aa5f4d6c570be3959068dd7f11d5 +size 4994466120 diff --git a/model-00020-of-00043.safetensors b/model-00020-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9ade2112b24037432fed7c409ad6fa14c6354c9d --- /dev/null +++ b/model-00020-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:819de2744c126a9472a239dfdd97fceb67e3fd554c6a1ced85bb075015ba2e70 +size 4994466120 diff --git a/model-00021-of-00043.safetensors b/model-00021-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..204b0c9b573c7990b53c9c98dd5ba1d1a68c182c --- /dev/null +++ b/model-00021-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1da88df140bf43acc805e403aa48041d173fa339cc1a827fae60b66d6e9e715 +size 4992409992 diff --git a/model-00022-of-00043.safetensors b/model-00022-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1e481df3a431a93a0317837cb6334e81dfff3acb --- /dev/null +++ b/model-00022-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e7ae936a92c97415b76fbf9c343834055311065c946f6adc097a24efb21cd53 +size 4996566656 diff --git a/model-00023-of-00043.safetensors b/model-00023-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6921828fa6ec3cdedf9468410ac217ce2d3d8095 --- /dev/null +++ b/model-00023-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4af23f53b359da50cadecf2615fbba2db6c7a9e5f17f4b42504d5b48978ff36 +size 4994466088 diff --git a/model-00024-of-00043.safetensors b/model-00024-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ac7c50e478bb69a2c7120573214a9acdb72a03e0 --- /dev/null +++ b/model-00024-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e600022626722fc1a27d2b1c7e2abe44011210f5740470f2b480b1852f4f75f8 +size 4994466104 diff --git a/model-00025-of-00043.safetensors b/model-00025-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..956c2635fd5e2992eff8da98a94ac0f23680bb7a --- /dev/null +++ b/model-00025-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e15b5cf247594f7beee01c7b76e76159034c2c16151d65b6d83b729c1219cb8 +size 4994466104 diff --git a/model-00026-of-00043.safetensors b/model-00026-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1c35f23958c98c58d028190bb627f8f6d2234e25 --- /dev/null +++ b/model-00026-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7950789e57ba1c211b76e2eb2f7f9d504c4ebd02422311a3e66c929a5c5d4636 +size 4994466104 diff --git a/model-00027-of-00043.safetensors b/model-00027-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..9f27a1f16db3775435927d3d7204634f61618856 --- /dev/null +++ b/model-00027-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd9afe43c15516d09c99813fdfc1fd71dc9f5ad83ff458f7ca9bf4c7949f577c +size 4994466104 diff --git a/model-00028-of-00043.safetensors b/model-00028-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..d7f226d4d8d531057759d5a625c968bb6b8e6561 --- /dev/null +++ b/model-00028-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c966254ec6db47d72fd0410f712330c4167f03846d0298fb3124d68fc474ef +size 4994466104 diff --git a/model-00029-of-00043.safetensors b/model-00029-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..58c0a8775504fff5c32134fedd6bf37d3d102d17 --- /dev/null +++ b/model-00029-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5939de91bff11a2deed12e68eb489198ba10cb6fd6566874bf997a1edfb54701 +size 4994466104 diff --git a/model-00030-of-00043.safetensors b/model-00030-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..2bc584fc45ac30f1aedc4c7643325620c3cbd562 --- /dev/null +++ b/model-00030-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55613837eb1a3d20ca416944023a6b6f1760d97ae053c876cf223d32238fadbd +size 4994466104 diff --git a/model-00031-of-00043.safetensors b/model-00031-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a6a2c3072029b0bd7be3b040d1d7e8862e808613 --- /dev/null +++ b/model-00031-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b371a2c51ee9e62b6a2fd29c50d41c5dc29a5d078c32406d86e6db4e8eb16d7 +size 4994466104 diff --git a/model-00032-of-00043.safetensors b/model-00032-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..623aac0b8d3763ab665466775ccd1009d9a0d3c6 --- /dev/null +++ b/model-00032-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457e4928c935d2546a7bc209dc92c696f648b700d836381279f5fe44a78d81f3 +size 4994466104 diff --git a/model-00033-of-00043.safetensors b/model-00033-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..57a555ff36bee84e2bb03f41e96a9ddee134b62f --- /dev/null +++ b/model-00033-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9532ddc08b2c89c4bccbe0c2001bf1da622004841460d919002622ffaa9d48a +size 4994466112 diff --git a/model-00035-of-00043.safetensors b/model-00035-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..926a2afe81d27a6427c756b5c30edb78c9065e87 --- /dev/null +++ b/model-00035-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f540c11eeee253a19dd68faed3cbd369e3be606597737a638cc39b28a4949a63 +size 4994466120 diff --git a/model-00036-of-00043.safetensors b/model-00036-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..6b1ffa87f1b74b42ca29695f3fec10c24754d049 --- /dev/null +++ b/model-00036-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:856683d83c4e7a5ab8f5ce2fe70596d56f40db5b29076e879fcd755355954d05 +size 4903256352 diff --git a/model-00037-of-00043.safetensors b/model-00037-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..a71d20d4ceed089895b73641171fc4a39d4fa794 --- /dev/null +++ b/model-00037-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a15089c9135ecd10ec2416a338960e8bdfae017bfe53d7636bedd9c5cdd2c3a +size 4993444616 diff --git a/model-00038-of-00043.safetensors b/model-00038-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..7d8249a141abb5cbdfbeefebdbd0af8505021eb6 --- /dev/null +++ b/model-00038-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e3599aa802a524d2cd1feb3dcb5ab44804770c883aac764c61331acc5247c69 +size 4994466080 diff --git a/model-00039-of-00043.safetensors b/model-00039-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..375c53c3fc8b16afc97aa2d8a97407d49b5d8d49 --- /dev/null +++ b/model-00039-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b05e5a3f5c334fe4f2f9802cd858c8825ad2ca41635e44cd388bc9420f99e15 +size 4994466104 diff --git a/model-00040-of-00043.safetensors b/model-00040-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..ee0041fa73bcee4ff997d7eb44977b859fd4d551 --- /dev/null +++ b/model-00040-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aeb2d838cb73505772f4b13f319b405e56d26fdc0478f8fa75b7fceb18b779a +size 4994466104 diff --git a/model-00041-of-00043.safetensors b/model-00041-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..c2aa68e0945e68bbb6b2040788d72898dbb5a73a --- /dev/null +++ b/model-00041-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aa75cf6c629e660807fc554384f5ee0af2c022b50765e7d1d6fc920f1c6fd49 +size 4994466104 diff --git a/model-00042-of-00043.safetensors b/model-00042-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..3d9f485cd6310a48b383e6bb508fd7a55e93cac3 --- /dev/null +++ b/model-00042-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d0b67b4c40bd6a3cfde6c9f95ad0ab516cdf722927c82f6f585816a7fadf279 +size 4994466104 diff --git a/model-00043-of-00043.safetensors b/model-00043-of-00043.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..1558df703b08bd7f8c674297929e7ee0ada8171f --- /dev/null +++ b/model-00043-of-00043.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7aeb6d063560105a06d50e8629632d6cad53e88280112b82e9909243c2863a5 +size 4056996976 diff --git a/model.safetensors.index.json b/model.safetensors.index.json new file mode 100644 index 0000000000000000000000000000000000000000..2e68b41cb57bf9f0df939e16bc06eae4c958ad34 --- /dev/null +++ b/model.safetensors.index.json @@ -0,0 +1,17933 @@ +{ + "metadata": { + "total_parameters": 106852245504, + "total_size": 213704514048 + }, + "weight_map": { + "lm_head.weight": "model-00043-of-00043.safetensors", + "model.embed_tokens.weight": "model-00001-of-00043.safetensors", + "model.layers.0.input_layernorm.weight": "model-00001-of-00043.safetensors", + "model.layers.0.mlp.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.mlp.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.input_layernorm.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.0.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.0.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.0.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.1.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.1.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.1.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.10.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.10.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.10.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.100.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.100.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.100.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.101.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.101.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.101.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.102.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.102.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.102.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.103.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.103.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.103.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.104.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.104.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.104.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.105.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.105.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.105.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.106.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.106.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.106.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.107.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.107.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.107.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.108.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.108.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.108.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.109.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.109.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.109.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.11.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.11.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.11.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.110.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.110.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.110.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.111.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.111.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.111.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.112.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.112.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.112.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.113.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.113.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.113.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.114.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.114.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.114.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.115.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.115.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.115.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.116.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.116.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.116.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.117.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.117.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.117.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.118.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.118.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.118.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.119.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.119.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.119.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.12.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.12.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.12.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.120.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.120.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.120.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.121.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.121.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.121.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.122.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.122.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.122.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.123.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.123.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.123.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.124.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.124.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.124.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.125.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.125.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.125.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.126.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.126.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.126.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.127.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.127.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.127.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.13.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.13.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.13.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.14.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.14.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.14.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.15.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.15.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.15.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.16.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.16.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.16.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.17.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.17.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.17.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.18.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.18.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.18.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.19.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.19.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.19.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.2.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.2.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.2.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.20.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.20.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.20.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.21.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.21.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.21.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.22.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.22.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.22.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.23.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.23.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.23.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.24.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.24.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.24.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.25.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.25.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.25.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.26.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.26.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.26.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.27.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.27.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.27.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.28.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.28.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.28.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.29.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.29.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.29.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.3.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.3.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.3.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.30.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.30.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.30.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.31.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.31.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.31.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.32.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.32.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.32.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.33.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.33.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.33.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.34.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.34.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.34.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.35.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.35.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.35.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.36.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.36.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.36.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.37.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.37.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.37.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.38.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.38.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.38.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.39.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.39.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.39.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.4.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.4.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.4.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.40.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.40.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.40.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.41.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.41.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.41.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.42.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.42.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.42.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.43.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.43.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.43.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.44.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.44.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.44.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.45.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.45.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.45.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.46.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.46.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.46.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.47.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.47.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.47.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.48.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.48.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.48.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.49.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.49.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.49.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.5.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.5.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.5.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.50.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.50.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.50.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.51.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.51.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.51.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.52.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.52.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.52.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.53.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.53.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.53.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.54.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.54.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.54.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.55.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.55.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.55.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.56.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.56.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.56.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.57.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.57.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.57.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.58.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.58.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.58.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.59.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.59.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.59.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.6.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.6.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.6.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.60.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.60.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.60.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.61.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.61.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.61.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.62.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.62.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.62.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.63.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.63.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.63.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.64.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.64.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.64.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.65.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.65.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.65.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.66.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.66.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.66.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.67.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.67.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.67.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.68.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.68.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.68.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.69.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.69.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.69.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.7.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.7.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.7.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.70.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.70.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.70.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.71.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.71.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.71.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.72.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.72.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.72.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.73.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.73.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.73.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.74.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.74.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.74.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.75.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.75.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.75.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.76.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.76.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.76.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.77.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.77.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.77.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.78.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.78.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.78.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.79.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.79.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.79.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.8.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.8.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.8.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.80.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.80.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.80.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.81.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.81.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.81.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.82.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.82.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.82.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.83.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.83.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.83.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.84.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.84.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.84.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.85.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.85.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.85.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.86.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.86.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.86.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.87.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.87.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.87.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.88.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.88.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.88.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.89.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.89.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.89.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.9.down_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.9.gate_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.9.up_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.mlp.experts.90.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.90.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.90.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.91.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.91.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.91.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.92.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.92.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.92.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.93.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.93.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.93.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.94.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.94.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.94.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.95.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.95.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.95.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.96.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.96.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.96.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.97.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.97.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.97.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.98.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.98.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.98.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.99.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.99.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.experts.99.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.gate.e_score_correction_bias": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.gate.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.shared_experts.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.shared_experts.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.mlp.shared_experts.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00043.safetensors", + "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00043.safetensors", + "model.layers.10.input_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.0.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.0.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.0.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.1.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.1.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.1.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.10.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.10.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.10.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.100.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.100.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.100.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.101.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.101.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.101.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.102.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.102.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.102.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.103.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.103.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.103.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.104.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.104.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.104.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.105.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.105.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.105.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.106.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.106.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.106.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.107.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.107.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.107.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.108.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.108.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.108.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.109.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.109.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.109.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.11.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.11.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.11.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.110.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.110.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.110.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.111.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.111.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.111.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.112.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.112.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.112.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.113.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.113.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.113.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.114.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.114.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.114.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.115.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.115.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.115.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.116.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.116.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.116.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.117.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.117.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.117.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.118.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.118.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.118.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.119.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.119.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.119.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.12.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.12.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.12.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.120.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.120.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.120.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.121.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.121.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.121.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.122.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.122.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.122.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.123.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.123.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.123.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.124.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.124.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.124.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.125.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.125.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.125.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.126.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.126.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.126.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.127.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.127.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.127.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.13.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.13.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.13.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.14.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.14.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.14.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.15.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.15.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.15.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.16.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.16.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.16.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.17.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.17.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.17.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.18.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.18.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.18.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.19.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.19.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.19.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.2.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.2.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.2.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.20.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.20.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.20.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.21.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.21.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.21.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.22.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.22.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.22.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.23.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.23.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.23.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.24.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.24.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.24.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.25.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.25.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.25.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.26.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.26.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.26.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.27.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.27.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.27.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.28.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.28.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.28.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.29.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.29.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.29.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.3.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.3.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.3.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.30.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.30.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.30.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.31.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.31.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.31.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.32.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.32.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.32.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.33.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.33.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.33.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.34.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.34.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.34.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.35.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.35.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.35.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.36.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.36.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.36.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.37.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.37.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.37.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.38.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.38.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.38.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.39.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.39.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.39.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.4.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.4.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.4.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.40.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.40.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.40.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.41.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.41.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.41.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.42.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.42.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.42.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.43.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.43.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.43.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.44.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.44.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.44.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.45.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.45.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.45.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.46.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.46.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.46.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.47.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.47.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.47.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.48.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.48.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.48.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.49.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.49.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.49.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.5.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.5.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.5.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.50.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.50.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.50.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.51.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.51.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.51.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.52.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.52.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.52.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.53.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.53.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.53.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.54.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.54.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.54.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.55.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.55.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.55.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.56.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.56.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.56.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.57.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.57.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.57.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.58.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.58.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.58.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.59.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.59.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.59.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.6.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.6.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.6.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.60.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.60.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.60.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.61.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.61.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.61.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.62.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.62.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.62.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.63.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.63.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.63.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.64.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.64.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.64.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.65.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.65.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.65.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.66.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.66.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.66.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.67.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.67.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.67.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.68.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.68.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.68.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.69.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.69.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.69.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.7.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.7.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.7.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.70.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.70.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.70.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.71.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.71.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.71.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.72.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.72.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.72.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.73.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.73.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.73.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.74.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.74.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.74.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.75.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.75.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.75.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.76.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.76.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.76.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.77.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.77.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.77.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.78.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.78.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.78.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.79.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.79.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.79.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.8.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.8.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.8.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.80.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.80.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.80.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.81.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.81.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.81.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.82.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.82.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.82.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.83.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.83.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.83.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.84.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.84.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.84.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.85.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.85.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.85.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.86.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.86.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.86.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.87.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.87.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.87.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.88.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.88.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.88.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.89.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.89.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.89.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.9.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.9.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.9.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.mlp.experts.90.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.90.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.90.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.91.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.91.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.91.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.92.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.92.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.92.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.93.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.93.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.93.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.94.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.94.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.94.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.95.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.95.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.95.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.96.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.96.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.96.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.97.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.97.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.97.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.98.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.98.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.98.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.99.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.99.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.experts.99.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.gate.e_score_correction_bias": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.gate.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.10.post_attention_layernorm.weight": "model-00010-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.k_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.o_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.q_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.bias": "model-00009-of-00043.safetensors", + "model.layers.10.self_attn.v_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.11.input_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.0.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.0.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.0.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.1.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.1.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.1.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.10.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.10.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.10.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.100.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.100.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.100.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.101.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.101.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.101.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.102.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.102.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.102.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.103.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.103.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.103.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.104.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.104.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.104.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.105.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.105.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.105.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.106.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.106.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.106.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.107.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.107.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.107.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.108.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.108.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.108.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.109.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.109.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.109.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.11.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.11.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.11.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.110.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.110.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.110.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.111.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.111.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.111.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.112.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.112.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.112.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.113.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.113.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.113.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.114.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.114.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.114.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.115.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.115.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.115.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.116.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.116.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.116.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.117.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.117.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.117.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.118.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.118.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.118.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.119.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.119.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.119.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.12.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.12.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.12.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.120.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.120.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.120.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.121.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.121.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.121.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.122.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.122.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.122.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.123.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.123.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.123.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.124.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.124.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.124.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.125.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.125.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.125.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.126.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.126.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.126.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.127.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.127.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.127.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.13.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.13.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.13.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.14.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.14.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.14.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.15.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.15.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.15.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.16.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.16.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.16.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.17.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.17.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.17.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.18.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.18.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.18.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.19.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.19.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.19.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.2.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.2.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.2.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.20.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.20.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.20.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.21.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.21.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.21.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.22.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.22.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.22.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.23.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.23.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.23.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.24.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.24.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.24.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.25.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.25.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.25.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.26.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.26.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.26.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.27.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.27.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.27.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.28.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.28.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.28.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.29.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.29.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.29.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.3.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.3.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.3.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.30.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.30.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.30.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.31.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.31.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.31.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.32.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.32.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.32.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.33.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.33.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.33.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.34.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.34.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.34.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.35.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.35.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.35.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.36.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.36.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.36.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.37.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.37.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.37.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.38.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.38.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.38.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.39.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.39.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.39.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.4.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.4.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.4.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.40.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.40.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.40.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.41.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.41.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.41.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.42.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.42.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.42.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.43.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.43.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.43.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.44.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.44.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.44.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.45.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.45.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.45.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.46.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.46.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.46.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.47.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.47.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.47.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.48.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.48.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.48.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.49.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.49.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.49.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.5.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.5.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.5.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.50.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.50.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.50.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.51.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.51.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.51.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.52.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.52.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.52.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.53.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.53.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.53.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.54.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.54.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.54.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.55.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.55.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.55.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.56.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.56.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.56.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.57.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.57.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.57.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.58.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.58.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.58.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.59.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.59.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.59.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.6.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.6.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.6.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.60.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.60.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.60.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.61.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.61.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.61.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.62.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.62.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.62.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.63.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.63.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.63.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.64.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.64.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.64.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.65.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.65.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.65.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.66.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.66.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.66.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.67.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.67.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.67.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.68.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.68.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.68.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.69.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.69.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.69.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.7.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.7.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.7.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.70.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.70.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.70.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.71.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.71.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.71.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.72.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.72.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.72.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.73.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.73.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.73.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.74.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.74.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.74.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.75.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.75.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.75.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.76.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.76.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.76.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.77.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.77.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.77.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.78.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.78.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.78.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.79.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.79.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.79.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.8.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.8.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.8.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.80.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.80.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.80.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.81.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.81.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.81.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.82.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.82.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.82.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.83.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.83.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.83.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.84.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.84.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.84.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.85.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.85.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.85.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.86.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.86.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.86.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.87.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.87.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.87.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.88.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.88.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.88.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.89.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.89.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.89.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.9.down_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.9.gate_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.9.up_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.mlp.experts.90.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.90.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.90.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.91.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.91.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.91.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.92.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.92.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.92.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.93.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.93.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.93.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.94.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.94.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.94.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.95.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.95.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.95.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.96.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.96.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.96.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.97.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.97.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.97.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.98.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.98.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.98.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.99.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.99.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.experts.99.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.gate.e_score_correction_bias": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.gate.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.11.post_attention_layernorm.weight": "model-00011-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.k_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.o_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.q_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.bias": "model-00010-of-00043.safetensors", + "model.layers.11.self_attn.v_proj.weight": "model-00010-of-00043.safetensors", + "model.layers.12.input_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.0.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.0.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.0.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.1.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.1.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.1.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.10.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.10.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.10.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.100.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.100.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.100.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.101.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.101.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.101.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.102.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.102.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.102.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.103.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.103.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.103.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.104.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.104.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.104.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.105.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.105.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.105.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.106.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.106.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.106.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.107.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.107.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.107.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.108.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.108.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.108.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.109.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.109.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.109.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.11.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.11.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.11.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.110.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.110.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.110.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.111.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.111.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.111.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.112.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.112.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.112.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.113.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.113.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.113.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.114.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.114.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.114.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.115.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.115.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.115.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.116.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.116.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.116.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.117.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.117.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.117.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.118.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.118.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.118.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.119.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.119.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.119.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.12.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.12.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.12.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.120.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.120.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.120.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.121.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.121.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.121.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.122.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.122.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.122.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.123.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.123.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.123.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.124.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.124.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.124.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.125.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.125.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.125.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.126.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.126.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.126.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.127.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.127.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.127.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.13.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.13.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.13.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.14.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.14.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.14.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.15.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.15.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.15.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.16.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.16.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.16.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.17.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.17.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.17.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.18.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.18.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.18.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.19.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.19.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.19.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.2.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.2.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.2.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.20.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.20.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.20.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.21.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.21.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.21.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.22.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.22.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.22.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.23.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.23.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.23.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.24.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.24.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.24.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.25.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.25.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.25.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.26.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.26.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.26.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.27.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.27.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.27.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.28.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.28.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.28.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.29.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.29.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.29.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.3.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.3.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.3.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.30.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.30.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.30.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.31.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.31.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.31.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.32.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.32.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.32.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.33.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.33.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.33.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.34.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.34.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.34.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.35.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.35.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.35.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.36.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.36.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.36.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.37.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.37.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.37.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.38.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.38.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.38.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.39.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.39.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.39.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.4.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.4.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.4.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.40.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.40.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.40.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.41.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.41.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.41.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.42.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.42.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.42.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.43.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.43.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.43.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.44.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.44.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.44.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.45.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.45.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.45.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.46.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.46.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.46.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.47.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.47.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.47.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.48.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.48.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.48.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.49.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.49.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.49.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.5.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.5.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.5.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.50.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.50.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.50.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.51.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.51.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.51.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.52.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.52.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.52.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.53.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.53.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.53.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.54.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.54.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.54.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.55.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.55.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.55.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.56.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.56.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.56.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.57.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.57.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.57.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.58.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.58.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.58.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.59.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.59.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.59.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.6.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.6.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.6.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.60.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.60.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.60.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.61.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.61.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.61.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.62.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.62.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.62.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.63.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.63.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.63.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.64.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.64.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.64.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.65.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.65.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.65.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.66.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.66.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.66.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.67.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.67.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.67.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.68.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.68.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.68.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.69.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.69.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.69.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.7.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.7.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.7.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.70.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.70.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.70.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.71.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.71.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.71.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.72.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.72.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.72.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.73.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.73.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.73.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.74.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.74.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.74.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.75.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.75.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.75.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.76.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.76.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.76.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.77.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.77.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.77.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.78.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.78.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.78.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.79.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.79.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.79.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.8.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.8.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.8.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.80.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.80.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.80.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.81.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.81.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.81.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.82.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.82.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.82.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.83.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.83.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.83.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.84.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.84.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.84.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.85.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.85.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.85.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.86.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.86.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.86.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.87.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.87.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.87.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.88.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.88.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.88.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.89.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.89.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.89.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.9.down_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.9.gate_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.9.up_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.mlp.experts.90.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.90.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.90.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.91.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.91.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.91.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.92.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.92.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.92.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.93.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.93.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.93.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.94.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.94.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.94.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.95.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.95.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.95.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.96.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.96.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.96.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.97.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.97.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.97.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.98.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.98.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.98.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.99.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.99.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.experts.99.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.gate.e_score_correction_bias": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.gate.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.12.post_attention_layernorm.weight": "model-00012-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.k_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.o_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.q_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.bias": "model-00011-of-00043.safetensors", + "model.layers.12.self_attn.v_proj.weight": "model-00011-of-00043.safetensors", + "model.layers.13.input_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.0.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.0.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.0.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.1.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.1.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.1.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.10.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.10.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.10.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.100.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.100.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.100.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.101.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.101.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.101.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.102.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.102.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.102.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.103.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.103.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.103.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.104.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.104.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.104.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.105.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.105.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.105.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.106.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.106.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.106.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.107.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.107.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.107.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.108.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.108.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.108.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.109.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.109.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.109.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.11.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.11.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.11.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.110.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.110.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.110.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.111.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.111.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.111.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.112.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.112.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.112.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.113.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.113.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.113.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.114.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.114.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.114.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.115.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.115.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.115.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.116.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.116.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.116.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.117.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.117.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.117.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.118.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.118.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.118.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.119.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.119.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.119.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.12.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.12.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.12.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.120.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.120.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.120.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.121.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.121.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.121.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.122.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.122.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.122.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.123.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.123.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.123.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.124.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.124.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.124.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.125.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.125.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.125.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.126.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.126.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.126.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.127.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.127.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.127.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.13.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.13.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.13.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.14.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.14.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.14.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.15.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.15.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.15.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.16.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.16.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.16.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.17.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.17.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.17.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.18.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.18.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.18.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.19.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.19.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.19.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.2.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.2.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.2.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.20.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.20.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.20.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.21.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.21.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.21.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.22.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.22.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.22.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.23.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.23.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.23.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.24.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.24.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.24.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.25.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.25.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.25.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.26.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.26.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.26.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.27.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.27.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.27.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.28.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.28.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.28.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.29.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.29.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.29.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.3.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.3.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.3.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.30.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.30.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.30.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.31.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.31.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.31.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.32.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.32.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.32.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.33.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.33.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.33.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.34.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.34.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.34.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.35.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.35.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.35.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.36.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.36.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.36.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.37.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.37.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.37.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.38.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.38.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.38.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.39.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.39.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.39.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.4.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.4.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.4.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.40.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.40.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.40.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.41.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.41.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.41.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.42.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.42.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.42.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.43.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.43.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.43.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.44.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.44.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.44.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.45.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.45.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.45.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.46.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.46.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.46.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.47.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.47.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.47.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.48.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.48.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.48.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.49.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.49.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.49.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.5.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.5.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.5.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.50.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.50.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.50.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.51.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.51.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.51.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.52.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.52.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.52.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.53.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.53.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.53.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.54.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.54.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.54.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.55.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.55.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.55.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.56.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.56.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.56.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.57.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.57.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.57.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.58.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.58.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.58.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.59.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.59.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.59.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.6.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.6.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.6.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.60.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.60.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.60.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.61.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.61.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.61.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.62.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.62.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.62.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.63.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.63.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.63.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.64.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.64.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.64.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.65.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.65.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.65.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.66.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.66.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.66.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.67.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.67.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.67.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.68.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.68.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.68.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.69.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.69.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.69.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.7.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.7.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.7.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.70.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.70.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.70.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.71.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.71.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.71.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.72.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.72.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.72.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.73.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.73.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.73.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.74.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.74.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.74.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.75.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.75.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.75.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.76.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.76.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.76.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.77.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.77.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.77.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.78.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.78.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.78.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.79.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.79.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.79.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.8.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.8.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.8.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.80.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.80.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.80.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.81.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.81.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.81.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.82.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.82.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.82.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.83.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.83.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.83.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.84.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.84.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.84.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.85.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.85.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.85.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.86.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.86.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.86.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.87.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.87.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.87.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.88.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.88.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.88.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.89.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.89.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.89.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.9.down_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.9.gate_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.9.up_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.mlp.experts.90.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.90.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.90.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.91.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.91.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.91.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.92.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.92.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.92.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.93.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.93.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.93.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.94.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.94.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.94.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.95.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.95.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.95.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.96.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.96.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.96.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.97.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.97.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.97.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.98.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.98.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.98.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.99.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.99.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.experts.99.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.gate.e_score_correction_bias": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.gate.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.13.post_attention_layernorm.weight": "model-00013-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.k_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.o_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.q_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.bias": "model-00012-of-00043.safetensors", + "model.layers.13.self_attn.v_proj.weight": "model-00012-of-00043.safetensors", + "model.layers.14.input_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.0.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.0.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.0.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.1.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.1.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.1.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.10.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.10.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.10.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.100.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.100.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.100.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.101.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.101.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.101.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.102.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.102.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.102.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.103.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.103.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.103.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.104.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.104.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.104.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.105.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.105.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.105.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.106.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.106.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.106.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.107.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.107.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.107.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.108.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.108.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.108.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.109.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.109.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.109.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.11.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.11.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.11.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.110.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.110.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.110.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.111.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.111.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.111.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.112.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.112.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.112.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.113.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.113.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.113.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.114.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.114.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.114.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.115.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.115.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.115.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.116.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.116.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.116.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.117.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.117.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.117.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.118.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.118.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.118.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.119.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.119.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.119.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.12.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.12.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.12.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.120.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.120.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.120.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.121.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.121.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.121.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.122.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.122.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.122.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.123.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.123.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.123.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.124.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.124.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.124.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.125.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.125.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.125.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.126.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.126.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.126.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.127.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.127.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.127.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.13.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.13.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.13.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.14.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.14.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.14.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.15.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.15.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.15.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.16.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.16.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.16.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.17.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.17.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.17.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.18.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.18.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.18.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.19.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.19.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.19.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.2.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.2.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.2.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.20.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.20.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.20.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.21.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.21.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.21.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.22.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.22.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.22.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.23.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.23.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.23.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.24.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.24.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.24.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.25.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.25.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.25.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.26.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.26.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.26.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.27.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.27.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.27.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.28.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.28.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.28.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.29.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.29.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.29.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.3.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.3.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.3.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.30.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.30.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.30.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.31.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.31.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.31.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.32.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.32.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.32.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.33.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.33.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.33.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.34.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.34.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.34.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.35.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.35.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.35.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.36.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.36.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.36.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.37.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.37.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.37.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.38.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.38.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.38.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.39.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.39.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.39.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.4.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.4.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.4.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.40.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.40.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.40.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.41.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.41.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.41.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.42.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.42.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.42.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.43.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.43.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.43.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.44.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.44.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.44.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.45.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.45.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.45.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.46.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.46.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.46.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.47.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.47.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.47.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.48.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.48.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.48.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.49.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.49.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.49.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.5.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.5.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.5.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.50.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.50.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.50.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.51.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.51.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.51.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.52.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.52.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.52.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.53.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.53.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.53.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.54.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.54.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.54.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.55.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.55.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.55.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.56.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.56.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.56.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.57.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.57.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.57.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.58.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.58.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.58.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.59.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.59.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.59.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.6.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.6.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.6.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.60.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.60.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.60.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.61.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.61.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.61.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.62.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.62.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.62.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.63.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.63.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.63.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.64.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.64.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.64.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.65.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.65.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.65.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.66.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.66.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.66.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.67.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.67.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.67.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.68.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.68.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.68.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.69.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.69.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.69.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.7.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.7.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.7.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.70.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.70.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.70.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.71.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.71.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.71.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.72.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.72.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.72.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.73.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.73.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.73.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.74.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.74.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.74.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.75.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.75.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.75.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.76.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.76.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.76.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.77.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.77.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.77.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.78.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.78.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.78.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.79.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.79.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.79.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.8.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.8.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.8.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.80.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.80.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.80.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.81.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.81.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.81.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.82.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.82.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.82.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.83.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.83.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.83.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.84.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.84.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.84.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.85.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.85.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.85.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.86.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.86.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.86.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.87.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.87.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.87.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.88.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.88.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.88.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.89.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.89.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.89.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.9.down_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.9.gate_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.9.up_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.mlp.experts.90.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.90.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.90.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.91.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.91.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.91.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.92.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.92.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.92.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.93.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.93.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.93.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.94.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.94.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.94.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.95.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.95.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.95.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.96.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.96.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.96.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.97.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.97.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.97.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.98.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.98.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.98.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.99.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.99.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.experts.99.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.gate.e_score_correction_bias": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.gate.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.14.post_attention_layernorm.weight": "model-00014-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.k_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.o_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.q_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.bias": "model-00013-of-00043.safetensors", + "model.layers.14.self_attn.v_proj.weight": "model-00013-of-00043.safetensors", + "model.layers.15.input_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.0.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.0.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.0.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.1.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.1.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.1.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.10.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.10.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.10.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.100.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.100.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.100.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.101.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.101.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.101.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.102.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.102.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.102.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.103.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.103.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.103.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.104.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.104.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.104.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.105.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.105.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.105.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.106.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.106.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.106.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.107.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.107.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.107.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.108.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.108.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.108.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.109.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.109.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.109.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.11.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.11.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.11.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.110.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.110.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.110.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.111.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.111.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.111.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.112.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.112.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.112.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.113.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.113.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.113.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.114.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.114.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.114.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.115.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.115.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.115.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.116.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.116.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.116.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.117.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.117.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.117.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.118.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.118.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.118.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.119.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.119.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.119.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.12.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.12.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.12.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.120.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.120.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.120.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.121.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.121.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.121.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.122.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.122.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.122.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.123.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.123.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.123.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.124.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.124.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.124.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.125.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.125.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.125.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.126.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.126.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.126.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.127.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.127.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.127.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.13.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.13.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.13.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.14.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.14.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.14.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.15.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.15.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.15.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.16.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.16.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.16.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.17.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.17.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.17.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.18.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.18.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.18.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.19.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.19.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.19.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.2.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.2.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.2.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.20.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.20.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.20.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.21.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.21.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.21.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.22.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.22.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.22.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.23.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.23.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.23.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.24.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.24.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.24.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.25.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.25.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.25.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.26.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.26.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.26.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.27.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.27.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.27.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.28.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.28.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.28.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.29.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.29.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.29.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.3.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.3.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.3.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.30.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.30.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.30.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.31.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.31.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.31.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.32.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.32.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.32.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.33.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.33.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.33.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.34.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.34.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.34.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.35.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.35.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.35.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.36.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.36.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.36.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.37.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.37.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.37.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.38.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.38.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.38.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.39.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.39.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.39.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.4.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.4.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.4.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.40.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.40.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.40.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.41.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.41.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.41.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.42.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.42.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.42.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.43.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.43.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.43.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.44.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.44.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.44.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.45.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.45.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.45.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.46.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.46.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.46.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.47.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.47.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.47.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.48.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.48.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.48.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.49.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.49.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.49.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.5.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.5.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.5.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.50.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.50.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.50.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.51.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.51.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.51.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.52.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.52.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.52.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.53.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.53.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.53.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.54.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.54.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.54.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.55.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.55.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.55.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.56.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.56.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.56.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.57.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.57.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.57.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.58.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.58.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.58.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.59.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.59.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.59.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.6.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.6.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.6.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.60.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.60.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.60.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.61.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.61.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.61.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.62.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.62.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.62.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.63.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.63.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.63.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.64.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.64.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.64.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.65.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.65.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.65.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.66.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.66.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.66.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.67.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.67.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.67.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.68.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.68.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.68.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.69.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.69.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.69.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.7.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.7.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.7.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.70.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.70.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.70.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.71.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.71.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.71.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.72.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.72.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.72.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.73.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.73.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.73.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.74.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.74.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.74.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.75.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.75.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.75.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.76.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.76.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.76.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.77.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.77.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.77.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.78.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.78.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.78.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.79.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.79.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.79.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.8.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.8.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.8.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.80.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.80.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.80.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.81.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.81.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.81.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.82.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.82.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.82.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.83.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.83.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.83.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.84.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.84.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.84.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.85.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.85.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.85.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.86.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.86.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.86.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.87.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.87.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.87.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.88.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.88.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.88.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.89.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.89.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.89.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.9.down_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.9.gate_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.9.up_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.mlp.experts.90.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.90.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.90.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.91.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.91.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.91.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.92.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.92.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.92.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.93.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.93.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.93.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.94.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.94.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.94.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.95.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.95.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.95.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.96.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.96.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.96.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.97.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.97.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.97.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.98.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.98.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.98.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.99.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.99.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.experts.99.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.gate.e_score_correction_bias": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.gate.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.15.post_attention_layernorm.weight": "model-00015-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.k_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.o_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.q_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.bias": "model-00014-of-00043.safetensors", + "model.layers.15.self_attn.v_proj.weight": "model-00014-of-00043.safetensors", + "model.layers.16.input_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.0.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.0.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.0.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.1.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.1.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.1.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.10.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.10.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.10.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.100.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.100.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.100.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.101.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.101.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.101.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.102.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.102.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.102.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.103.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.103.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.103.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.104.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.104.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.104.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.105.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.105.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.105.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.106.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.106.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.106.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.107.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.107.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.107.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.108.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.108.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.108.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.109.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.109.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.109.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.11.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.11.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.11.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.110.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.110.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.110.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.111.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.111.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.111.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.112.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.112.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.112.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.113.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.113.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.113.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.114.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.114.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.114.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.115.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.115.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.115.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.116.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.116.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.116.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.117.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.117.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.117.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.118.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.118.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.118.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.119.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.119.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.119.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.12.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.12.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.12.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.120.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.120.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.120.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.121.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.121.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.121.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.122.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.122.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.122.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.123.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.123.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.123.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.124.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.124.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.124.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.125.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.125.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.125.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.126.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.126.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.126.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.127.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.127.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.127.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.13.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.13.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.13.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.14.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.14.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.14.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.15.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.15.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.15.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.16.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.16.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.16.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.17.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.17.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.17.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.18.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.18.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.18.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.19.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.19.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.19.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.2.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.2.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.2.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.20.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.20.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.20.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.21.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.21.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.21.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.22.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.22.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.22.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.23.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.23.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.23.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.24.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.24.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.24.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.25.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.25.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.25.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.26.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.26.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.26.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.27.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.27.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.27.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.28.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.28.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.28.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.29.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.29.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.29.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.3.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.3.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.3.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.30.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.30.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.30.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.31.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.31.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.31.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.32.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.32.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.32.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.33.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.33.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.33.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.34.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.34.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.34.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.35.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.35.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.35.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.36.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.36.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.36.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.37.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.37.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.37.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.38.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.38.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.38.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.39.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.39.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.39.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.4.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.4.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.4.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.40.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.40.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.40.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.41.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.41.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.41.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.42.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.42.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.42.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.43.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.43.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.43.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.44.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.44.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.44.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.45.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.45.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.45.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.46.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.46.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.46.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.47.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.47.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.47.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.48.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.48.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.48.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.49.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.49.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.49.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.5.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.5.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.5.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.50.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.50.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.50.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.51.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.51.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.51.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.52.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.52.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.52.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.53.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.53.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.53.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.54.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.54.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.54.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.55.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.55.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.55.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.56.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.56.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.56.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.57.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.57.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.57.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.58.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.58.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.58.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.59.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.59.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.59.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.6.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.6.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.6.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.60.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.60.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.60.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.61.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.61.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.61.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.62.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.62.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.62.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.63.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.63.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.63.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.64.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.64.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.64.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.65.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.65.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.65.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.66.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.66.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.66.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.67.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.67.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.67.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.68.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.68.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.68.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.69.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.69.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.69.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.7.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.7.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.7.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.70.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.70.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.70.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.71.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.71.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.71.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.72.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.72.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.72.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.73.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.73.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.73.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.74.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.74.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.74.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.75.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.75.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.75.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.76.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.76.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.76.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.77.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.77.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.77.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.78.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.78.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.78.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.79.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.79.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.79.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.8.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.8.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.8.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.80.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.80.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.80.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.81.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.81.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.81.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.82.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.82.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.82.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.83.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.83.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.83.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.84.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.84.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.84.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.85.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.85.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.85.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.86.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.86.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.86.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.87.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.87.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.87.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.88.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.88.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.88.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.89.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.89.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.89.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.9.down_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.9.gate_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.9.up_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.mlp.experts.90.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.90.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.90.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.91.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.91.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.91.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.92.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.92.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.92.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.93.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.93.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.93.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.94.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.94.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.94.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.95.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.95.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.95.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.96.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.96.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.96.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.97.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.97.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.97.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.98.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.98.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.98.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.99.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.99.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.experts.99.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.gate.e_score_correction_bias": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.gate.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.16.post_attention_layernorm.weight": "model-00016-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.k_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.o_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.q_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.bias": "model-00015-of-00043.safetensors", + "model.layers.16.self_attn.v_proj.weight": "model-00015-of-00043.safetensors", + "model.layers.17.input_layernorm.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.0.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.0.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.0.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.1.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.1.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.1.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.10.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.10.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.10.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.100.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.100.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.100.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.101.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.101.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.101.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.102.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.102.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.102.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.103.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.103.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.103.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.104.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.104.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.104.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.105.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.105.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.105.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.106.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.106.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.106.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.107.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.107.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.107.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.108.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.108.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.108.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.109.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.109.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.109.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.11.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.11.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.11.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.110.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.110.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.110.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.111.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.111.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.111.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.112.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.112.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.112.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.113.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.113.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.113.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.114.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.114.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.114.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.115.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.115.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.115.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.116.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.116.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.116.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.117.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.117.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.117.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.118.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.118.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.118.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.119.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.119.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.119.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.12.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.12.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.12.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.120.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.120.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.120.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.121.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.121.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.121.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.122.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.122.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.122.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.123.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.123.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.123.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.124.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.124.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.124.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.125.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.125.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.125.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.126.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.126.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.126.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.127.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.127.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.127.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.13.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.13.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.13.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.14.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.14.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.14.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.15.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.15.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.15.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.16.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.16.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.16.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.17.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.17.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.17.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.18.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.18.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.18.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.19.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.19.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.19.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.2.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.2.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.2.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.20.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.20.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.20.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.21.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.21.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.21.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.22.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.22.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.22.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.23.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.23.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.23.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.24.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.24.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.24.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.25.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.25.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.25.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.26.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.26.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.26.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.27.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.27.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.27.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.28.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.28.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.28.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.29.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.29.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.29.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.3.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.3.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.3.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.30.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.30.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.30.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.31.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.31.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.31.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.32.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.32.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.32.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.33.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.33.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.33.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.34.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.34.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.34.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.35.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.35.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.35.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.36.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.36.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.36.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.37.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.37.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.37.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.38.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.38.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.38.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.39.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.39.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.39.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.4.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.4.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.4.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.40.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.40.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.40.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.41.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.41.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.41.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.42.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.42.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.42.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.43.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.43.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.43.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.44.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.44.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.44.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.45.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.45.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.45.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.46.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.46.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.46.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.47.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.47.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.47.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.48.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.48.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.48.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.49.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.49.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.49.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.5.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.5.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.5.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.50.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.50.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.50.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.51.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.51.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.51.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.52.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.52.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.52.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.53.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.53.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.53.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.54.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.54.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.54.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.55.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.55.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.55.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.56.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.56.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.56.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.57.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.57.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.57.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.58.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.58.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.58.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.59.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.59.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.59.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.6.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.6.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.6.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.60.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.60.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.60.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.61.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.61.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.61.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.62.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.62.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.62.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.63.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.63.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.63.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.64.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.64.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.64.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.65.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.65.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.65.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.66.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.66.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.66.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.67.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.67.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.67.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.68.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.68.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.68.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.69.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.69.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.69.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.7.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.7.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.7.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.70.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.70.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.70.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.71.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.71.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.71.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.72.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.72.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.72.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.73.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.73.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.73.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.74.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.74.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.74.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.75.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.75.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.75.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.76.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.76.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.76.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.77.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.77.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.77.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.78.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.78.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.78.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.79.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.79.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.79.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.8.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.8.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.8.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.80.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.80.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.80.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.81.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.81.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.81.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.82.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.82.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.82.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.83.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.83.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.83.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.84.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.84.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.84.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.85.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.85.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.85.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.86.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.86.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.86.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.87.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.87.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.87.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.88.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.88.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.88.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.89.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.89.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.89.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.9.down_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.9.gate_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.9.up_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.mlp.experts.90.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.90.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.90.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.91.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.91.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.91.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.92.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.92.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.92.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.93.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.93.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.93.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.94.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.94.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.94.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.95.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.95.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.95.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.96.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.96.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.96.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.97.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.97.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.97.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.98.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.98.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.98.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.99.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.99.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.experts.99.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.gate.e_score_correction_bias": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.gate.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.17.post_attention_layernorm.weight": "model-00017-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.k_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.o_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.q_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.bias": "model-00016-of-00043.safetensors", + "model.layers.17.self_attn.v_proj.weight": "model-00016-of-00043.safetensors", + "model.layers.18.input_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.0.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.0.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.0.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.1.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.1.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.1.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.10.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.10.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.10.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.100.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.100.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.100.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.101.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.101.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.101.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.102.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.102.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.102.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.103.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.103.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.103.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.104.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.104.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.104.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.105.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.105.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.105.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.106.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.106.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.106.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.107.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.107.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.107.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.108.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.108.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.108.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.109.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.109.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.109.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.11.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.11.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.11.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.110.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.110.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.110.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.111.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.111.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.111.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.112.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.112.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.112.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.113.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.113.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.113.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.114.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.114.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.114.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.115.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.115.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.115.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.116.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.116.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.116.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.117.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.117.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.117.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.118.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.118.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.118.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.119.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.119.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.119.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.12.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.12.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.12.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.120.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.120.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.120.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.121.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.121.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.121.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.122.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.122.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.122.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.123.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.123.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.123.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.124.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.124.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.124.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.125.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.125.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.125.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.126.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.126.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.126.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.127.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.127.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.127.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.13.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.13.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.13.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.14.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.14.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.14.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.15.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.15.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.15.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.16.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.16.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.16.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.17.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.17.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.17.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.18.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.18.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.18.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.19.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.19.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.19.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.2.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.2.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.2.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.20.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.20.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.20.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.21.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.21.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.21.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.22.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.22.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.22.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.23.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.23.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.23.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.24.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.24.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.24.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.25.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.25.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.25.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.26.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.26.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.26.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.27.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.27.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.27.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.28.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.28.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.28.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.29.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.29.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.29.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.3.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.3.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.3.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.30.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.30.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.30.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.31.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.31.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.31.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.32.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.32.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.32.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.33.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.33.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.33.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.34.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.34.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.34.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.35.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.35.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.35.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.36.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.36.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.36.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.37.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.37.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.37.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.38.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.38.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.38.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.39.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.39.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.39.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.4.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.4.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.4.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.40.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.40.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.40.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.41.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.41.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.41.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.42.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.42.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.42.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.43.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.43.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.43.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.44.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.44.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.44.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.45.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.45.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.45.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.46.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.46.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.46.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.47.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.47.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.47.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.48.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.48.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.48.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.49.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.49.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.49.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.5.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.5.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.5.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.50.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.50.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.50.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.51.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.51.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.51.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.52.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.52.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.52.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.53.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.53.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.53.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.54.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.54.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.54.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.55.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.55.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.55.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.56.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.56.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.56.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.57.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.57.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.57.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.58.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.58.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.58.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.59.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.59.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.59.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.6.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.6.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.6.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.60.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.60.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.60.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.61.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.61.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.61.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.62.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.62.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.62.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.63.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.63.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.63.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.64.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.64.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.64.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.65.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.65.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.65.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.66.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.66.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.66.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.67.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.67.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.67.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.68.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.68.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.68.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.69.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.69.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.69.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.7.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.7.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.7.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.70.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.70.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.70.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.71.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.71.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.71.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.72.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.72.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.72.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.73.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.73.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.73.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.74.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.74.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.74.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.75.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.75.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.75.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.76.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.76.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.76.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.77.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.77.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.77.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.78.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.78.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.78.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.79.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.79.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.79.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.8.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.8.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.8.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.80.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.80.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.80.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.81.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.81.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.81.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.82.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.82.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.82.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.83.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.83.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.83.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.84.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.84.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.84.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.85.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.85.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.85.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.86.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.86.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.86.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.87.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.87.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.87.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.88.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.88.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.88.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.89.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.89.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.89.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.9.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.9.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.9.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.90.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.90.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.90.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.91.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.91.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.91.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.92.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.92.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.92.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.93.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.93.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.93.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.94.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.94.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.94.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.95.down_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.95.gate_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.95.up_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.mlp.experts.96.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.96.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.96.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.97.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.97.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.97.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.98.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.98.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.98.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.99.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.99.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.experts.99.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.gate.e_score_correction_bias": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.gate.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.18.post_attention_layernorm.weight": "model-00018-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.k_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.o_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.q_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.bias": "model-00017-of-00043.safetensors", + "model.layers.18.self_attn.v_proj.weight": "model-00017-of-00043.safetensors", + "model.layers.19.input_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.0.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.0.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.0.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.1.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.1.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.1.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.10.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.10.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.10.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.100.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.100.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.100.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.101.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.101.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.101.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.102.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.102.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.102.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.103.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.103.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.103.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.104.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.104.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.104.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.105.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.105.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.105.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.106.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.106.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.106.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.107.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.107.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.107.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.108.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.108.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.108.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.109.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.109.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.109.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.11.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.11.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.11.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.110.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.110.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.110.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.111.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.111.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.111.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.112.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.112.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.112.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.113.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.113.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.113.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.114.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.114.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.114.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.115.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.115.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.115.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.116.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.116.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.116.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.117.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.117.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.117.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.118.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.118.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.118.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.119.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.119.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.119.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.12.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.12.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.12.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.120.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.120.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.120.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.121.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.121.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.121.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.122.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.122.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.122.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.123.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.123.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.123.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.124.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.124.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.124.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.125.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.125.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.125.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.126.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.126.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.126.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.127.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.127.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.127.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.experts.13.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.13.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.13.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.14.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.14.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.14.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.15.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.15.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.15.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.16.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.16.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.16.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.17.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.17.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.17.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.18.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.18.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.18.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.19.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.19.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.19.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.2.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.2.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.2.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.20.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.20.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.20.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.21.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.21.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.21.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.22.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.22.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.22.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.23.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.23.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.23.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.24.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.24.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.24.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.25.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.25.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.25.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.26.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.26.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.26.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.27.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.27.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.27.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.28.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.28.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.28.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.29.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.29.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.29.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.3.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.3.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.3.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.30.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.30.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.30.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.31.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.31.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.31.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.32.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.32.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.32.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.33.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.33.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.33.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.34.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.34.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.34.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.35.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.35.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.35.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.36.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.36.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.36.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.37.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.37.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.37.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.38.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.38.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.38.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.39.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.39.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.39.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.4.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.4.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.4.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.40.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.40.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.40.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.41.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.41.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.41.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.42.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.42.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.42.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.43.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.43.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.43.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.44.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.44.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.44.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.45.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.45.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.45.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.46.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.46.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.46.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.47.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.47.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.47.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.48.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.48.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.48.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.49.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.49.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.49.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.5.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.5.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.5.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.50.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.50.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.50.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.51.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.51.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.51.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.52.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.52.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.52.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.53.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.53.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.53.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.54.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.54.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.54.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.55.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.55.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.55.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.56.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.56.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.56.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.57.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.57.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.57.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.58.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.58.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.58.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.59.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.59.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.59.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.6.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.6.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.6.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.60.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.60.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.60.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.61.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.61.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.61.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.62.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.62.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.62.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.63.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.63.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.63.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.64.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.64.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.64.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.65.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.65.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.65.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.66.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.66.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.66.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.67.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.67.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.67.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.68.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.68.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.68.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.69.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.69.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.69.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.7.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.7.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.7.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.70.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.70.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.70.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.71.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.71.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.71.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.72.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.72.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.72.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.73.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.73.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.73.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.74.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.74.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.74.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.75.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.75.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.75.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.76.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.76.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.76.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.77.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.77.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.77.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.78.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.78.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.78.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.79.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.79.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.79.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.8.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.8.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.8.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.80.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.80.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.80.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.81.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.81.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.81.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.82.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.82.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.82.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.83.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.83.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.83.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.84.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.84.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.84.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.85.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.85.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.85.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.86.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.86.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.86.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.87.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.87.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.87.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.88.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.88.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.88.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.89.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.89.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.89.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.9.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.9.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.9.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.90.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.90.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.90.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.91.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.91.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.91.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.92.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.92.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.92.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.93.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.93.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.93.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.94.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.94.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.94.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.95.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.95.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.95.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.96.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.96.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.96.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.97.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.97.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.97.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.98.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.98.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.98.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.99.down_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.99.gate_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.experts.99.up_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.mlp.gate.e_score_correction_bias": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.gate.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.19.post_attention_layernorm.weight": "model-00019-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.k_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.o_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.q_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.bias": "model-00018-of-00043.safetensors", + "model.layers.19.self_attn.v_proj.weight": "model-00018-of-00043.safetensors", + "model.layers.2.input_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.0.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.0.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.0.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.1.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.1.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.1.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.10.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.10.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.10.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.100.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.100.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.100.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.101.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.101.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.101.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.102.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.102.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.102.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.103.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.103.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.103.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.104.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.104.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.104.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.105.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.105.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.105.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.106.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.106.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.106.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.107.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.107.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.107.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.108.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.108.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.108.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.109.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.109.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.109.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.11.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.11.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.11.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.110.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.110.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.110.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.111.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.111.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.111.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.112.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.112.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.112.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.113.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.113.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.113.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.114.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.114.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.114.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.115.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.115.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.115.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.116.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.116.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.116.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.117.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.117.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.117.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.118.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.118.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.118.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.119.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.119.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.119.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.12.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.12.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.12.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.120.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.120.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.120.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.121.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.121.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.121.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.122.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.122.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.122.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.123.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.123.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.123.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.124.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.124.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.124.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.125.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.125.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.125.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.126.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.126.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.126.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.127.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.127.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.127.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.13.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.13.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.13.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.14.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.14.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.14.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.15.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.15.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.15.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.16.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.16.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.16.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.17.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.17.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.17.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.18.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.18.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.18.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.19.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.19.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.19.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.2.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.2.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.2.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.20.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.20.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.20.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.21.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.21.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.21.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.22.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.22.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.22.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.23.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.23.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.23.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.24.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.24.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.24.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.25.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.25.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.25.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.26.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.26.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.26.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.27.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.27.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.27.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.28.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.28.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.28.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.29.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.29.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.29.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.3.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.3.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.3.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.30.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.30.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.30.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.31.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.31.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.31.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.32.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.32.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.32.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.33.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.33.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.33.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.34.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.34.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.34.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.35.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.35.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.35.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.36.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.36.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.36.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.37.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.37.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.37.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.38.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.38.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.38.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.39.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.39.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.39.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.4.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.4.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.4.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.40.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.40.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.40.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.41.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.41.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.41.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.42.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.42.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.42.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.43.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.43.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.43.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.44.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.44.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.44.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.45.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.45.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.45.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.46.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.46.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.46.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.47.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.47.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.47.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.48.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.48.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.48.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.49.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.49.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.49.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.5.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.5.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.5.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.50.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.50.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.50.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.51.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.51.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.51.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.52.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.52.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.52.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.53.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.53.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.53.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.54.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.54.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.54.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.55.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.55.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.55.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.56.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.56.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.56.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.57.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.57.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.57.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.58.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.58.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.58.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.59.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.59.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.59.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.6.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.6.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.6.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.60.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.60.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.60.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.61.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.61.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.61.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.62.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.62.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.62.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.63.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.63.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.63.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.64.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.64.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.64.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.65.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.65.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.65.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.66.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.66.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.66.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.67.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.67.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.67.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.68.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.68.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.68.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.69.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.69.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.69.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.7.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.7.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.7.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.70.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.70.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.70.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.71.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.71.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.71.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.72.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.72.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.72.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.73.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.73.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.73.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.74.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.74.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.74.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.75.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.75.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.75.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.76.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.76.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.76.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.77.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.77.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.77.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.78.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.78.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.78.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.79.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.79.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.79.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.8.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.8.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.8.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.80.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.80.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.80.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.81.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.81.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.81.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.82.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.82.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.82.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.83.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.83.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.83.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.84.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.84.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.84.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.85.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.85.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.85.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.86.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.86.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.86.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.87.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.87.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.87.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.88.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.88.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.88.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.89.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.89.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.89.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.9.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.9.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.9.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.90.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.90.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.90.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.91.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.91.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.91.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.92.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.92.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.92.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.93.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.93.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.93.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.94.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.94.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.94.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.95.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.95.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.95.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.96.down_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.96.gate_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.96.up_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.mlp.experts.97.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.97.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.97.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.98.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.98.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.98.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.99.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.99.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.experts.99.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.gate.e_score_correction_bias": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.gate.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.mlp.shared_experts.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.2.post_attention_layernorm.weight": "model-00003-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00043.safetensors", + "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00043.safetensors", + "model.layers.20.input_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.0.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.0.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.0.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.1.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.1.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.1.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.10.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.10.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.10.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.100.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.100.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.100.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.101.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.101.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.101.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.102.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.102.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.102.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.103.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.103.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.103.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.104.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.104.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.104.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.105.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.105.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.105.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.106.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.106.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.106.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.107.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.107.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.107.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.108.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.108.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.108.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.109.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.109.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.109.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.11.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.11.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.11.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.110.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.110.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.110.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.111.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.111.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.111.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.112.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.112.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.112.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.113.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.113.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.113.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.114.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.114.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.114.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.115.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.115.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.115.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.116.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.116.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.116.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.117.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.117.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.117.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.118.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.118.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.118.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.119.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.119.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.119.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.12.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.12.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.12.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.120.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.120.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.120.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.121.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.121.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.121.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.122.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.122.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.122.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.123.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.123.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.123.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.124.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.124.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.124.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.125.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.125.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.125.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.126.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.126.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.126.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.127.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.127.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.127.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.experts.13.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.13.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.13.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.14.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.14.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.14.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.15.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.15.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.15.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.16.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.16.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.16.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.17.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.17.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.17.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.18.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.18.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.18.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.19.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.19.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.19.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.2.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.2.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.2.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.20.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.20.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.20.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.21.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.21.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.21.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.22.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.22.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.22.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.23.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.23.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.23.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.24.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.24.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.24.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.25.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.25.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.25.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.26.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.26.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.26.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.27.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.27.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.27.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.28.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.28.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.28.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.29.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.29.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.29.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.3.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.3.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.3.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.30.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.30.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.30.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.31.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.31.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.31.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.32.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.32.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.32.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.33.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.33.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.33.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.34.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.34.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.34.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.35.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.35.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.35.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.36.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.36.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.36.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.37.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.37.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.37.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.38.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.38.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.38.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.39.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.39.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.39.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.4.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.4.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.4.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.40.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.40.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.40.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.41.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.41.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.41.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.42.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.42.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.42.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.43.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.43.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.43.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.44.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.44.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.44.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.45.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.45.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.45.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.46.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.46.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.46.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.47.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.47.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.47.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.48.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.48.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.48.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.49.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.49.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.49.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.5.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.5.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.5.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.50.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.50.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.50.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.51.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.51.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.51.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.52.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.52.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.52.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.53.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.53.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.53.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.54.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.54.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.54.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.55.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.55.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.55.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.56.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.56.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.56.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.57.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.57.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.57.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.58.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.58.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.58.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.59.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.59.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.59.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.6.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.6.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.6.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.60.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.60.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.60.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.61.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.61.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.61.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.62.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.62.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.62.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.63.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.63.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.63.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.64.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.64.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.64.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.65.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.65.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.65.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.66.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.66.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.66.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.67.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.67.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.67.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.68.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.68.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.68.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.69.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.69.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.69.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.7.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.7.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.7.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.70.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.70.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.70.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.71.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.71.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.71.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.72.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.72.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.72.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.73.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.73.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.73.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.74.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.74.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.74.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.75.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.75.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.75.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.76.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.76.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.76.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.77.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.77.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.77.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.78.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.78.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.78.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.79.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.79.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.79.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.8.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.8.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.8.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.80.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.80.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.80.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.81.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.81.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.81.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.82.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.82.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.82.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.83.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.83.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.83.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.84.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.84.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.84.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.85.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.85.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.85.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.86.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.86.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.86.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.87.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.87.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.87.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.88.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.88.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.88.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.89.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.89.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.89.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.9.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.9.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.9.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.90.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.90.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.90.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.91.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.91.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.91.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.92.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.92.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.92.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.93.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.93.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.93.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.94.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.94.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.94.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.95.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.95.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.95.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.96.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.96.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.96.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.97.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.97.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.97.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.98.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.98.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.98.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.99.down_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.99.gate_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.experts.99.up_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.mlp.gate.e_score_correction_bias": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.gate.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.20.post_attention_layernorm.weight": "model-00020-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.k_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.o_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.q_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.bias": "model-00019-of-00043.safetensors", + "model.layers.20.self_attn.v_proj.weight": "model-00019-of-00043.safetensors", + "model.layers.21.input_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.0.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.0.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.0.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.1.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.1.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.1.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.10.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.10.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.10.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.100.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.100.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.100.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.101.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.101.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.101.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.102.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.102.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.102.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.103.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.103.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.103.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.104.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.104.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.104.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.105.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.105.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.105.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.106.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.106.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.106.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.107.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.107.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.107.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.108.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.108.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.108.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.109.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.109.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.109.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.11.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.11.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.11.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.110.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.110.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.110.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.111.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.111.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.111.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.112.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.112.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.112.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.113.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.113.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.113.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.114.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.114.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.114.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.115.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.115.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.115.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.116.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.116.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.116.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.117.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.117.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.117.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.118.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.118.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.118.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.119.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.119.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.119.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.12.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.12.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.12.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.120.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.120.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.120.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.121.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.121.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.121.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.122.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.122.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.122.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.123.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.123.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.123.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.124.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.124.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.124.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.125.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.125.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.125.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.126.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.126.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.126.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.127.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.127.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.127.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.experts.13.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.13.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.13.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.14.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.14.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.14.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.15.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.15.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.15.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.16.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.16.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.16.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.17.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.17.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.17.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.18.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.18.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.18.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.19.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.19.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.19.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.2.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.2.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.2.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.20.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.20.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.20.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.21.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.21.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.21.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.22.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.22.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.22.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.23.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.23.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.23.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.24.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.24.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.24.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.25.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.25.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.25.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.26.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.26.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.26.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.27.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.27.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.27.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.28.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.28.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.28.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.29.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.29.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.29.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.3.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.3.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.3.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.30.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.30.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.30.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.31.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.31.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.31.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.32.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.32.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.32.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.33.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.33.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.33.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.34.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.34.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.34.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.35.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.35.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.35.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.36.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.36.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.36.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.37.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.37.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.37.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.38.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.38.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.38.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.39.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.39.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.39.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.4.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.4.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.4.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.40.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.40.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.40.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.41.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.41.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.41.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.42.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.42.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.42.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.43.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.43.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.43.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.44.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.44.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.44.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.45.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.45.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.45.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.46.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.46.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.46.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.47.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.47.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.47.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.48.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.48.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.48.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.49.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.49.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.49.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.5.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.5.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.5.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.50.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.50.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.50.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.51.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.51.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.51.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.52.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.52.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.52.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.53.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.53.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.53.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.54.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.54.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.54.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.55.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.55.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.55.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.56.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.56.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.56.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.57.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.57.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.57.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.58.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.58.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.58.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.59.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.59.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.59.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.6.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.6.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.6.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.60.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.60.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.60.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.61.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.61.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.61.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.62.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.62.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.62.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.63.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.63.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.63.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.64.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.64.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.64.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.65.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.65.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.65.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.66.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.66.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.66.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.67.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.67.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.67.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.68.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.68.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.68.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.69.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.69.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.69.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.7.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.7.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.7.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.70.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.70.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.70.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.71.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.71.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.71.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.72.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.72.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.72.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.73.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.73.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.73.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.74.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.74.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.74.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.75.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.75.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.75.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.76.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.76.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.76.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.77.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.77.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.77.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.78.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.78.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.78.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.79.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.79.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.79.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.8.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.8.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.8.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.80.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.80.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.80.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.81.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.81.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.81.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.82.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.82.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.82.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.83.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.83.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.83.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.84.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.84.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.84.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.85.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.85.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.85.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.86.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.86.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.86.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.87.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.87.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.87.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.88.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.88.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.88.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.89.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.89.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.89.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.9.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.9.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.9.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.90.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.90.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.90.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.91.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.91.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.91.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.92.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.92.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.92.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.93.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.93.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.93.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.94.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.94.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.94.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.95.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.95.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.95.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.96.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.96.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.96.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.97.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.97.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.97.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.98.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.98.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.98.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.99.down_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.99.gate_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.experts.99.up_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.mlp.gate.e_score_correction_bias": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.gate.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.21.post_attention_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.k_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.o_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.q_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.bias": "model-00020-of-00043.safetensors", + "model.layers.21.self_attn.v_proj.weight": "model-00020-of-00043.safetensors", + "model.layers.22.input_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.0.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.0.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.0.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.1.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.1.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.1.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.10.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.10.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.10.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.100.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.100.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.100.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.101.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.101.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.101.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.102.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.102.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.102.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.103.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.103.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.103.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.104.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.104.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.104.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.105.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.105.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.105.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.106.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.106.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.106.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.107.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.107.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.107.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.108.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.108.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.108.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.109.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.109.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.109.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.11.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.11.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.11.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.110.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.110.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.110.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.111.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.111.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.111.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.112.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.112.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.112.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.113.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.113.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.113.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.114.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.114.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.114.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.115.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.115.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.115.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.116.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.116.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.116.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.117.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.117.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.117.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.118.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.118.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.118.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.119.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.119.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.119.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.12.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.12.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.12.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.120.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.120.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.120.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.121.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.121.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.121.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.122.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.122.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.122.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.123.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.123.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.123.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.124.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.124.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.124.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.125.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.125.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.125.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.126.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.126.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.126.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.127.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.127.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.127.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.13.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.13.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.13.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.14.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.14.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.14.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.15.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.15.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.15.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.16.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.16.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.16.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.17.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.17.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.17.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.18.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.18.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.18.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.19.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.19.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.19.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.2.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.2.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.2.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.20.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.20.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.20.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.21.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.21.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.21.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.22.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.22.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.22.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.23.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.23.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.23.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.24.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.24.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.24.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.25.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.25.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.25.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.26.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.26.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.26.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.27.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.27.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.27.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.28.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.28.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.28.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.29.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.29.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.29.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.3.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.3.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.3.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.30.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.30.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.30.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.31.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.31.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.31.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.32.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.32.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.32.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.33.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.33.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.33.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.34.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.34.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.34.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.35.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.35.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.35.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.36.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.36.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.36.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.37.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.37.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.37.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.38.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.38.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.38.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.39.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.39.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.39.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.4.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.4.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.4.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.40.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.40.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.40.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.41.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.41.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.41.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.42.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.42.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.42.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.43.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.43.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.43.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.44.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.44.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.44.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.45.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.45.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.45.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.46.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.46.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.46.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.47.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.47.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.47.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.48.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.48.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.48.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.49.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.49.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.49.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.5.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.5.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.5.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.50.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.50.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.50.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.51.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.51.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.51.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.52.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.52.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.52.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.53.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.53.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.53.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.54.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.54.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.54.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.55.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.55.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.55.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.56.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.56.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.56.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.57.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.57.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.57.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.58.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.58.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.58.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.59.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.59.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.59.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.6.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.6.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.6.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.60.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.60.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.60.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.61.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.61.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.61.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.62.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.62.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.62.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.63.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.63.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.63.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.64.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.64.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.64.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.65.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.65.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.65.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.66.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.66.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.66.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.67.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.67.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.67.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.68.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.68.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.68.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.69.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.69.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.69.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.7.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.7.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.7.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.70.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.70.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.70.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.71.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.71.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.71.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.72.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.72.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.72.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.73.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.73.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.73.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.74.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.74.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.74.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.75.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.75.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.75.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.76.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.76.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.76.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.77.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.77.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.77.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.78.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.78.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.78.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.79.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.79.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.79.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.8.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.8.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.8.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.80.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.80.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.80.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.81.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.81.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.81.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.82.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.82.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.82.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.83.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.83.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.83.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.84.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.84.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.84.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.85.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.85.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.85.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.86.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.86.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.86.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.87.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.87.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.87.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.88.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.88.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.88.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.89.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.89.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.89.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.9.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.9.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.9.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.90.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.90.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.90.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.91.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.91.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.91.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.92.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.92.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.92.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.93.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.93.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.93.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.94.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.94.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.94.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.95.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.95.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.95.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.96.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.96.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.96.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.97.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.97.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.97.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.98.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.98.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.98.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.99.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.99.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.experts.99.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.gate.e_score_correction_bias": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.gate.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.post_attention_layernorm.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.k_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.o_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.q_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.22.self_attn.v_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.23.input_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.0.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.0.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.0.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.1.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.1.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.1.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.10.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.10.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.10.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.100.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.100.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.100.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.101.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.101.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.101.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.102.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.102.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.102.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.103.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.103.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.103.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.104.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.104.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.104.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.105.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.105.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.105.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.106.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.106.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.106.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.107.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.107.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.107.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.108.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.108.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.108.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.109.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.109.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.109.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.11.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.11.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.11.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.110.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.110.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.110.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.111.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.111.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.111.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.112.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.112.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.112.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.113.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.113.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.113.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.114.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.114.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.114.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.115.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.115.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.115.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.116.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.116.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.116.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.117.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.117.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.117.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.118.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.118.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.118.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.119.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.119.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.119.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.12.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.12.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.12.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.120.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.120.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.120.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.121.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.121.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.121.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.122.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.122.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.122.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.123.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.123.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.123.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.124.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.124.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.124.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.125.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.125.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.125.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.126.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.126.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.126.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.127.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.127.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.127.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.13.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.13.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.13.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.14.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.14.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.14.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.15.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.15.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.15.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.16.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.16.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.16.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.17.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.17.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.17.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.18.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.18.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.18.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.19.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.19.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.19.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.2.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.2.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.2.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.20.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.20.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.20.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.21.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.21.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.21.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.22.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.22.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.22.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.23.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.23.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.23.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.24.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.24.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.24.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.25.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.25.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.25.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.26.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.26.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.26.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.27.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.27.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.27.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.28.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.28.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.28.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.29.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.29.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.29.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.3.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.3.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.3.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.30.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.30.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.30.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.31.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.31.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.31.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.32.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.32.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.32.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.33.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.33.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.33.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.34.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.34.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.34.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.35.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.35.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.35.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.36.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.36.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.36.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.37.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.37.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.37.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.38.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.38.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.38.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.39.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.39.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.39.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.4.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.4.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.4.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.40.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.40.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.40.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.41.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.41.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.41.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.42.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.42.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.42.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.43.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.43.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.43.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.44.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.44.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.44.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.45.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.45.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.45.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.46.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.46.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.46.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.47.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.47.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.47.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.48.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.48.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.48.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.49.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.49.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.49.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.5.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.5.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.5.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.50.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.50.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.50.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.51.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.51.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.51.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.52.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.52.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.52.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.53.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.53.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.53.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.54.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.54.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.54.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.55.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.55.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.55.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.56.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.56.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.56.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.57.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.57.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.57.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.58.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.58.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.58.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.59.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.59.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.59.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.6.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.6.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.6.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.60.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.60.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.60.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.61.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.61.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.61.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.62.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.62.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.62.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.63.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.63.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.63.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.64.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.64.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.64.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.65.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.65.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.65.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.66.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.66.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.66.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.67.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.67.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.67.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.68.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.68.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.68.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.69.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.69.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.69.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.7.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.7.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.7.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.70.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.70.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.70.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.71.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.71.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.71.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.72.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.72.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.72.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.73.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.73.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.73.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.74.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.74.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.74.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.75.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.75.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.75.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.76.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.76.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.76.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.77.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.77.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.77.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.78.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.78.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.78.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.79.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.79.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.79.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.8.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.8.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.8.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.80.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.80.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.80.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.81.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.81.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.81.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.82.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.82.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.82.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.83.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.83.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.83.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.84.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.84.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.84.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.85.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.85.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.85.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.86.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.86.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.86.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.87.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.87.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.87.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.88.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.88.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.88.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.89.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.89.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.89.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.9.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.9.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.9.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.90.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.90.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.90.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.91.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.91.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.91.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.92.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.92.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.92.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.93.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.93.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.93.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.94.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.94.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.94.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.95.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.95.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.95.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.96.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.96.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.96.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.97.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.97.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.97.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.98.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.98.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.98.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.99.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.99.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.experts.99.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.gate.e_score_correction_bias": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.gate.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.post_attention_layernorm.weight": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.k_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.o_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.bias": "model-00021-of-00043.safetensors", + "model.layers.23.self_attn.q_proj.weight": "model-00021-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.23.self_attn.v_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.input_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.0.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.0.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.0.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.1.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.1.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.1.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.10.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.10.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.10.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.100.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.100.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.100.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.101.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.101.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.101.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.102.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.102.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.102.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.103.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.103.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.103.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.104.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.104.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.104.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.105.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.105.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.105.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.106.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.106.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.106.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.107.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.107.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.107.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.108.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.108.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.108.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.109.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.109.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.109.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.11.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.11.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.11.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.110.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.110.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.110.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.111.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.111.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.111.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.112.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.112.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.112.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.113.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.113.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.113.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.114.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.114.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.114.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.115.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.115.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.115.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.116.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.116.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.116.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.117.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.117.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.117.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.118.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.118.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.118.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.119.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.119.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.119.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.12.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.12.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.12.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.120.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.120.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.120.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.121.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.121.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.121.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.122.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.122.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.122.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.123.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.123.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.123.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.124.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.124.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.124.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.125.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.125.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.125.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.126.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.126.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.126.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.127.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.127.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.127.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.13.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.13.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.13.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.14.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.14.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.14.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.15.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.15.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.15.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.16.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.16.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.16.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.17.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.17.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.17.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.18.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.18.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.18.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.19.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.19.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.19.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.2.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.2.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.2.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.20.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.20.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.20.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.21.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.21.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.21.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.22.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.22.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.22.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.23.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.23.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.23.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.24.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.24.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.24.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.25.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.25.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.25.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.26.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.26.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.26.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.27.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.27.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.27.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.28.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.28.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.28.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.29.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.29.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.29.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.3.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.3.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.3.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.30.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.30.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.30.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.31.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.31.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.31.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.32.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.32.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.32.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.33.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.33.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.33.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.34.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.34.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.34.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.35.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.35.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.35.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.36.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.36.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.36.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.37.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.37.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.37.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.38.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.38.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.38.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.39.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.39.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.39.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.4.down_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.4.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.4.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.40.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.40.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.40.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.41.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.41.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.41.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.42.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.42.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.42.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.43.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.43.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.43.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.44.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.44.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.44.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.45.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.45.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.45.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.46.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.46.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.46.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.47.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.47.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.47.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.48.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.48.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.48.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.49.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.49.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.49.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.5.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.5.gate_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.5.up_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.mlp.experts.50.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.50.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.50.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.51.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.51.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.51.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.52.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.52.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.52.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.53.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.53.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.53.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.54.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.54.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.54.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.55.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.55.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.55.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.56.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.56.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.56.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.57.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.57.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.57.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.58.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.58.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.58.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.59.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.59.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.59.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.6.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.6.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.6.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.60.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.60.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.60.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.61.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.61.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.61.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.62.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.62.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.62.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.63.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.63.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.63.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.64.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.64.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.64.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.65.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.65.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.65.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.66.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.66.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.66.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.67.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.67.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.67.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.68.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.68.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.68.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.69.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.69.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.69.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.7.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.7.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.7.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.70.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.70.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.70.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.71.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.71.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.71.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.72.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.72.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.72.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.73.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.73.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.73.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.74.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.74.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.74.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.75.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.75.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.75.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.76.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.76.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.76.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.77.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.77.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.77.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.78.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.78.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.78.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.79.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.79.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.79.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.8.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.8.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.8.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.80.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.80.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.80.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.81.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.81.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.81.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.82.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.82.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.82.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.83.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.83.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.83.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.84.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.84.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.84.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.85.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.85.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.85.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.86.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.86.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.86.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.87.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.87.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.87.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.88.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.88.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.88.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.89.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.89.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.89.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.9.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.9.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.9.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.90.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.90.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.90.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.91.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.91.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.91.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.92.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.92.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.92.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.93.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.93.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.93.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.94.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.94.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.94.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.95.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.95.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.95.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.96.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.96.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.96.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.97.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.97.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.97.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.98.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.98.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.98.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.99.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.99.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.experts.99.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.gate.e_score_correction_bias": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.gate.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.24.post_attention_layernorm.weight": "model-00023-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.k_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.o_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.q_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.bias": "model-00022-of-00043.safetensors", + "model.layers.24.self_attn.v_proj.weight": "model-00022-of-00043.safetensors", + "model.layers.25.input_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.0.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.0.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.0.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.1.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.1.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.1.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.10.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.10.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.10.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.100.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.100.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.100.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.101.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.101.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.101.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.102.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.102.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.102.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.103.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.103.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.103.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.104.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.104.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.104.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.105.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.105.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.105.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.106.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.106.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.106.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.107.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.107.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.107.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.108.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.108.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.108.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.109.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.109.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.109.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.11.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.11.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.11.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.110.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.110.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.110.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.111.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.111.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.111.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.112.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.112.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.112.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.113.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.113.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.113.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.114.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.114.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.114.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.115.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.115.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.115.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.116.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.116.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.116.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.117.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.117.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.117.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.118.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.118.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.118.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.119.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.119.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.119.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.12.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.12.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.12.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.120.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.120.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.120.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.121.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.121.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.121.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.122.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.122.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.122.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.123.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.123.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.123.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.124.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.124.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.124.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.125.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.125.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.125.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.126.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.126.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.126.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.127.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.127.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.127.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.13.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.13.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.13.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.14.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.14.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.14.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.15.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.15.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.15.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.16.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.16.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.16.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.17.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.17.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.17.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.18.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.18.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.18.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.19.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.19.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.19.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.2.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.2.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.2.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.20.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.20.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.20.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.21.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.21.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.21.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.22.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.22.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.22.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.23.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.23.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.23.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.24.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.24.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.24.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.25.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.25.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.25.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.26.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.26.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.26.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.27.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.27.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.27.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.28.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.28.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.28.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.29.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.29.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.29.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.3.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.3.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.3.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.30.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.30.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.30.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.31.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.31.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.31.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.32.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.32.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.32.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.33.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.33.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.33.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.34.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.34.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.34.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.35.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.35.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.35.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.36.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.36.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.36.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.37.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.37.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.37.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.38.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.38.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.38.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.39.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.39.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.39.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.4.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.4.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.4.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.40.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.40.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.40.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.41.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.41.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.41.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.42.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.42.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.42.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.43.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.43.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.43.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.44.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.44.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.44.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.45.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.45.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.45.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.46.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.46.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.46.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.47.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.47.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.47.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.48.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.48.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.48.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.49.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.49.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.49.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.5.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.5.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.5.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.50.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.50.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.50.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.51.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.51.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.51.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.52.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.52.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.52.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.53.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.53.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.53.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.54.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.54.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.54.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.55.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.55.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.55.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.56.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.56.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.56.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.57.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.57.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.57.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.58.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.58.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.58.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.59.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.59.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.59.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.6.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.6.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.6.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.60.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.60.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.60.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.61.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.61.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.61.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.62.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.62.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.62.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.63.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.63.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.63.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.64.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.64.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.64.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.65.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.65.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.65.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.66.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.66.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.66.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.67.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.67.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.67.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.68.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.68.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.68.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.69.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.69.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.69.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.7.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.7.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.7.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.70.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.70.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.70.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.71.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.71.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.71.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.72.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.72.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.72.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.73.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.73.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.73.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.74.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.74.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.74.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.75.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.75.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.75.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.76.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.76.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.76.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.77.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.77.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.77.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.78.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.78.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.78.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.79.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.79.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.79.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.8.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.8.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.8.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.80.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.80.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.80.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.81.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.81.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.81.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.82.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.82.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.82.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.83.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.83.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.83.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.84.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.84.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.84.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.85.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.85.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.85.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.86.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.86.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.86.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.87.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.87.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.87.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.88.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.88.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.88.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.89.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.89.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.89.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.9.down_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.9.gate_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.9.up_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.mlp.experts.90.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.90.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.90.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.91.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.91.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.91.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.92.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.92.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.92.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.93.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.93.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.93.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.94.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.94.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.94.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.95.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.95.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.95.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.96.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.96.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.96.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.97.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.97.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.97.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.98.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.98.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.98.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.99.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.99.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.experts.99.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.gate.e_score_correction_bias": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.gate.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.25.post_attention_layernorm.weight": "model-00024-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.k_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.o_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.q_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.bias": "model-00023-of-00043.safetensors", + "model.layers.25.self_attn.v_proj.weight": "model-00023-of-00043.safetensors", + "model.layers.26.input_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.0.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.0.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.0.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.1.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.1.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.1.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.10.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.10.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.10.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.100.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.100.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.100.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.101.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.101.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.101.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.102.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.102.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.102.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.103.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.103.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.103.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.104.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.104.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.104.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.105.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.105.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.105.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.106.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.106.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.106.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.107.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.107.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.107.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.108.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.108.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.108.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.109.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.109.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.109.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.11.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.11.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.11.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.110.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.110.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.110.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.111.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.111.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.111.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.112.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.112.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.112.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.113.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.113.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.113.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.114.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.114.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.114.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.115.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.115.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.115.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.116.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.116.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.116.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.117.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.117.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.117.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.118.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.118.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.118.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.119.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.119.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.119.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.12.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.12.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.12.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.120.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.120.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.120.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.121.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.121.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.121.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.122.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.122.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.122.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.123.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.123.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.123.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.124.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.124.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.124.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.125.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.125.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.125.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.126.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.126.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.126.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.127.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.127.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.127.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.13.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.13.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.13.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.14.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.14.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.14.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.15.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.15.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.15.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.16.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.16.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.16.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.17.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.17.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.17.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.18.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.18.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.18.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.19.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.19.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.19.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.2.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.2.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.2.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.20.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.20.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.20.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.21.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.21.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.21.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.22.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.22.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.22.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.23.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.23.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.23.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.24.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.24.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.24.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.25.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.25.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.25.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.26.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.26.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.26.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.27.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.27.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.27.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.28.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.28.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.28.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.29.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.29.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.29.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.3.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.3.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.3.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.30.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.30.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.30.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.31.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.31.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.31.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.32.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.32.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.32.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.33.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.33.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.33.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.34.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.34.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.34.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.35.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.35.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.35.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.36.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.36.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.36.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.37.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.37.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.37.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.38.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.38.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.38.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.39.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.39.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.39.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.4.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.4.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.4.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.40.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.40.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.40.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.41.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.41.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.41.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.42.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.42.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.42.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.43.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.43.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.43.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.44.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.44.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.44.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.45.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.45.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.45.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.46.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.46.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.46.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.47.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.47.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.47.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.48.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.48.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.48.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.49.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.49.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.49.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.5.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.5.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.5.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.50.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.50.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.50.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.51.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.51.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.51.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.52.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.52.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.52.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.53.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.53.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.53.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.54.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.54.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.54.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.55.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.55.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.55.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.56.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.56.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.56.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.57.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.57.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.57.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.58.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.58.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.58.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.59.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.59.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.59.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.6.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.6.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.6.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.60.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.60.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.60.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.61.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.61.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.61.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.62.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.62.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.62.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.63.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.63.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.63.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.64.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.64.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.64.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.65.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.65.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.65.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.66.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.66.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.66.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.67.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.67.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.67.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.68.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.68.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.68.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.69.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.69.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.69.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.7.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.7.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.7.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.70.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.70.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.70.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.71.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.71.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.71.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.72.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.72.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.72.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.73.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.73.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.73.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.74.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.74.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.74.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.75.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.75.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.75.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.76.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.76.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.76.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.77.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.77.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.77.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.78.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.78.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.78.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.79.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.79.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.79.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.8.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.8.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.8.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.80.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.80.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.80.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.81.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.81.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.81.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.82.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.82.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.82.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.83.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.83.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.83.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.84.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.84.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.84.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.85.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.85.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.85.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.86.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.86.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.86.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.87.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.87.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.87.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.88.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.88.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.88.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.89.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.89.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.89.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.9.down_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.9.gate_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.9.up_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.mlp.experts.90.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.90.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.90.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.91.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.91.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.91.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.92.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.92.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.92.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.93.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.93.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.93.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.94.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.94.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.94.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.95.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.95.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.95.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.96.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.96.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.96.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.97.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.97.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.97.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.98.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.98.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.98.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.99.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.99.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.experts.99.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.gate.e_score_correction_bias": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.gate.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.26.post_attention_layernorm.weight": "model-00025-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.k_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.o_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.q_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.bias": "model-00024-of-00043.safetensors", + "model.layers.26.self_attn.v_proj.weight": "model-00024-of-00043.safetensors", + "model.layers.27.input_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.0.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.0.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.0.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.1.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.1.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.1.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.10.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.10.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.10.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.100.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.100.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.100.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.101.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.101.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.101.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.102.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.102.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.102.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.103.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.103.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.103.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.104.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.104.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.104.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.105.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.105.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.105.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.106.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.106.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.106.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.107.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.107.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.107.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.108.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.108.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.108.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.109.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.109.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.109.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.11.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.11.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.11.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.110.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.110.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.110.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.111.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.111.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.111.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.112.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.112.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.112.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.113.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.113.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.113.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.114.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.114.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.114.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.115.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.115.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.115.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.116.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.116.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.116.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.117.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.117.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.117.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.118.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.118.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.118.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.119.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.119.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.119.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.12.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.12.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.12.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.120.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.120.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.120.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.121.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.121.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.121.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.122.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.122.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.122.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.123.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.123.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.123.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.124.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.124.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.124.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.125.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.125.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.125.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.126.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.126.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.126.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.127.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.127.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.127.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.13.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.13.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.13.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.14.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.14.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.14.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.15.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.15.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.15.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.16.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.16.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.16.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.17.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.17.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.17.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.18.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.18.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.18.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.19.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.19.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.19.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.2.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.2.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.2.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.20.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.20.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.20.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.21.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.21.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.21.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.22.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.22.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.22.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.23.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.23.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.23.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.24.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.24.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.24.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.25.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.25.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.25.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.26.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.26.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.26.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.27.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.27.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.27.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.28.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.28.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.28.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.29.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.29.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.29.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.3.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.3.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.3.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.30.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.30.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.30.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.31.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.31.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.31.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.32.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.32.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.32.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.33.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.33.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.33.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.34.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.34.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.34.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.35.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.35.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.35.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.36.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.36.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.36.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.37.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.37.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.37.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.38.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.38.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.38.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.39.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.39.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.39.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.4.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.4.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.4.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.40.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.40.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.40.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.41.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.41.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.41.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.42.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.42.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.42.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.43.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.43.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.43.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.44.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.44.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.44.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.45.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.45.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.45.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.46.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.46.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.46.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.47.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.47.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.47.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.48.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.48.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.48.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.49.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.49.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.49.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.5.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.5.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.5.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.50.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.50.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.50.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.51.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.51.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.51.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.52.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.52.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.52.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.53.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.53.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.53.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.54.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.54.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.54.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.55.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.55.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.55.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.56.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.56.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.56.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.57.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.57.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.57.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.58.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.58.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.58.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.59.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.59.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.59.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.6.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.6.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.6.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.60.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.60.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.60.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.61.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.61.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.61.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.62.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.62.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.62.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.63.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.63.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.63.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.64.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.64.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.64.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.65.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.65.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.65.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.66.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.66.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.66.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.67.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.67.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.67.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.68.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.68.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.68.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.69.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.69.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.69.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.7.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.7.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.7.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.70.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.70.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.70.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.71.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.71.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.71.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.72.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.72.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.72.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.73.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.73.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.73.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.74.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.74.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.74.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.75.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.75.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.75.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.76.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.76.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.76.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.77.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.77.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.77.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.78.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.78.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.78.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.79.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.79.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.79.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.8.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.8.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.8.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.80.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.80.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.80.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.81.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.81.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.81.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.82.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.82.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.82.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.83.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.83.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.83.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.84.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.84.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.84.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.85.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.85.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.85.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.86.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.86.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.86.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.87.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.87.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.87.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.88.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.88.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.88.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.89.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.89.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.89.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.9.down_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.9.gate_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.9.up_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.mlp.experts.90.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.90.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.90.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.91.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.91.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.91.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.92.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.92.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.92.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.93.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.93.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.93.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.94.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.94.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.94.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.95.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.95.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.95.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.96.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.96.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.96.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.97.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.97.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.97.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.98.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.98.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.98.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.99.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.99.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.experts.99.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.gate.e_score_correction_bias": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.gate.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.27.post_attention_layernorm.weight": "model-00026-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.k_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.o_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.q_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.bias": "model-00025-of-00043.safetensors", + "model.layers.27.self_attn.v_proj.weight": "model-00025-of-00043.safetensors", + "model.layers.28.input_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.0.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.0.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.0.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.1.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.1.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.1.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.10.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.10.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.10.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.100.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.100.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.100.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.101.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.101.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.101.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.102.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.102.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.102.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.103.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.103.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.103.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.104.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.104.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.104.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.105.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.105.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.105.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.106.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.106.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.106.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.107.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.107.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.107.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.108.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.108.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.108.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.109.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.109.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.109.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.11.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.11.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.11.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.110.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.110.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.110.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.111.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.111.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.111.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.112.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.112.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.112.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.113.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.113.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.113.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.114.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.114.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.114.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.115.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.115.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.115.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.116.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.116.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.116.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.117.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.117.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.117.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.118.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.118.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.118.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.119.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.119.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.119.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.12.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.12.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.12.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.120.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.120.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.120.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.121.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.121.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.121.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.122.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.122.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.122.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.123.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.123.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.123.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.124.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.124.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.124.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.125.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.125.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.125.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.126.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.126.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.126.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.127.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.127.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.127.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.13.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.13.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.13.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.14.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.14.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.14.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.15.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.15.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.15.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.16.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.16.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.16.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.17.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.17.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.17.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.18.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.18.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.18.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.19.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.19.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.19.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.2.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.2.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.2.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.20.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.20.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.20.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.21.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.21.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.21.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.22.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.22.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.22.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.23.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.23.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.23.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.24.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.24.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.24.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.25.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.25.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.25.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.26.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.26.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.26.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.27.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.27.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.27.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.28.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.28.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.28.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.29.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.29.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.29.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.3.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.3.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.3.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.30.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.30.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.30.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.31.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.31.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.31.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.32.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.32.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.32.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.33.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.33.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.33.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.34.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.34.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.34.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.35.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.35.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.35.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.36.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.36.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.36.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.37.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.37.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.37.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.38.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.38.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.38.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.39.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.39.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.39.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.4.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.4.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.4.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.40.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.40.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.40.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.41.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.41.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.41.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.42.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.42.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.42.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.43.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.43.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.43.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.44.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.44.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.44.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.45.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.45.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.45.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.46.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.46.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.46.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.47.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.47.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.47.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.48.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.48.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.48.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.49.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.49.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.49.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.5.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.5.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.5.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.50.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.50.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.50.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.51.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.51.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.51.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.52.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.52.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.52.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.53.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.53.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.53.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.54.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.54.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.54.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.55.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.55.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.55.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.56.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.56.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.56.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.57.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.57.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.57.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.58.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.58.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.58.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.59.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.59.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.59.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.6.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.6.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.6.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.60.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.60.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.60.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.61.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.61.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.61.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.62.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.62.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.62.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.63.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.63.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.63.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.64.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.64.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.64.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.65.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.65.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.65.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.66.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.66.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.66.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.67.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.67.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.67.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.68.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.68.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.68.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.69.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.69.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.69.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.7.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.7.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.7.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.70.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.70.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.70.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.71.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.71.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.71.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.72.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.72.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.72.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.73.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.73.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.73.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.74.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.74.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.74.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.75.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.75.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.75.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.76.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.76.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.76.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.77.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.77.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.77.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.78.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.78.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.78.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.79.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.79.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.79.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.8.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.8.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.8.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.80.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.80.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.80.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.81.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.81.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.81.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.82.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.82.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.82.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.83.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.83.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.83.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.84.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.84.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.84.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.85.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.85.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.85.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.86.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.86.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.86.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.87.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.87.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.87.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.88.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.88.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.88.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.89.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.89.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.89.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.9.down_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.9.gate_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.9.up_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.mlp.experts.90.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.90.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.90.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.91.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.91.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.91.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.92.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.92.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.92.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.93.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.93.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.93.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.94.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.94.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.94.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.95.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.95.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.95.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.96.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.96.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.96.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.97.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.97.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.97.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.98.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.98.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.98.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.99.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.99.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.experts.99.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.gate.e_score_correction_bias": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.gate.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.28.post_attention_layernorm.weight": "model-00027-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.k_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.o_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.q_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.bias": "model-00026-of-00043.safetensors", + "model.layers.28.self_attn.v_proj.weight": "model-00026-of-00043.safetensors", + "model.layers.29.input_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.0.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.0.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.0.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.1.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.1.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.1.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.10.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.10.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.10.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.100.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.100.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.100.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.101.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.101.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.101.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.102.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.102.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.102.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.103.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.103.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.103.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.104.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.104.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.104.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.105.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.105.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.105.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.106.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.106.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.106.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.107.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.107.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.107.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.108.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.108.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.108.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.109.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.109.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.109.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.11.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.11.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.11.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.110.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.110.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.110.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.111.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.111.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.111.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.112.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.112.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.112.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.113.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.113.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.113.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.114.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.114.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.114.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.115.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.115.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.115.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.116.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.116.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.116.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.117.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.117.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.117.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.118.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.118.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.118.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.119.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.119.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.119.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.12.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.12.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.12.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.120.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.120.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.120.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.121.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.121.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.121.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.122.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.122.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.122.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.123.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.123.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.123.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.124.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.124.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.124.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.125.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.125.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.125.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.126.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.126.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.126.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.127.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.127.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.127.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.13.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.13.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.13.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.14.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.14.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.14.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.15.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.15.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.15.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.16.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.16.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.16.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.17.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.17.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.17.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.18.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.18.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.18.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.19.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.19.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.19.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.2.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.2.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.2.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.20.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.20.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.20.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.21.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.21.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.21.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.22.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.22.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.22.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.23.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.23.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.23.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.24.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.24.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.24.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.25.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.25.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.25.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.26.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.26.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.26.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.27.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.27.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.27.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.28.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.28.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.28.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.29.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.29.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.29.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.3.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.3.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.3.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.30.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.30.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.30.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.31.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.31.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.31.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.32.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.32.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.32.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.33.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.33.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.33.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.34.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.34.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.34.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.35.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.35.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.35.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.36.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.36.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.36.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.37.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.37.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.37.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.38.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.38.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.38.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.39.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.39.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.39.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.4.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.4.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.4.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.40.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.40.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.40.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.41.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.41.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.41.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.42.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.42.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.42.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.43.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.43.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.43.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.44.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.44.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.44.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.45.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.45.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.45.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.46.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.46.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.46.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.47.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.47.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.47.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.48.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.48.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.48.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.49.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.49.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.49.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.5.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.5.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.5.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.50.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.50.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.50.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.51.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.51.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.51.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.52.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.52.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.52.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.53.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.53.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.53.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.54.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.54.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.54.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.55.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.55.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.55.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.56.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.56.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.56.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.57.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.57.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.57.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.58.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.58.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.58.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.59.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.59.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.59.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.6.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.6.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.6.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.60.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.60.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.60.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.61.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.61.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.61.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.62.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.62.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.62.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.63.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.63.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.63.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.64.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.64.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.64.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.65.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.65.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.65.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.66.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.66.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.66.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.67.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.67.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.67.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.68.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.68.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.68.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.69.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.69.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.69.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.7.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.7.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.7.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.70.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.70.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.70.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.71.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.71.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.71.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.72.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.72.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.72.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.73.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.73.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.73.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.74.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.74.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.74.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.75.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.75.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.75.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.76.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.76.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.76.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.77.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.77.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.77.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.78.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.78.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.78.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.79.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.79.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.79.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.8.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.8.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.8.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.80.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.80.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.80.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.81.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.81.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.81.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.82.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.82.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.82.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.83.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.83.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.83.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.84.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.84.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.84.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.85.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.85.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.85.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.86.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.86.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.86.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.87.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.87.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.87.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.88.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.88.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.88.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.89.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.89.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.89.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.9.down_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.9.gate_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.9.up_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.mlp.experts.90.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.90.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.90.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.91.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.91.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.91.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.92.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.92.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.92.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.93.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.93.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.93.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.94.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.94.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.94.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.95.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.95.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.95.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.96.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.96.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.96.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.97.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.97.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.97.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.98.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.98.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.98.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.99.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.99.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.experts.99.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.gate.e_score_correction_bias": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.gate.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.29.post_attention_layernorm.weight": "model-00028-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.k_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.o_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.q_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.bias": "model-00027-of-00043.safetensors", + "model.layers.29.self_attn.v_proj.weight": "model-00027-of-00043.safetensors", + "model.layers.3.input_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.0.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.0.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.0.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.1.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.1.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.1.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.10.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.10.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.10.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.100.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.100.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.100.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.101.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.101.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.101.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.102.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.102.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.102.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.103.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.103.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.103.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.104.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.104.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.104.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.105.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.105.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.105.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.106.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.106.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.106.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.107.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.107.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.107.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.108.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.108.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.108.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.109.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.109.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.109.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.11.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.11.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.11.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.110.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.110.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.110.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.111.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.111.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.111.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.112.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.112.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.112.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.113.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.113.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.113.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.114.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.114.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.114.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.115.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.115.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.115.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.116.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.116.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.116.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.117.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.117.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.117.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.118.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.118.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.118.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.119.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.119.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.119.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.12.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.12.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.12.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.120.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.120.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.120.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.121.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.121.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.121.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.122.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.122.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.122.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.123.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.123.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.123.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.124.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.124.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.124.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.125.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.125.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.125.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.126.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.126.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.126.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.127.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.127.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.127.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.experts.13.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.13.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.13.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.14.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.14.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.14.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.15.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.15.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.15.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.16.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.16.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.16.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.17.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.17.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.17.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.18.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.18.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.18.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.19.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.19.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.19.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.2.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.2.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.2.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.20.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.20.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.20.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.21.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.21.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.21.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.22.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.22.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.22.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.23.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.23.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.23.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.24.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.24.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.24.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.25.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.25.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.25.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.26.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.26.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.26.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.27.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.27.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.27.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.28.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.28.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.28.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.29.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.29.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.29.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.3.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.3.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.3.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.30.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.30.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.30.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.31.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.31.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.31.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.32.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.32.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.32.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.33.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.33.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.33.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.34.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.34.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.34.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.35.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.35.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.35.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.36.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.36.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.36.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.37.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.37.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.37.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.38.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.38.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.38.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.39.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.39.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.39.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.4.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.4.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.4.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.40.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.40.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.40.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.41.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.41.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.41.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.42.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.42.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.42.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.43.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.43.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.43.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.44.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.44.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.44.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.45.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.45.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.45.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.46.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.46.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.46.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.47.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.47.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.47.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.48.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.48.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.48.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.49.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.49.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.49.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.5.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.5.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.5.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.50.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.50.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.50.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.51.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.51.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.51.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.52.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.52.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.52.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.53.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.53.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.53.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.54.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.54.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.54.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.55.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.55.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.55.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.56.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.56.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.56.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.57.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.57.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.57.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.58.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.58.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.58.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.59.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.59.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.59.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.6.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.6.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.6.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.60.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.60.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.60.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.61.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.61.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.61.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.62.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.62.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.62.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.63.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.63.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.63.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.64.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.64.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.64.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.65.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.65.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.65.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.66.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.66.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.66.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.67.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.67.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.67.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.68.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.68.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.68.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.69.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.69.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.69.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.7.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.7.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.7.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.70.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.70.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.70.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.71.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.71.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.71.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.72.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.72.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.72.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.73.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.73.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.73.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.74.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.74.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.74.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.75.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.75.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.75.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.76.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.76.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.76.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.77.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.77.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.77.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.78.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.78.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.78.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.79.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.79.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.79.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.8.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.8.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.8.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.80.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.80.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.80.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.81.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.81.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.81.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.82.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.82.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.82.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.83.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.83.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.83.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.84.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.84.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.84.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.85.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.85.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.85.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.86.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.86.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.86.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.87.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.87.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.87.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.88.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.88.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.88.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.89.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.89.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.89.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.9.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.9.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.9.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.90.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.90.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.90.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.91.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.91.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.91.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.92.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.92.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.92.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.93.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.93.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.93.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.94.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.94.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.94.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.95.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.95.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.95.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.96.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.96.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.96.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.97.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.97.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.97.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.98.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.98.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.98.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.99.down_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.99.gate_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.experts.99.up_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.mlp.gate.e_score_correction_bias": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.gate.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.3.post_attention_layernorm.weight": "model-00004-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00043.safetensors", + "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00043.safetensors", + "model.layers.30.input_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.0.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.0.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.0.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.1.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.1.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.1.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.10.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.10.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.10.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.100.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.100.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.100.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.101.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.101.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.101.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.102.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.102.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.102.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.103.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.103.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.103.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.104.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.104.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.104.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.105.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.105.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.105.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.106.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.106.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.106.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.107.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.107.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.107.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.108.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.108.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.108.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.109.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.109.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.109.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.11.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.11.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.11.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.110.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.110.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.110.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.111.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.111.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.111.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.112.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.112.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.112.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.113.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.113.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.113.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.114.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.114.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.114.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.115.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.115.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.115.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.116.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.116.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.116.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.117.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.117.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.117.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.118.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.118.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.118.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.119.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.119.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.119.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.12.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.12.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.12.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.120.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.120.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.120.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.121.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.121.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.121.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.122.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.122.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.122.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.123.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.123.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.123.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.124.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.124.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.124.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.125.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.125.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.125.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.126.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.126.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.126.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.127.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.127.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.127.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.13.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.13.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.13.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.14.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.14.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.14.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.15.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.15.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.15.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.16.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.16.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.16.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.17.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.17.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.17.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.18.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.18.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.18.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.19.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.19.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.19.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.2.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.2.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.2.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.20.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.20.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.20.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.21.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.21.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.21.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.22.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.22.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.22.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.23.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.23.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.23.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.24.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.24.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.24.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.25.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.25.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.25.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.26.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.26.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.26.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.27.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.27.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.27.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.28.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.28.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.28.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.29.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.29.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.29.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.3.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.3.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.3.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.30.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.30.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.30.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.31.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.31.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.31.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.32.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.32.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.32.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.33.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.33.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.33.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.34.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.34.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.34.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.35.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.35.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.35.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.36.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.36.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.36.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.37.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.37.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.37.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.38.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.38.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.38.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.39.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.39.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.39.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.4.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.4.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.4.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.40.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.40.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.40.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.41.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.41.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.41.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.42.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.42.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.42.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.43.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.43.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.43.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.44.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.44.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.44.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.45.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.45.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.45.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.46.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.46.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.46.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.47.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.47.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.47.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.48.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.48.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.48.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.49.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.49.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.49.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.5.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.5.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.5.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.50.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.50.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.50.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.51.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.51.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.51.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.52.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.52.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.52.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.53.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.53.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.53.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.54.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.54.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.54.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.55.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.55.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.55.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.56.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.56.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.56.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.57.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.57.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.57.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.58.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.58.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.58.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.59.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.59.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.59.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.6.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.6.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.6.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.60.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.60.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.60.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.61.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.61.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.61.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.62.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.62.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.62.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.63.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.63.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.63.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.64.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.64.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.64.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.65.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.65.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.65.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.66.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.66.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.66.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.67.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.67.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.67.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.68.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.68.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.68.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.69.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.69.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.69.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.7.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.7.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.7.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.70.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.70.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.70.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.71.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.71.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.71.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.72.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.72.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.72.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.73.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.73.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.73.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.74.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.74.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.74.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.75.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.75.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.75.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.76.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.76.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.76.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.77.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.77.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.77.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.78.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.78.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.78.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.79.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.79.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.79.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.8.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.8.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.8.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.80.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.80.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.80.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.81.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.81.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.81.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.82.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.82.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.82.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.83.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.83.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.83.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.84.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.84.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.84.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.85.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.85.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.85.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.86.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.86.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.86.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.87.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.87.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.87.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.88.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.88.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.88.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.89.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.89.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.89.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.9.down_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.9.gate_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.9.up_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.mlp.experts.90.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.90.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.90.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.91.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.91.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.91.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.92.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.92.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.92.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.93.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.93.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.93.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.94.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.94.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.94.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.95.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.95.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.95.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.96.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.96.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.96.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.97.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.97.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.97.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.98.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.98.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.98.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.99.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.99.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.experts.99.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.gate.e_score_correction_bias": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.gate.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.30.post_attention_layernorm.weight": "model-00029-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.k_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.o_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.q_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.bias": "model-00028-of-00043.safetensors", + "model.layers.30.self_attn.v_proj.weight": "model-00028-of-00043.safetensors", + "model.layers.31.input_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.0.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.0.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.0.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.1.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.1.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.1.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.10.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.10.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.10.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.100.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.100.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.100.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.101.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.101.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.101.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.102.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.102.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.102.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.103.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.103.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.103.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.104.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.104.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.104.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.105.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.105.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.105.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.106.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.106.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.106.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.107.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.107.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.107.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.108.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.108.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.108.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.109.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.109.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.109.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.11.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.11.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.11.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.110.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.110.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.110.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.111.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.111.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.111.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.112.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.112.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.112.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.113.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.113.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.113.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.114.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.114.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.114.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.115.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.115.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.115.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.116.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.116.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.116.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.117.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.117.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.117.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.118.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.118.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.118.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.119.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.119.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.119.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.12.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.12.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.12.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.120.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.120.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.120.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.121.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.121.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.121.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.122.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.122.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.122.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.123.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.123.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.123.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.124.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.124.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.124.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.125.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.125.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.125.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.126.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.126.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.126.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.127.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.127.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.127.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.13.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.13.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.13.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.14.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.14.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.14.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.15.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.15.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.15.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.16.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.16.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.16.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.17.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.17.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.17.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.18.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.18.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.18.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.19.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.19.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.19.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.2.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.2.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.2.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.20.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.20.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.20.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.21.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.21.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.21.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.22.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.22.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.22.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.23.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.23.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.23.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.24.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.24.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.24.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.25.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.25.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.25.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.26.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.26.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.26.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.27.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.27.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.27.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.28.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.28.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.28.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.29.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.29.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.29.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.3.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.3.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.3.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.30.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.30.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.30.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.31.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.31.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.31.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.32.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.32.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.32.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.33.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.33.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.33.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.34.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.34.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.34.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.35.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.35.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.35.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.36.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.36.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.36.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.37.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.37.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.37.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.38.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.38.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.38.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.39.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.39.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.39.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.4.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.4.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.4.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.40.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.40.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.40.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.41.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.41.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.41.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.42.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.42.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.42.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.43.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.43.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.43.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.44.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.44.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.44.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.45.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.45.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.45.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.46.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.46.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.46.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.47.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.47.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.47.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.48.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.48.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.48.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.49.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.49.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.49.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.5.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.5.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.5.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.50.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.50.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.50.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.51.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.51.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.51.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.52.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.52.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.52.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.53.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.53.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.53.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.54.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.54.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.54.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.55.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.55.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.55.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.56.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.56.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.56.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.57.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.57.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.57.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.58.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.58.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.58.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.59.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.59.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.59.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.6.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.6.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.6.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.60.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.60.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.60.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.61.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.61.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.61.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.62.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.62.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.62.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.63.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.63.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.63.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.64.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.64.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.64.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.65.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.65.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.65.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.66.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.66.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.66.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.67.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.67.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.67.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.68.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.68.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.68.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.69.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.69.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.69.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.7.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.7.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.7.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.70.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.70.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.70.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.71.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.71.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.71.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.72.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.72.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.72.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.73.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.73.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.73.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.74.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.74.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.74.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.75.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.75.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.75.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.76.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.76.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.76.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.77.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.77.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.77.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.78.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.78.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.78.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.79.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.79.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.79.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.8.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.8.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.8.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.80.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.80.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.80.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.81.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.81.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.81.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.82.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.82.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.82.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.83.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.83.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.83.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.84.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.84.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.84.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.85.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.85.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.85.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.86.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.86.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.86.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.87.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.87.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.87.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.88.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.88.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.88.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.89.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.89.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.89.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.9.down_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.9.gate_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.9.up_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.mlp.experts.90.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.90.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.90.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.91.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.91.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.91.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.92.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.92.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.92.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.93.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.93.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.93.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.94.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.94.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.94.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.95.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.95.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.95.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.96.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.96.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.96.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.97.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.97.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.97.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.98.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.98.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.98.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.99.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.99.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.experts.99.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.gate.e_score_correction_bias": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.gate.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.31.post_attention_layernorm.weight": "model-00030-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.k_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.o_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.q_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.bias": "model-00029-of-00043.safetensors", + "model.layers.31.self_attn.v_proj.weight": "model-00029-of-00043.safetensors", + "model.layers.32.input_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.0.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.0.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.0.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.1.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.1.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.1.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.10.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.10.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.10.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.100.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.100.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.100.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.101.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.101.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.101.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.102.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.102.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.102.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.103.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.103.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.103.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.104.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.104.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.104.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.105.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.105.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.105.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.106.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.106.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.106.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.107.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.107.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.107.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.108.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.108.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.108.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.109.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.109.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.109.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.11.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.11.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.11.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.110.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.110.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.110.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.111.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.111.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.111.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.112.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.112.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.112.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.113.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.113.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.113.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.114.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.114.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.114.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.115.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.115.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.115.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.116.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.116.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.116.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.117.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.117.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.117.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.118.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.118.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.118.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.119.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.119.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.119.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.12.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.12.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.12.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.120.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.120.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.120.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.121.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.121.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.121.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.122.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.122.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.122.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.123.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.123.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.123.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.124.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.124.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.124.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.125.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.125.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.125.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.126.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.126.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.126.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.127.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.127.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.127.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.13.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.13.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.13.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.14.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.14.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.14.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.15.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.15.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.15.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.16.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.16.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.16.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.17.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.17.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.17.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.18.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.18.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.18.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.19.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.19.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.19.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.2.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.2.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.2.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.20.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.20.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.20.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.21.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.21.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.21.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.22.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.22.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.22.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.23.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.23.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.23.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.24.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.24.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.24.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.25.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.25.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.25.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.26.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.26.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.26.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.27.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.27.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.27.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.28.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.28.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.28.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.29.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.29.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.29.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.3.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.3.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.3.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.30.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.30.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.30.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.31.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.31.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.31.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.32.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.32.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.32.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.33.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.33.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.33.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.34.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.34.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.34.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.35.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.35.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.35.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.36.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.36.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.36.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.37.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.37.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.37.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.38.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.38.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.38.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.39.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.39.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.39.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.4.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.4.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.4.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.40.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.40.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.40.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.41.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.41.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.41.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.42.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.42.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.42.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.43.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.43.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.43.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.44.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.44.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.44.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.45.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.45.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.45.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.46.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.46.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.46.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.47.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.47.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.47.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.48.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.48.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.48.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.49.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.49.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.49.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.5.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.5.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.5.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.50.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.50.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.50.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.51.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.51.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.51.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.52.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.52.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.52.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.53.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.53.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.53.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.54.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.54.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.54.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.55.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.55.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.55.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.56.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.56.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.56.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.57.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.57.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.57.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.58.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.58.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.58.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.59.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.59.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.59.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.6.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.6.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.6.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.60.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.60.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.60.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.61.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.61.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.61.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.62.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.62.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.62.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.63.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.63.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.63.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.64.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.64.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.64.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.65.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.65.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.65.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.66.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.66.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.66.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.67.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.67.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.67.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.68.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.68.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.68.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.69.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.69.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.69.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.7.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.7.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.7.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.70.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.70.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.70.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.71.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.71.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.71.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.72.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.72.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.72.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.73.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.73.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.73.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.74.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.74.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.74.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.75.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.75.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.75.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.76.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.76.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.76.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.77.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.77.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.77.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.78.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.78.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.78.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.79.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.79.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.79.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.8.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.8.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.8.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.80.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.80.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.80.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.81.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.81.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.81.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.82.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.82.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.82.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.83.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.83.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.83.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.84.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.84.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.84.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.85.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.85.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.85.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.86.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.86.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.86.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.87.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.87.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.87.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.88.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.88.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.88.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.89.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.89.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.89.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.9.down_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.9.gate_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.9.up_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.mlp.experts.90.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.90.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.90.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.91.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.91.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.91.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.92.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.92.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.92.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.93.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.93.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.93.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.94.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.94.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.94.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.95.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.95.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.95.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.96.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.96.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.96.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.97.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.97.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.97.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.98.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.98.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.98.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.99.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.99.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.experts.99.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.gate.e_score_correction_bias": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.gate.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.32.post_attention_layernorm.weight": "model-00031-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.k_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.o_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.q_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.bias": "model-00030-of-00043.safetensors", + "model.layers.32.self_attn.v_proj.weight": "model-00030-of-00043.safetensors", + "model.layers.33.input_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.0.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.0.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.0.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.1.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.1.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.1.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.10.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.10.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.10.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.100.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.100.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.100.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.101.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.101.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.101.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.102.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.102.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.102.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.103.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.103.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.103.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.104.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.104.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.104.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.105.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.105.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.105.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.106.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.106.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.106.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.107.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.107.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.107.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.108.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.108.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.108.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.109.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.109.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.109.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.11.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.11.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.11.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.110.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.110.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.110.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.111.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.111.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.111.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.112.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.112.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.112.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.113.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.113.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.113.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.114.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.114.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.114.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.115.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.115.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.115.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.116.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.116.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.116.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.117.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.117.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.117.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.118.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.118.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.118.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.119.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.119.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.119.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.12.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.12.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.12.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.120.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.120.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.120.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.121.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.121.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.121.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.122.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.122.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.122.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.123.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.123.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.123.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.124.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.124.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.124.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.125.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.125.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.125.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.126.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.126.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.126.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.127.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.127.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.127.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.13.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.13.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.13.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.14.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.14.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.14.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.15.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.15.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.15.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.16.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.16.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.16.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.17.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.17.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.17.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.18.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.18.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.18.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.19.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.19.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.19.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.2.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.2.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.2.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.20.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.20.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.20.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.21.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.21.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.21.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.22.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.22.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.22.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.23.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.23.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.23.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.24.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.24.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.24.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.25.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.25.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.25.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.26.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.26.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.26.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.27.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.27.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.27.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.28.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.28.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.28.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.29.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.29.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.29.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.3.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.3.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.3.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.30.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.30.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.30.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.31.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.31.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.31.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.32.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.32.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.32.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.33.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.33.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.33.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.34.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.34.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.34.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.35.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.35.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.35.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.36.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.36.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.36.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.37.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.37.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.37.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.38.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.38.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.38.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.39.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.39.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.39.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.4.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.4.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.4.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.40.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.40.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.40.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.41.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.41.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.41.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.42.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.42.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.42.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.43.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.43.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.43.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.44.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.44.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.44.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.45.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.45.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.45.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.46.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.46.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.46.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.47.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.47.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.47.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.48.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.48.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.48.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.49.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.49.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.49.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.5.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.5.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.5.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.50.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.50.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.50.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.51.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.51.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.51.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.52.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.52.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.52.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.53.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.53.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.53.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.54.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.54.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.54.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.55.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.55.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.55.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.56.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.56.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.56.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.57.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.57.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.57.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.58.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.58.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.58.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.59.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.59.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.59.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.6.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.6.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.6.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.60.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.60.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.60.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.61.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.61.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.61.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.62.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.62.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.62.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.63.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.63.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.63.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.64.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.64.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.64.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.65.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.65.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.65.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.66.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.66.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.66.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.67.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.67.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.67.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.68.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.68.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.68.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.69.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.69.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.69.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.7.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.7.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.7.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.70.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.70.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.70.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.71.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.71.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.71.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.72.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.72.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.72.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.73.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.73.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.73.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.74.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.74.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.74.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.75.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.75.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.75.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.76.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.76.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.76.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.77.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.77.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.77.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.78.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.78.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.78.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.79.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.79.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.79.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.8.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.8.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.8.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.80.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.80.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.80.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.81.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.81.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.81.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.82.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.82.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.82.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.83.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.83.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.83.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.84.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.84.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.84.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.85.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.85.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.85.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.86.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.86.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.86.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.87.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.87.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.87.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.88.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.88.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.88.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.89.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.89.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.89.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.9.down_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.9.gate_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.9.up_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.mlp.experts.90.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.90.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.90.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.91.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.91.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.91.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.92.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.92.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.92.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.93.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.93.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.93.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.94.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.94.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.94.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.95.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.95.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.95.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.96.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.96.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.96.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.97.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.97.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.97.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.98.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.98.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.98.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.99.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.99.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.experts.99.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.gate.e_score_correction_bias": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.gate.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.33.post_attention_layernorm.weight": "model-00032-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.k_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.o_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.q_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.bias": "model-00031-of-00043.safetensors", + "model.layers.33.self_attn.v_proj.weight": "model-00031-of-00043.safetensors", + "model.layers.34.input_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.0.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.0.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.0.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.1.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.1.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.1.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.10.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.10.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.10.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.100.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.100.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.100.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.101.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.101.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.101.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.102.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.102.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.102.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.103.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.103.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.103.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.104.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.104.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.104.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.105.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.105.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.105.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.106.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.106.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.106.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.107.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.107.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.107.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.108.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.108.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.108.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.109.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.109.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.109.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.11.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.11.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.11.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.110.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.110.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.110.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.111.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.111.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.111.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.112.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.112.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.112.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.113.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.113.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.113.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.114.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.114.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.114.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.115.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.115.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.115.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.116.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.116.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.116.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.117.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.117.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.117.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.118.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.118.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.118.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.119.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.119.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.119.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.12.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.12.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.12.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.120.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.120.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.120.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.121.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.121.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.121.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.122.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.122.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.122.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.123.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.123.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.123.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.124.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.124.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.124.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.125.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.125.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.125.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.126.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.126.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.126.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.127.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.127.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.127.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.13.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.13.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.13.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.14.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.14.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.14.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.15.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.15.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.15.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.16.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.16.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.16.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.17.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.17.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.17.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.18.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.18.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.18.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.19.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.19.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.19.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.2.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.2.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.2.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.20.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.20.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.20.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.21.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.21.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.21.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.22.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.22.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.22.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.23.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.23.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.23.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.24.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.24.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.24.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.25.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.25.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.25.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.26.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.26.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.26.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.27.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.27.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.27.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.28.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.28.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.28.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.29.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.29.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.29.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.3.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.3.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.3.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.30.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.30.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.30.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.31.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.31.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.31.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.32.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.32.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.32.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.33.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.33.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.33.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.34.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.34.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.34.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.35.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.35.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.35.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.36.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.36.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.36.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.37.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.37.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.37.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.38.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.38.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.38.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.39.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.39.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.39.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.4.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.4.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.4.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.40.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.40.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.40.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.41.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.41.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.41.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.42.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.42.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.42.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.43.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.43.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.43.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.44.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.44.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.44.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.45.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.45.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.45.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.46.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.46.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.46.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.47.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.47.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.47.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.48.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.48.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.48.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.49.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.49.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.49.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.5.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.5.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.5.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.50.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.50.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.50.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.51.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.51.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.51.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.52.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.52.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.52.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.53.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.53.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.53.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.54.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.54.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.54.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.55.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.55.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.55.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.56.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.56.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.56.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.57.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.57.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.57.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.58.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.58.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.58.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.59.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.59.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.59.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.6.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.6.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.6.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.60.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.60.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.60.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.61.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.61.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.61.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.62.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.62.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.62.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.63.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.63.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.63.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.64.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.64.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.64.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.65.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.65.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.65.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.66.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.66.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.66.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.67.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.67.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.67.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.68.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.68.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.68.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.69.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.69.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.69.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.7.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.7.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.7.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.70.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.70.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.70.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.71.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.71.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.71.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.72.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.72.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.72.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.73.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.73.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.73.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.74.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.74.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.74.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.75.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.75.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.75.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.76.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.76.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.76.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.77.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.77.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.77.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.78.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.78.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.78.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.79.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.79.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.79.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.8.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.8.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.8.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.80.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.80.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.80.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.81.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.81.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.81.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.82.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.82.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.82.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.83.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.83.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.83.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.84.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.84.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.84.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.85.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.85.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.85.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.86.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.86.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.86.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.87.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.87.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.87.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.88.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.88.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.88.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.89.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.89.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.89.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.9.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.9.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.9.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.90.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.90.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.90.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.91.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.91.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.91.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.92.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.92.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.92.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.93.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.93.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.93.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.94.down_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.94.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.94.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.95.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.95.gate_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.95.up_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.mlp.experts.96.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.96.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.96.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.97.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.97.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.97.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.98.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.98.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.98.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.99.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.99.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.experts.99.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.gate.e_score_correction_bias": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.gate.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.34.post_attention_layernorm.weight": "model-00033-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.k_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.o_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.q_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.bias": "model-00032-of-00043.safetensors", + "model.layers.34.self_attn.v_proj.weight": "model-00032-of-00043.safetensors", + "model.layers.35.input_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.0.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.0.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.0.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.1.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.1.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.1.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.10.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.10.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.10.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.100.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.100.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.100.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.101.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.101.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.101.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.102.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.102.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.102.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.103.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.103.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.103.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.104.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.104.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.104.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.105.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.105.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.105.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.106.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.106.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.106.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.107.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.107.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.107.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.108.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.108.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.108.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.109.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.109.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.109.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.11.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.11.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.11.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.110.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.110.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.110.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.111.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.111.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.111.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.112.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.112.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.112.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.113.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.113.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.113.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.114.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.114.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.114.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.115.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.115.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.115.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.116.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.116.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.116.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.117.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.117.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.117.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.118.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.118.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.118.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.119.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.119.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.119.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.12.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.12.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.12.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.120.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.120.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.120.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.121.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.121.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.121.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.122.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.122.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.122.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.123.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.123.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.123.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.124.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.124.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.124.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.125.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.125.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.125.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.126.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.126.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.126.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.127.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.127.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.127.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.experts.13.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.13.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.13.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.14.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.14.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.14.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.15.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.15.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.15.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.16.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.16.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.16.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.17.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.17.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.17.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.18.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.18.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.18.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.19.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.19.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.19.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.2.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.2.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.2.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.20.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.20.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.20.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.21.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.21.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.21.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.22.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.22.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.22.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.23.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.23.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.23.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.24.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.24.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.24.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.25.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.25.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.25.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.26.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.26.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.26.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.27.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.27.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.27.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.28.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.28.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.28.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.29.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.29.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.29.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.3.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.3.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.3.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.30.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.30.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.30.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.31.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.31.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.31.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.32.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.32.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.32.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.33.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.33.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.33.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.34.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.34.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.34.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.35.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.35.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.35.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.36.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.36.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.36.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.37.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.37.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.37.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.38.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.38.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.38.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.39.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.39.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.39.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.4.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.4.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.4.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.40.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.40.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.40.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.41.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.41.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.41.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.42.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.42.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.42.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.43.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.43.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.43.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.44.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.44.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.44.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.45.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.45.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.45.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.46.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.46.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.46.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.47.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.47.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.47.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.48.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.48.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.48.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.49.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.49.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.49.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.5.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.5.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.5.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.50.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.50.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.50.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.51.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.51.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.51.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.52.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.52.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.52.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.53.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.53.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.53.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.54.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.54.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.54.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.55.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.55.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.55.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.56.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.56.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.56.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.57.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.57.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.57.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.58.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.58.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.58.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.59.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.59.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.59.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.6.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.6.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.6.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.60.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.60.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.60.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.61.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.61.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.61.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.62.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.62.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.62.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.63.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.63.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.63.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.64.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.64.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.64.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.65.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.65.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.65.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.66.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.66.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.66.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.67.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.67.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.67.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.68.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.68.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.68.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.69.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.69.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.69.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.7.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.7.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.7.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.70.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.70.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.70.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.71.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.71.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.71.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.72.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.72.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.72.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.73.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.73.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.73.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.74.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.74.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.74.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.75.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.75.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.75.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.76.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.76.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.76.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.77.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.77.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.77.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.78.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.78.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.78.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.79.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.79.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.79.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.8.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.8.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.8.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.80.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.80.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.80.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.81.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.81.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.81.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.82.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.82.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.82.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.83.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.83.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.83.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.84.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.84.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.84.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.85.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.85.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.85.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.86.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.86.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.86.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.87.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.87.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.87.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.88.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.88.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.88.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.89.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.89.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.89.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.9.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.9.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.9.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.90.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.90.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.90.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.91.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.91.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.91.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.92.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.92.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.92.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.93.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.93.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.93.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.94.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.94.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.94.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.95.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.95.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.95.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.96.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.96.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.96.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.97.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.97.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.97.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.98.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.98.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.98.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.99.down_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.99.gate_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.experts.99.up_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.mlp.gate.e_score_correction_bias": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.gate.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.35.post_attention_layernorm.weight": "model-00034-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.k_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.o_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.q_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.bias": "model-00033-of-00043.safetensors", + "model.layers.35.self_attn.v_proj.weight": "model-00033-of-00043.safetensors", + "model.layers.36.input_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.0.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.0.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.0.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.1.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.1.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.1.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.10.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.10.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.10.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.100.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.100.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.100.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.101.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.101.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.101.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.102.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.102.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.102.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.103.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.103.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.103.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.104.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.104.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.104.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.105.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.105.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.105.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.106.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.106.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.106.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.107.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.107.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.107.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.108.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.108.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.108.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.109.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.109.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.109.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.11.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.11.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.11.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.110.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.110.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.110.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.111.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.111.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.111.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.112.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.112.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.112.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.113.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.113.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.113.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.114.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.114.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.114.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.115.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.115.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.115.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.116.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.116.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.116.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.117.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.117.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.117.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.118.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.118.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.118.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.119.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.119.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.119.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.12.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.12.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.12.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.120.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.120.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.120.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.121.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.121.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.121.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.122.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.122.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.122.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.123.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.123.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.123.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.124.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.124.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.124.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.125.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.125.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.125.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.126.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.126.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.126.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.127.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.127.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.127.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.experts.13.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.13.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.13.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.14.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.14.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.14.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.15.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.15.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.15.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.16.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.16.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.16.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.17.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.17.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.17.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.18.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.18.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.18.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.19.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.19.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.19.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.2.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.2.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.2.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.20.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.20.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.20.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.21.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.21.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.21.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.22.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.22.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.22.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.23.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.23.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.23.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.24.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.24.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.24.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.25.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.25.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.25.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.26.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.26.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.26.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.27.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.27.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.27.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.28.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.28.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.28.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.29.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.29.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.29.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.3.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.3.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.3.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.30.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.30.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.30.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.31.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.31.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.31.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.32.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.32.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.32.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.33.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.33.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.33.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.34.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.34.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.34.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.35.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.35.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.35.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.36.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.36.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.36.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.37.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.37.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.37.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.38.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.38.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.38.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.39.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.39.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.39.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.4.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.4.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.4.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.40.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.40.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.40.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.41.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.41.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.41.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.42.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.42.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.42.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.43.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.43.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.43.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.44.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.44.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.44.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.45.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.45.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.45.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.46.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.46.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.46.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.47.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.47.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.47.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.48.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.48.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.48.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.49.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.49.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.49.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.5.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.5.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.5.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.50.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.50.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.50.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.51.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.51.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.51.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.52.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.52.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.52.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.53.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.53.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.53.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.54.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.54.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.54.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.55.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.55.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.55.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.56.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.56.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.56.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.57.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.57.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.57.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.58.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.58.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.58.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.59.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.59.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.59.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.6.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.6.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.6.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.60.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.60.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.60.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.61.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.61.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.61.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.62.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.62.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.62.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.63.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.63.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.63.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.64.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.64.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.64.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.65.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.65.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.65.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.66.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.66.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.66.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.67.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.67.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.67.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.68.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.68.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.68.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.69.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.69.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.69.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.7.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.7.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.7.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.70.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.70.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.70.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.71.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.71.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.71.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.72.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.72.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.72.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.73.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.73.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.73.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.74.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.74.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.74.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.75.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.75.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.75.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.76.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.76.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.76.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.77.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.77.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.77.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.78.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.78.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.78.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.79.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.79.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.79.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.8.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.8.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.8.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.80.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.80.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.80.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.81.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.81.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.81.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.82.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.82.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.82.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.83.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.83.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.83.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.84.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.84.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.84.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.85.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.85.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.85.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.86.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.86.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.86.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.87.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.87.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.87.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.88.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.88.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.88.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.89.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.89.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.89.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.9.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.9.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.9.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.90.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.90.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.90.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.91.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.91.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.91.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.92.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.92.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.92.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.93.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.93.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.93.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.94.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.94.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.94.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.95.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.95.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.95.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.96.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.96.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.96.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.97.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.97.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.97.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.98.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.98.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.98.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.99.down_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.99.gate_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.experts.99.up_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.mlp.gate.e_score_correction_bias": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.gate.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.36.post_attention_layernorm.weight": "model-00035-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.k_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.o_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.q_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.bias": "model-00034-of-00043.safetensors", + "model.layers.36.self_attn.v_proj.weight": "model-00034-of-00043.safetensors", + "model.layers.37.input_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.0.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.0.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.0.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.1.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.1.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.1.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.10.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.10.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.10.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.100.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.100.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.100.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.101.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.101.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.101.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.102.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.102.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.102.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.103.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.103.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.103.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.104.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.104.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.104.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.105.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.105.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.105.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.106.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.106.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.106.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.107.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.107.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.107.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.108.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.108.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.108.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.109.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.109.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.109.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.11.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.11.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.11.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.110.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.110.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.110.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.111.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.111.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.111.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.112.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.112.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.112.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.113.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.113.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.113.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.114.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.114.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.114.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.115.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.115.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.115.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.116.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.116.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.116.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.117.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.117.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.117.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.118.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.118.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.118.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.119.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.119.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.119.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.12.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.12.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.12.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.120.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.120.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.120.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.121.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.121.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.121.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.122.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.122.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.122.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.123.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.123.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.123.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.124.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.124.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.124.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.125.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.125.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.125.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.126.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.126.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.126.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.127.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.127.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.127.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.experts.13.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.13.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.13.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.14.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.14.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.14.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.15.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.15.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.15.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.16.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.16.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.16.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.17.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.17.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.17.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.18.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.18.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.18.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.19.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.19.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.19.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.2.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.2.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.2.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.20.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.20.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.20.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.21.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.21.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.21.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.22.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.22.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.22.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.23.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.23.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.23.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.24.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.24.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.24.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.25.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.25.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.25.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.26.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.26.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.26.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.27.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.27.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.27.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.28.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.28.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.28.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.29.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.29.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.29.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.3.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.3.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.3.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.30.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.30.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.30.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.31.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.31.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.31.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.32.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.32.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.32.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.33.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.33.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.33.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.34.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.34.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.34.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.35.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.35.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.35.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.36.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.36.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.36.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.37.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.37.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.37.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.38.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.38.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.38.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.39.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.39.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.39.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.4.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.4.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.4.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.40.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.40.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.40.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.41.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.41.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.41.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.42.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.42.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.42.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.43.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.43.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.43.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.44.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.44.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.44.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.45.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.45.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.45.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.46.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.46.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.46.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.47.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.47.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.47.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.48.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.48.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.48.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.49.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.49.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.49.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.5.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.5.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.5.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.50.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.50.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.50.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.51.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.51.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.51.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.52.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.52.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.52.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.53.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.53.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.53.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.54.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.54.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.54.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.55.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.55.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.55.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.56.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.56.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.56.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.57.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.57.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.57.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.58.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.58.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.58.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.59.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.59.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.59.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.6.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.6.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.6.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.60.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.60.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.60.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.61.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.61.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.61.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.62.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.62.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.62.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.63.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.63.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.63.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.64.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.64.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.64.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.65.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.65.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.65.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.66.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.66.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.66.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.67.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.67.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.67.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.68.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.68.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.68.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.69.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.69.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.69.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.7.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.7.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.7.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.70.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.70.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.70.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.71.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.71.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.71.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.72.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.72.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.72.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.73.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.73.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.73.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.74.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.74.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.74.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.75.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.75.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.75.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.76.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.76.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.76.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.77.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.77.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.77.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.78.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.78.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.78.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.79.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.79.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.79.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.8.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.8.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.8.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.80.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.80.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.80.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.81.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.81.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.81.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.82.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.82.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.82.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.83.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.83.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.83.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.84.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.84.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.84.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.85.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.85.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.85.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.86.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.86.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.86.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.87.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.87.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.87.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.88.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.88.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.88.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.89.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.89.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.89.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.9.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.9.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.9.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.90.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.90.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.90.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.91.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.91.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.91.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.92.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.92.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.92.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.93.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.93.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.93.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.94.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.94.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.94.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.95.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.95.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.95.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.96.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.96.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.96.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.97.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.97.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.97.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.98.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.98.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.98.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.99.down_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.99.gate_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.experts.99.up_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.mlp.gate.e_score_correction_bias": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.gate.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.37.post_attention_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.k_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.o_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.q_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.bias": "model-00035-of-00043.safetensors", + "model.layers.37.self_attn.v_proj.weight": "model-00035-of-00043.safetensors", + "model.layers.38.input_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.0.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.0.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.0.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.1.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.1.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.1.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.10.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.10.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.10.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.100.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.100.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.100.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.101.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.101.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.101.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.102.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.102.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.102.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.103.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.103.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.103.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.104.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.104.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.104.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.105.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.105.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.105.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.106.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.106.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.106.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.107.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.107.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.107.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.108.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.108.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.108.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.109.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.109.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.109.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.11.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.11.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.11.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.110.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.110.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.110.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.111.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.111.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.111.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.112.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.112.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.112.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.113.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.113.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.113.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.114.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.114.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.114.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.115.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.115.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.115.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.116.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.116.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.116.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.117.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.117.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.117.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.118.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.118.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.118.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.119.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.119.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.119.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.12.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.12.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.12.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.120.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.120.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.120.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.121.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.121.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.121.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.122.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.122.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.122.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.123.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.123.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.123.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.124.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.124.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.124.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.125.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.125.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.125.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.126.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.126.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.126.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.127.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.127.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.127.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.13.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.13.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.13.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.14.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.14.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.14.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.15.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.15.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.15.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.16.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.16.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.16.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.17.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.17.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.17.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.18.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.18.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.18.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.19.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.19.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.19.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.2.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.2.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.2.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.20.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.20.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.20.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.21.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.21.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.21.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.22.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.22.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.22.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.23.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.23.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.23.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.24.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.24.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.24.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.25.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.25.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.25.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.26.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.26.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.26.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.27.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.27.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.27.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.28.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.28.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.28.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.29.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.29.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.29.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.3.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.3.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.3.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.30.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.30.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.30.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.31.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.31.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.31.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.32.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.32.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.32.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.33.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.33.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.33.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.34.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.34.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.34.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.35.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.35.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.35.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.36.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.36.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.36.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.37.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.37.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.37.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.38.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.38.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.38.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.39.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.39.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.39.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.4.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.4.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.4.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.40.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.40.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.40.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.41.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.41.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.41.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.42.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.42.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.42.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.43.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.43.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.43.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.44.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.44.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.44.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.45.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.45.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.45.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.46.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.46.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.46.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.47.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.47.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.47.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.48.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.48.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.48.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.49.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.49.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.49.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.5.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.5.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.5.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.50.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.50.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.50.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.51.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.51.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.51.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.52.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.52.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.52.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.53.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.53.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.53.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.54.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.54.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.54.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.55.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.55.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.55.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.56.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.56.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.56.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.57.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.57.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.57.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.58.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.58.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.58.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.59.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.59.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.59.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.6.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.6.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.6.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.60.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.60.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.60.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.61.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.61.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.61.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.62.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.62.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.62.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.63.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.63.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.63.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.64.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.64.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.64.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.65.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.65.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.65.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.66.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.66.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.66.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.67.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.67.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.67.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.68.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.68.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.68.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.69.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.69.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.69.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.7.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.7.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.7.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.70.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.70.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.70.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.71.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.71.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.71.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.72.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.72.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.72.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.73.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.73.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.73.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.74.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.74.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.74.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.75.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.75.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.75.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.76.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.76.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.76.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.77.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.77.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.77.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.78.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.78.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.78.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.79.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.79.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.79.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.8.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.8.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.8.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.80.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.80.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.80.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.81.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.81.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.81.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.82.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.82.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.82.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.83.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.83.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.83.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.84.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.84.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.84.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.85.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.85.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.85.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.86.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.86.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.86.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.87.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.87.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.87.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.88.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.88.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.88.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.89.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.89.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.89.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.9.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.9.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.9.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.90.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.90.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.90.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.91.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.91.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.91.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.92.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.92.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.92.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.93.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.93.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.93.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.94.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.94.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.94.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.95.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.95.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.95.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.96.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.96.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.96.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.97.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.97.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.97.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.98.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.98.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.98.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.99.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.99.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.experts.99.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.gate.e_score_correction_bias": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.gate.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.down_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.gate_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.mlp.shared_experts.up_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.post_attention_layernorm.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.k_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.o_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.q_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.bias": "model-00036-of-00043.safetensors", + "model.layers.38.self_attn.v_proj.weight": "model-00036-of-00043.safetensors", + "model.layers.39.input_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.0.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.0.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.0.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.1.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.1.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.1.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.10.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.10.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.10.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.100.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.100.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.100.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.101.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.101.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.101.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.102.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.102.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.102.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.103.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.103.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.103.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.104.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.104.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.104.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.105.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.105.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.105.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.106.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.106.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.106.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.107.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.107.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.107.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.108.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.108.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.108.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.109.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.109.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.109.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.11.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.11.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.11.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.110.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.110.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.110.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.111.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.111.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.111.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.112.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.112.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.112.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.113.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.113.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.113.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.114.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.114.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.114.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.115.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.115.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.115.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.116.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.116.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.116.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.117.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.117.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.117.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.118.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.118.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.118.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.119.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.119.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.119.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.12.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.12.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.12.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.120.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.120.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.120.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.121.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.121.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.121.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.122.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.122.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.122.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.123.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.123.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.123.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.124.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.124.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.124.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.125.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.125.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.125.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.126.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.126.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.126.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.127.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.127.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.127.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.13.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.13.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.13.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.14.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.14.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.14.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.15.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.15.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.15.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.16.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.16.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.16.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.17.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.17.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.17.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.18.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.18.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.18.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.19.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.19.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.19.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.2.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.2.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.2.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.20.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.20.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.20.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.21.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.21.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.21.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.22.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.22.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.22.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.23.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.23.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.23.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.24.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.24.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.24.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.25.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.25.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.25.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.26.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.26.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.26.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.27.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.27.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.27.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.28.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.28.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.28.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.29.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.29.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.29.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.3.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.3.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.3.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.30.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.30.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.30.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.31.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.31.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.31.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.32.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.32.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.32.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.33.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.33.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.33.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.34.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.34.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.34.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.35.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.35.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.35.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.36.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.36.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.36.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.37.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.37.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.37.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.38.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.38.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.38.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.39.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.39.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.39.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.4.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.4.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.4.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.40.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.40.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.40.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.41.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.41.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.41.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.42.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.42.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.42.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.43.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.43.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.43.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.44.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.44.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.44.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.45.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.45.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.45.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.46.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.46.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.46.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.47.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.47.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.47.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.48.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.48.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.48.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.49.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.49.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.49.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.5.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.5.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.5.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.50.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.50.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.50.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.51.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.51.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.51.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.52.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.52.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.52.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.53.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.53.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.53.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.54.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.54.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.54.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.55.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.55.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.55.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.56.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.56.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.56.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.57.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.57.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.57.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.58.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.58.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.58.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.59.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.59.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.59.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.6.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.6.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.6.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.60.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.60.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.60.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.61.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.61.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.61.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.62.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.62.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.62.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.63.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.63.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.63.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.64.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.64.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.64.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.65.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.65.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.65.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.66.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.66.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.66.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.67.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.67.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.67.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.68.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.68.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.68.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.69.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.69.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.69.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.7.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.7.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.7.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.70.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.70.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.70.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.71.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.71.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.71.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.72.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.72.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.72.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.73.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.73.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.73.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.74.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.74.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.74.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.75.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.75.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.75.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.76.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.76.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.76.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.77.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.77.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.77.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.78.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.78.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.78.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.79.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.79.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.79.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.8.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.8.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.8.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.80.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.80.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.80.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.81.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.81.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.81.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.82.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.82.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.82.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.83.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.83.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.83.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.84.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.84.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.84.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.85.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.85.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.85.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.86.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.86.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.86.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.87.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.87.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.87.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.88.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.88.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.88.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.89.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.89.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.89.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.9.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.9.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.9.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.90.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.90.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.90.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.91.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.91.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.91.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.92.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.92.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.92.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.93.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.93.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.93.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.94.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.94.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.94.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.95.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.95.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.95.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.96.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.96.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.96.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.97.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.97.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.97.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.98.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.98.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.98.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.99.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.99.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.experts.99.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.gate.e_score_correction_bias": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.gate.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.mlp.shared_experts.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.post_attention_layernorm.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.k_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.o_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.q_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.39.self_attn.v_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.4.input_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.0.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.0.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.0.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.1.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.1.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.1.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.10.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.10.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.10.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.100.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.100.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.100.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.101.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.101.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.101.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.102.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.102.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.102.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.103.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.103.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.103.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.104.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.104.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.104.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.105.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.105.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.105.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.106.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.106.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.106.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.107.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.107.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.107.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.108.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.108.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.108.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.109.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.109.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.109.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.11.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.11.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.11.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.110.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.110.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.110.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.111.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.111.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.111.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.112.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.112.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.112.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.113.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.113.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.113.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.114.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.114.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.114.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.115.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.115.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.115.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.116.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.116.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.116.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.117.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.117.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.117.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.118.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.118.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.118.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.119.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.119.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.119.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.12.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.12.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.12.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.120.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.120.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.120.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.121.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.121.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.121.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.122.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.122.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.122.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.123.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.123.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.123.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.124.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.124.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.124.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.125.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.125.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.125.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.126.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.126.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.126.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.127.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.127.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.127.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.experts.13.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.13.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.13.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.14.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.14.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.14.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.15.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.15.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.15.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.16.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.16.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.16.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.17.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.17.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.17.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.18.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.18.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.18.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.19.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.19.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.19.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.2.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.2.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.2.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.20.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.20.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.20.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.21.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.21.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.21.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.22.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.22.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.22.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.23.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.23.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.23.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.24.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.24.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.24.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.25.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.25.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.25.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.26.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.26.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.26.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.27.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.27.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.27.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.28.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.28.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.28.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.29.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.29.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.29.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.3.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.3.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.3.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.30.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.30.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.30.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.31.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.31.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.31.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.32.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.32.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.32.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.33.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.33.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.33.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.34.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.34.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.34.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.35.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.35.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.35.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.36.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.36.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.36.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.37.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.37.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.37.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.38.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.38.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.38.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.39.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.39.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.39.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.4.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.4.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.4.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.40.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.40.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.40.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.41.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.41.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.41.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.42.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.42.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.42.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.43.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.43.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.43.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.44.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.44.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.44.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.45.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.45.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.45.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.46.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.46.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.46.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.47.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.47.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.47.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.48.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.48.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.48.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.49.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.49.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.49.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.5.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.5.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.5.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.50.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.50.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.50.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.51.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.51.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.51.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.52.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.52.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.52.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.53.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.53.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.53.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.54.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.54.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.54.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.55.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.55.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.55.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.56.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.56.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.56.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.57.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.57.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.57.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.58.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.58.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.58.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.59.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.59.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.59.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.6.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.6.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.6.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.60.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.60.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.60.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.61.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.61.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.61.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.62.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.62.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.62.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.63.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.63.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.63.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.64.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.64.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.64.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.65.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.65.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.65.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.66.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.66.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.66.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.67.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.67.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.67.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.68.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.68.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.68.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.69.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.69.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.69.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.7.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.7.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.7.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.70.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.70.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.70.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.71.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.71.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.71.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.72.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.72.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.72.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.73.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.73.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.73.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.74.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.74.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.74.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.75.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.75.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.75.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.76.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.76.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.76.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.77.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.77.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.77.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.78.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.78.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.78.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.79.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.79.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.79.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.8.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.8.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.8.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.80.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.80.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.80.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.81.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.81.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.81.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.82.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.82.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.82.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.83.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.83.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.83.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.84.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.84.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.84.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.85.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.85.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.85.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.86.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.86.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.86.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.87.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.87.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.87.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.88.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.88.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.88.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.89.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.89.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.89.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.9.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.9.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.9.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.90.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.90.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.90.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.91.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.91.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.91.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.92.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.92.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.92.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.93.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.93.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.93.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.94.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.94.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.94.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.95.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.95.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.95.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.96.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.96.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.96.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.97.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.97.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.97.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.98.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.98.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.98.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.99.down_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.99.gate_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.experts.99.up_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.mlp.gate.e_score_correction_bias": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.gate.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.mlp.shared_experts.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.4.post_attention_layernorm.weight": "model-00005-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.k_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.o_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.q_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.bias": "model-00004-of-00043.safetensors", + "model.layers.4.self_attn.v_proj.weight": "model-00004-of-00043.safetensors", + "model.layers.40.input_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.0.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.0.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.0.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.1.down_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.1.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.1.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.10.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.10.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.10.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.100.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.100.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.100.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.101.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.101.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.101.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.102.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.102.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.102.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.103.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.103.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.103.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.104.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.104.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.104.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.105.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.105.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.105.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.106.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.106.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.106.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.107.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.107.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.107.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.108.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.108.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.108.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.109.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.109.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.109.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.11.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.11.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.11.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.110.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.110.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.110.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.111.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.111.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.111.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.112.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.112.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.112.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.113.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.113.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.113.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.114.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.114.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.114.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.115.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.115.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.115.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.116.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.116.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.116.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.117.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.117.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.117.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.118.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.118.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.118.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.119.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.119.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.119.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.12.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.12.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.12.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.120.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.120.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.120.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.121.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.121.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.121.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.122.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.122.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.122.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.123.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.123.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.123.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.124.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.124.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.124.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.125.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.125.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.125.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.126.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.126.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.126.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.127.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.127.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.127.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.13.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.13.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.13.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.14.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.14.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.14.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.15.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.15.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.15.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.16.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.16.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.16.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.17.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.17.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.17.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.18.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.18.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.18.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.19.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.19.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.19.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.2.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.2.gate_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.2.up_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.mlp.experts.20.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.20.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.20.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.21.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.21.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.21.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.22.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.22.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.22.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.23.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.23.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.23.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.24.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.24.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.24.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.25.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.25.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.25.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.26.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.26.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.26.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.27.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.27.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.27.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.28.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.28.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.28.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.29.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.29.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.29.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.3.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.3.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.3.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.30.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.30.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.30.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.31.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.31.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.31.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.32.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.32.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.32.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.33.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.33.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.33.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.34.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.34.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.34.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.35.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.35.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.35.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.36.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.36.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.36.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.37.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.37.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.37.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.38.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.38.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.38.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.39.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.39.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.39.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.4.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.4.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.4.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.40.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.40.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.40.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.41.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.41.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.41.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.42.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.42.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.42.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.43.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.43.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.43.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.44.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.44.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.44.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.45.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.45.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.45.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.46.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.46.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.46.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.47.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.47.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.47.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.48.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.48.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.48.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.49.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.49.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.49.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.5.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.5.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.5.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.50.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.50.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.50.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.51.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.51.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.51.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.52.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.52.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.52.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.53.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.53.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.53.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.54.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.54.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.54.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.55.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.55.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.55.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.56.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.56.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.56.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.57.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.57.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.57.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.58.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.58.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.58.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.59.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.59.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.59.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.6.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.6.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.6.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.60.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.60.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.60.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.61.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.61.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.61.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.62.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.62.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.62.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.63.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.63.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.63.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.64.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.64.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.64.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.65.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.65.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.65.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.66.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.66.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.66.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.67.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.67.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.67.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.68.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.68.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.68.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.69.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.69.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.69.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.7.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.7.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.7.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.70.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.70.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.70.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.71.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.71.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.71.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.72.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.72.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.72.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.73.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.73.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.73.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.74.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.74.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.74.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.75.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.75.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.75.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.76.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.76.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.76.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.77.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.77.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.77.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.78.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.78.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.78.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.79.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.79.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.79.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.8.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.8.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.8.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.80.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.80.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.80.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.81.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.81.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.81.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.82.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.82.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.82.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.83.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.83.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.83.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.84.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.84.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.84.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.85.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.85.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.85.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.86.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.86.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.86.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.87.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.87.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.87.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.88.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.88.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.88.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.89.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.89.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.89.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.9.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.9.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.9.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.90.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.90.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.90.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.91.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.91.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.91.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.92.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.92.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.92.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.93.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.93.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.93.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.94.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.94.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.94.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.95.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.95.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.95.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.96.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.96.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.96.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.97.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.97.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.97.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.98.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.98.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.98.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.99.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.99.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.experts.99.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.gate.e_score_correction_bias": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.gate.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.mlp.shared_experts.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.40.post_attention_layernorm.weight": "model-00038-of-00043.safetensors", + "model.layers.40.self_attn.k_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.k_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.o_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.q_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.q_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.v_proj.bias": "model-00037-of-00043.safetensors", + "model.layers.40.self_attn.v_proj.weight": "model-00037-of-00043.safetensors", + "model.layers.41.input_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.0.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.0.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.0.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.1.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.1.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.1.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.10.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.10.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.10.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.100.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.100.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.100.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.101.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.101.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.101.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.102.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.102.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.102.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.103.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.103.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.103.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.104.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.104.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.104.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.105.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.105.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.105.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.106.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.106.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.106.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.107.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.107.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.107.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.108.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.108.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.108.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.109.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.109.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.109.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.11.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.11.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.11.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.110.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.110.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.110.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.111.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.111.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.111.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.112.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.112.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.112.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.113.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.113.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.113.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.114.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.114.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.114.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.115.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.115.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.115.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.116.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.116.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.116.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.117.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.117.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.117.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.118.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.118.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.118.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.119.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.119.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.119.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.12.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.12.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.12.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.120.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.120.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.120.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.121.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.121.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.121.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.122.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.122.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.122.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.123.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.123.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.123.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.124.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.124.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.124.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.125.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.125.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.125.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.126.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.126.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.126.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.127.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.127.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.127.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.13.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.13.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.13.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.14.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.14.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.14.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.15.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.15.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.15.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.16.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.16.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.16.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.17.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.17.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.17.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.18.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.18.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.18.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.19.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.19.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.19.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.2.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.2.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.2.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.20.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.20.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.20.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.21.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.21.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.21.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.22.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.22.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.22.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.23.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.23.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.23.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.24.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.24.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.24.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.25.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.25.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.25.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.26.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.26.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.26.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.27.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.27.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.27.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.28.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.28.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.28.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.29.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.29.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.29.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.3.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.3.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.3.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.30.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.30.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.30.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.31.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.31.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.31.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.32.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.32.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.32.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.33.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.33.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.33.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.34.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.34.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.34.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.35.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.35.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.35.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.36.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.36.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.36.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.37.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.37.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.37.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.38.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.38.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.38.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.39.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.39.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.39.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.4.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.4.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.4.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.40.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.40.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.40.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.41.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.41.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.41.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.42.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.42.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.42.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.43.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.43.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.43.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.44.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.44.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.44.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.45.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.45.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.45.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.46.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.46.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.46.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.47.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.47.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.47.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.48.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.48.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.48.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.49.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.49.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.49.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.5.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.5.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.5.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.50.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.50.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.50.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.51.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.51.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.51.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.52.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.52.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.52.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.53.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.53.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.53.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.54.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.54.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.54.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.55.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.55.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.55.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.56.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.56.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.56.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.57.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.57.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.57.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.58.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.58.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.58.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.59.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.59.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.59.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.6.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.6.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.6.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.60.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.60.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.60.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.61.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.61.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.61.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.62.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.62.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.62.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.63.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.63.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.63.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.64.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.64.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.64.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.65.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.65.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.65.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.66.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.66.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.66.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.67.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.67.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.67.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.68.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.68.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.68.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.69.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.69.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.69.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.7.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.7.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.7.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.70.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.70.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.70.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.71.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.71.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.71.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.72.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.72.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.72.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.73.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.73.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.73.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.74.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.74.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.74.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.75.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.75.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.75.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.76.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.76.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.76.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.77.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.77.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.77.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.78.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.78.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.78.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.79.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.79.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.79.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.8.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.8.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.8.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.80.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.80.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.80.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.81.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.81.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.81.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.82.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.82.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.82.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.83.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.83.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.83.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.84.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.84.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.84.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.85.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.85.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.85.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.86.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.86.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.86.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.87.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.87.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.87.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.88.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.88.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.88.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.89.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.89.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.89.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.9.down_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.9.gate_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.9.up_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.mlp.experts.90.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.90.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.90.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.91.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.91.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.91.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.92.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.92.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.92.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.93.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.93.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.93.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.94.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.94.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.94.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.95.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.95.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.95.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.96.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.96.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.96.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.97.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.97.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.97.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.98.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.98.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.98.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.99.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.99.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.experts.99.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.gate.e_score_correction_bias": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.gate.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.mlp.shared_experts.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.41.post_attention_layernorm.weight": "model-00039-of-00043.safetensors", + "model.layers.41.self_attn.k_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.k_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.o_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.q_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.q_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.v_proj.bias": "model-00038-of-00043.safetensors", + "model.layers.41.self_attn.v_proj.weight": "model-00038-of-00043.safetensors", + "model.layers.42.input_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.0.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.0.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.0.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.1.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.1.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.1.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.10.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.10.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.10.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.100.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.100.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.100.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.101.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.101.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.101.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.102.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.102.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.102.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.103.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.103.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.103.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.104.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.104.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.104.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.105.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.105.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.105.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.106.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.106.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.106.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.107.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.107.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.107.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.108.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.108.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.108.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.109.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.109.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.109.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.11.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.11.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.11.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.110.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.110.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.110.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.111.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.111.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.111.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.112.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.112.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.112.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.113.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.113.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.113.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.114.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.114.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.114.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.115.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.115.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.115.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.116.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.116.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.116.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.117.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.117.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.117.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.118.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.118.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.118.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.119.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.119.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.119.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.12.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.12.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.12.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.120.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.120.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.120.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.121.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.121.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.121.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.122.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.122.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.122.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.123.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.123.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.123.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.124.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.124.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.124.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.125.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.125.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.125.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.126.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.126.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.126.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.127.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.127.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.127.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.13.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.13.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.13.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.14.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.14.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.14.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.15.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.15.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.15.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.16.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.16.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.16.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.17.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.17.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.17.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.18.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.18.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.18.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.19.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.19.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.19.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.2.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.2.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.2.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.20.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.20.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.20.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.21.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.21.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.21.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.22.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.22.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.22.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.23.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.23.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.23.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.24.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.24.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.24.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.25.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.25.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.25.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.26.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.26.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.26.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.27.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.27.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.27.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.28.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.28.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.28.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.29.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.29.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.29.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.3.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.3.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.3.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.30.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.30.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.30.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.31.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.31.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.31.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.32.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.32.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.32.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.33.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.33.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.33.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.34.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.34.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.34.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.35.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.35.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.35.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.36.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.36.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.36.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.37.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.37.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.37.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.38.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.38.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.38.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.39.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.39.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.39.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.4.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.4.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.4.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.40.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.40.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.40.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.41.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.41.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.41.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.42.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.42.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.42.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.43.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.43.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.43.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.44.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.44.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.44.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.45.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.45.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.45.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.46.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.46.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.46.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.47.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.47.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.47.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.48.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.48.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.48.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.49.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.49.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.49.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.5.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.5.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.5.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.50.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.50.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.50.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.51.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.51.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.51.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.52.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.52.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.52.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.53.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.53.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.53.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.54.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.54.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.54.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.55.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.55.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.55.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.56.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.56.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.56.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.57.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.57.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.57.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.58.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.58.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.58.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.59.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.59.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.59.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.6.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.6.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.6.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.60.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.60.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.60.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.61.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.61.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.61.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.62.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.62.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.62.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.63.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.63.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.63.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.64.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.64.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.64.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.65.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.65.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.65.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.66.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.66.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.66.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.67.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.67.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.67.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.68.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.68.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.68.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.69.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.69.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.69.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.7.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.7.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.7.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.70.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.70.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.70.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.71.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.71.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.71.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.72.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.72.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.72.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.73.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.73.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.73.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.74.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.74.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.74.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.75.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.75.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.75.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.76.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.76.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.76.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.77.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.77.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.77.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.78.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.78.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.78.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.79.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.79.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.79.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.8.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.8.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.8.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.80.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.80.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.80.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.81.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.81.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.81.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.82.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.82.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.82.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.83.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.83.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.83.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.84.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.84.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.84.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.85.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.85.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.85.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.86.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.86.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.86.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.87.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.87.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.87.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.88.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.88.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.88.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.89.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.89.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.89.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.9.down_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.9.gate_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.9.up_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.mlp.experts.90.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.90.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.90.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.91.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.91.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.91.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.92.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.92.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.92.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.93.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.93.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.93.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.94.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.94.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.94.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.95.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.95.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.95.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.96.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.96.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.96.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.97.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.97.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.97.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.98.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.98.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.98.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.99.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.99.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.experts.99.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.gate.e_score_correction_bias": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.gate.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.mlp.shared_experts.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.42.post_attention_layernorm.weight": "model-00040-of-00043.safetensors", + "model.layers.42.self_attn.k_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.k_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.o_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.q_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.q_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.v_proj.bias": "model-00039-of-00043.safetensors", + "model.layers.42.self_attn.v_proj.weight": "model-00039-of-00043.safetensors", + "model.layers.43.input_layernorm.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.0.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.0.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.0.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.1.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.1.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.1.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.10.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.10.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.10.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.100.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.100.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.100.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.101.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.101.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.101.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.102.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.102.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.102.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.103.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.103.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.103.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.104.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.104.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.104.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.105.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.105.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.105.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.106.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.106.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.106.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.107.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.107.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.107.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.108.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.108.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.108.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.109.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.109.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.109.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.11.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.11.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.11.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.110.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.110.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.110.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.111.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.111.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.111.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.112.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.112.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.112.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.113.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.113.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.113.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.114.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.114.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.114.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.115.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.115.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.115.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.116.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.116.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.116.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.117.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.117.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.117.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.118.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.118.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.118.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.119.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.119.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.119.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.12.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.12.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.12.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.120.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.120.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.120.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.121.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.121.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.121.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.122.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.122.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.122.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.123.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.123.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.123.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.124.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.124.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.124.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.125.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.125.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.125.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.126.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.126.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.126.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.127.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.127.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.127.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.13.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.13.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.13.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.14.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.14.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.14.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.15.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.15.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.15.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.16.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.16.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.16.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.17.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.17.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.17.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.18.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.18.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.18.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.19.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.19.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.19.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.2.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.2.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.2.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.20.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.20.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.20.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.21.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.21.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.21.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.22.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.22.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.22.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.23.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.23.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.23.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.24.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.24.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.24.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.25.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.25.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.25.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.26.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.26.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.26.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.27.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.27.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.27.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.28.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.28.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.28.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.29.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.29.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.29.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.3.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.3.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.3.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.30.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.30.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.30.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.31.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.31.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.31.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.32.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.32.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.32.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.33.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.33.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.33.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.34.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.34.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.34.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.35.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.35.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.35.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.36.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.36.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.36.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.37.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.37.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.37.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.38.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.38.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.38.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.39.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.39.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.39.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.4.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.4.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.4.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.40.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.40.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.40.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.41.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.41.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.41.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.42.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.42.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.42.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.43.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.43.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.43.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.44.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.44.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.44.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.45.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.45.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.45.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.46.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.46.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.46.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.47.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.47.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.47.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.48.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.48.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.48.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.49.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.49.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.49.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.5.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.5.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.5.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.50.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.50.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.50.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.51.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.51.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.51.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.52.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.52.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.52.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.53.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.53.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.53.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.54.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.54.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.54.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.55.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.55.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.55.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.56.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.56.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.56.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.57.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.57.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.57.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.58.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.58.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.58.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.59.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.59.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.59.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.6.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.6.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.6.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.60.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.60.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.60.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.61.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.61.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.61.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.62.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.62.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.62.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.63.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.63.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.63.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.64.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.64.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.64.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.65.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.65.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.65.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.66.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.66.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.66.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.67.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.67.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.67.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.68.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.68.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.68.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.69.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.69.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.69.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.7.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.7.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.7.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.70.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.70.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.70.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.71.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.71.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.71.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.72.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.72.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.72.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.73.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.73.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.73.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.74.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.74.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.74.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.75.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.75.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.75.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.76.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.76.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.76.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.77.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.77.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.77.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.78.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.78.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.78.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.79.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.79.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.79.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.8.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.8.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.8.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.80.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.80.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.80.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.81.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.81.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.81.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.82.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.82.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.82.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.83.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.83.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.83.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.84.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.84.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.84.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.85.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.85.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.85.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.86.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.86.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.86.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.87.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.87.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.87.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.88.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.88.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.88.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.89.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.89.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.89.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.9.down_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.9.gate_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.9.up_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.mlp.experts.90.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.90.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.90.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.91.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.91.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.91.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.92.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.92.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.92.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.93.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.93.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.93.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.94.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.94.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.94.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.95.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.95.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.95.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.96.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.96.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.96.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.97.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.97.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.97.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.98.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.98.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.98.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.99.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.99.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.experts.99.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.gate.e_score_correction_bias": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.gate.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.mlp.shared_experts.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.43.post_attention_layernorm.weight": "model-00041-of-00043.safetensors", + "model.layers.43.self_attn.k_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.k_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.o_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.q_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.q_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.v_proj.bias": "model-00040-of-00043.safetensors", + "model.layers.43.self_attn.v_proj.weight": "model-00040-of-00043.safetensors", + "model.layers.44.input_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.0.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.0.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.0.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.1.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.1.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.1.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.10.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.10.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.10.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.100.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.100.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.100.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.101.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.101.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.101.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.102.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.102.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.102.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.103.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.103.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.103.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.104.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.104.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.104.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.105.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.105.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.105.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.106.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.106.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.106.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.107.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.107.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.107.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.108.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.108.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.108.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.109.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.109.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.109.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.11.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.11.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.11.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.110.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.110.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.110.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.111.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.111.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.111.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.112.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.112.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.112.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.113.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.113.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.113.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.114.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.114.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.114.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.115.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.115.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.115.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.116.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.116.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.116.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.117.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.117.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.117.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.118.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.118.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.118.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.119.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.119.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.119.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.12.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.12.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.12.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.120.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.120.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.120.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.121.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.121.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.121.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.122.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.122.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.122.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.123.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.123.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.123.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.124.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.124.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.124.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.125.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.125.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.125.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.126.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.126.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.126.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.127.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.127.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.127.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.13.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.13.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.13.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.14.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.14.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.14.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.15.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.15.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.15.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.16.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.16.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.16.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.17.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.17.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.17.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.18.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.18.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.18.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.19.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.19.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.19.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.2.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.2.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.2.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.20.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.20.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.20.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.21.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.21.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.21.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.22.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.22.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.22.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.23.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.23.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.23.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.24.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.24.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.24.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.25.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.25.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.25.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.26.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.26.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.26.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.27.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.27.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.27.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.28.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.28.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.28.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.29.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.29.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.29.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.3.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.3.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.3.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.30.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.30.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.30.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.31.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.31.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.31.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.32.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.32.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.32.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.33.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.33.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.33.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.34.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.34.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.34.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.35.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.35.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.35.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.36.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.36.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.36.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.37.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.37.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.37.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.38.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.38.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.38.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.39.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.39.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.39.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.4.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.4.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.4.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.40.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.40.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.40.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.41.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.41.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.41.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.42.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.42.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.42.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.43.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.43.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.43.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.44.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.44.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.44.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.45.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.45.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.45.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.46.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.46.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.46.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.47.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.47.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.47.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.48.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.48.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.48.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.49.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.49.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.49.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.5.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.5.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.5.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.50.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.50.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.50.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.51.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.51.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.51.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.52.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.52.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.52.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.53.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.53.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.53.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.54.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.54.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.54.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.55.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.55.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.55.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.56.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.56.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.56.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.57.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.57.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.57.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.58.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.58.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.58.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.59.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.59.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.59.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.6.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.6.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.6.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.60.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.60.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.60.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.61.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.61.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.61.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.62.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.62.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.62.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.63.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.63.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.63.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.64.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.64.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.64.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.65.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.65.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.65.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.66.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.66.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.66.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.67.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.67.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.67.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.68.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.68.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.68.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.69.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.69.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.69.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.7.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.7.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.7.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.70.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.70.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.70.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.71.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.71.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.71.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.72.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.72.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.72.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.73.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.73.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.73.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.74.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.74.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.74.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.75.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.75.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.75.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.76.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.76.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.76.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.77.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.77.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.77.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.78.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.78.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.78.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.79.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.79.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.79.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.8.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.8.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.8.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.80.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.80.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.80.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.81.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.81.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.81.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.82.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.82.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.82.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.83.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.83.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.83.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.84.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.84.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.84.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.85.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.85.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.85.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.86.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.86.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.86.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.87.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.87.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.87.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.88.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.88.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.88.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.89.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.89.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.89.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.9.down_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.9.gate_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.9.up_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.mlp.experts.90.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.90.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.90.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.91.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.91.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.91.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.92.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.92.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.92.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.93.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.93.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.93.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.94.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.94.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.94.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.95.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.95.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.95.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.96.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.96.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.96.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.97.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.97.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.97.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.98.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.98.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.98.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.99.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.99.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.experts.99.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.gate.e_score_correction_bias": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.gate.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.mlp.shared_experts.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.44.post_attention_layernorm.weight": "model-00042-of-00043.safetensors", + "model.layers.44.self_attn.k_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.k_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.o_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.q_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.q_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.v_proj.bias": "model-00041-of-00043.safetensors", + "model.layers.44.self_attn.v_proj.weight": "model-00041-of-00043.safetensors", + "model.layers.45.input_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.0.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.0.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.0.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.1.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.1.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.1.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.10.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.10.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.10.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.100.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.100.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.100.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.101.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.101.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.101.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.102.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.102.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.102.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.103.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.103.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.103.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.104.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.104.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.104.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.105.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.105.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.105.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.106.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.106.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.106.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.107.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.107.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.107.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.108.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.108.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.108.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.109.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.109.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.109.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.11.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.11.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.11.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.110.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.110.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.110.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.111.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.111.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.111.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.112.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.112.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.112.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.113.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.113.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.113.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.114.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.114.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.114.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.115.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.115.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.115.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.116.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.116.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.116.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.117.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.117.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.117.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.118.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.118.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.118.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.119.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.119.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.119.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.12.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.12.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.12.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.120.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.120.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.120.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.121.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.121.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.121.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.122.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.122.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.122.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.123.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.123.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.123.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.124.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.124.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.124.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.125.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.125.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.125.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.126.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.126.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.126.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.127.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.127.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.127.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.13.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.13.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.13.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.14.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.14.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.14.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.15.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.15.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.15.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.16.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.16.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.16.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.17.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.17.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.17.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.18.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.18.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.18.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.19.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.19.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.19.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.2.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.2.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.2.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.20.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.20.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.20.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.21.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.21.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.21.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.22.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.22.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.22.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.23.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.23.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.23.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.24.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.24.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.24.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.25.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.25.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.25.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.26.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.26.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.26.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.27.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.27.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.27.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.28.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.28.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.28.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.29.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.29.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.29.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.3.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.3.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.3.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.30.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.30.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.30.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.31.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.31.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.31.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.32.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.32.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.32.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.33.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.33.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.33.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.34.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.34.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.34.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.35.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.35.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.35.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.36.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.36.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.36.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.37.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.37.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.37.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.38.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.38.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.38.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.39.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.39.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.39.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.4.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.4.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.4.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.40.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.40.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.40.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.41.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.41.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.41.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.42.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.42.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.42.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.43.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.43.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.43.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.44.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.44.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.44.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.45.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.45.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.45.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.46.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.46.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.46.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.47.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.47.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.47.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.48.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.48.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.48.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.49.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.49.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.49.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.5.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.5.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.5.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.50.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.50.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.50.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.51.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.51.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.51.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.52.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.52.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.52.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.53.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.53.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.53.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.54.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.54.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.54.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.55.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.55.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.55.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.56.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.56.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.56.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.57.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.57.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.57.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.58.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.58.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.58.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.59.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.59.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.59.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.6.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.6.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.6.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.60.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.60.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.60.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.61.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.61.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.61.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.62.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.62.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.62.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.63.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.63.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.63.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.64.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.64.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.64.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.65.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.65.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.65.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.66.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.66.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.66.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.67.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.67.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.67.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.68.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.68.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.68.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.69.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.69.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.69.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.7.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.7.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.7.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.70.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.70.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.70.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.71.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.71.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.71.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.72.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.72.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.72.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.73.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.73.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.73.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.74.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.74.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.74.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.75.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.75.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.75.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.76.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.76.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.76.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.77.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.77.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.77.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.78.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.78.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.78.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.79.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.79.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.79.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.8.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.8.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.8.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.80.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.80.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.80.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.81.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.81.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.81.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.82.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.82.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.82.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.83.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.83.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.83.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.84.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.84.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.84.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.85.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.85.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.85.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.86.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.86.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.86.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.87.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.87.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.87.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.88.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.88.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.88.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.89.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.89.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.89.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.9.down_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.9.gate_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.9.up_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.mlp.experts.90.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.90.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.90.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.91.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.91.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.91.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.92.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.92.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.92.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.93.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.93.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.93.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.94.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.94.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.94.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.95.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.95.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.95.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.96.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.96.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.96.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.97.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.97.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.97.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.98.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.98.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.98.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.99.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.99.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.experts.99.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.gate.e_score_correction_bias": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.gate.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.down_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.gate_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.mlp.shared_experts.up_proj.weight": "model-00043-of-00043.safetensors", + "model.layers.45.post_attention_layernorm.weight": "model-00043-of-00043.safetensors", + "model.layers.45.self_attn.k_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.k_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.o_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.q_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.q_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.v_proj.bias": "model-00042-of-00043.safetensors", + "model.layers.45.self_attn.v_proj.weight": "model-00042-of-00043.safetensors", + "model.layers.5.input_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.0.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.0.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.0.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.1.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.1.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.1.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.10.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.10.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.10.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.100.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.100.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.100.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.101.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.101.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.101.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.102.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.102.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.102.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.103.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.103.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.103.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.104.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.104.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.104.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.105.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.105.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.105.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.106.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.106.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.106.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.107.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.107.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.107.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.108.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.108.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.108.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.109.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.109.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.109.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.11.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.11.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.11.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.110.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.110.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.110.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.111.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.111.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.111.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.112.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.112.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.112.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.113.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.113.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.113.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.114.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.114.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.114.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.115.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.115.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.115.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.116.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.116.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.116.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.117.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.117.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.117.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.118.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.118.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.118.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.119.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.119.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.119.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.12.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.12.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.12.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.120.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.120.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.120.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.121.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.121.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.121.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.122.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.122.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.122.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.123.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.123.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.123.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.124.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.124.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.124.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.125.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.125.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.125.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.126.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.126.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.126.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.127.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.127.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.127.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.experts.13.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.13.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.13.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.14.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.14.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.14.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.15.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.15.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.15.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.16.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.16.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.16.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.17.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.17.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.17.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.18.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.18.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.18.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.19.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.19.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.19.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.2.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.2.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.2.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.20.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.20.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.20.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.21.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.21.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.21.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.22.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.22.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.22.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.23.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.23.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.23.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.24.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.24.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.24.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.25.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.25.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.25.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.26.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.26.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.26.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.27.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.27.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.27.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.28.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.28.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.28.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.29.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.29.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.29.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.3.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.3.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.3.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.30.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.30.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.30.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.31.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.31.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.31.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.32.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.32.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.32.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.33.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.33.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.33.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.34.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.34.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.34.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.35.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.35.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.35.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.36.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.36.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.36.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.37.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.37.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.37.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.38.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.38.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.38.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.39.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.39.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.39.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.4.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.4.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.4.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.40.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.40.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.40.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.41.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.41.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.41.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.42.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.42.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.42.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.43.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.43.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.43.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.44.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.44.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.44.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.45.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.45.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.45.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.46.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.46.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.46.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.47.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.47.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.47.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.48.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.48.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.48.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.49.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.49.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.49.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.5.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.5.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.5.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.50.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.50.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.50.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.51.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.51.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.51.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.52.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.52.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.52.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.53.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.53.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.53.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.54.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.54.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.54.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.55.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.55.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.55.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.56.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.56.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.56.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.57.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.57.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.57.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.58.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.58.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.58.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.59.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.59.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.59.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.6.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.6.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.6.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.60.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.60.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.60.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.61.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.61.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.61.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.62.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.62.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.62.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.63.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.63.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.63.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.64.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.64.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.64.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.65.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.65.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.65.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.66.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.66.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.66.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.67.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.67.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.67.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.68.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.68.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.68.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.69.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.69.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.69.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.7.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.7.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.7.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.70.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.70.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.70.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.71.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.71.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.71.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.72.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.72.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.72.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.73.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.73.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.73.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.74.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.74.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.74.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.75.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.75.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.75.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.76.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.76.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.76.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.77.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.77.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.77.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.78.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.78.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.78.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.79.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.79.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.79.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.8.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.8.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.8.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.80.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.80.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.80.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.81.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.81.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.81.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.82.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.82.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.82.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.83.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.83.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.83.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.84.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.84.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.84.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.85.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.85.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.85.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.86.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.86.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.86.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.87.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.87.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.87.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.88.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.88.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.88.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.89.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.89.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.89.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.9.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.9.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.9.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.90.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.90.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.90.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.91.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.91.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.91.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.92.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.92.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.92.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.93.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.93.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.93.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.94.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.94.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.94.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.95.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.95.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.95.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.96.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.96.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.96.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.97.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.97.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.97.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.98.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.98.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.98.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.99.down_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.99.gate_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.experts.99.up_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.mlp.gate.e_score_correction_bias": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.gate.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.mlp.shared_experts.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.5.post_attention_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.k_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.o_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.q_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.bias": "model-00005-of-00043.safetensors", + "model.layers.5.self_attn.v_proj.weight": "model-00005-of-00043.safetensors", + "model.layers.6.input_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.0.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.0.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.0.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.1.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.1.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.1.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.10.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.10.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.10.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.100.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.100.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.100.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.101.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.101.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.101.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.102.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.102.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.102.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.103.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.103.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.103.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.104.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.104.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.104.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.105.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.105.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.105.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.106.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.106.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.106.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.107.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.107.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.107.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.108.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.108.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.108.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.109.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.109.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.109.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.11.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.11.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.11.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.110.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.110.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.110.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.111.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.111.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.111.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.112.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.112.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.112.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.113.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.113.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.113.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.114.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.114.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.114.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.115.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.115.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.115.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.116.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.116.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.116.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.117.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.117.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.117.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.118.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.118.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.118.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.119.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.119.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.119.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.12.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.12.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.12.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.120.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.120.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.120.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.121.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.121.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.121.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.122.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.122.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.122.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.123.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.123.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.123.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.124.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.124.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.124.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.125.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.125.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.125.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.126.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.126.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.126.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.127.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.127.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.127.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.13.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.13.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.13.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.14.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.14.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.14.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.15.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.15.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.15.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.16.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.16.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.16.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.17.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.17.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.17.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.18.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.18.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.18.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.19.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.19.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.19.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.2.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.2.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.2.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.20.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.20.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.20.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.21.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.21.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.21.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.22.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.22.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.22.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.23.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.23.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.23.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.24.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.24.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.24.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.25.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.25.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.25.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.26.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.26.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.26.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.27.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.27.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.27.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.28.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.28.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.28.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.29.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.29.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.29.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.3.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.3.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.3.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.30.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.30.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.30.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.31.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.31.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.31.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.32.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.32.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.32.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.33.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.33.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.33.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.34.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.34.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.34.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.35.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.35.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.35.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.36.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.36.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.36.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.37.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.37.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.37.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.38.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.38.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.38.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.39.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.39.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.39.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.4.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.4.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.4.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.40.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.40.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.40.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.41.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.41.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.41.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.42.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.42.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.42.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.43.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.43.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.43.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.44.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.44.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.44.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.45.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.45.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.45.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.46.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.46.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.46.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.47.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.47.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.47.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.48.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.48.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.48.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.49.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.49.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.49.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.5.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.5.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.5.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.50.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.50.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.50.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.51.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.51.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.51.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.52.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.52.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.52.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.53.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.53.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.53.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.54.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.54.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.54.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.55.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.55.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.55.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.56.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.56.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.56.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.57.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.57.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.57.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.58.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.58.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.58.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.59.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.59.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.59.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.6.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.6.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.6.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.60.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.60.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.60.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.61.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.61.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.61.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.62.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.62.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.62.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.63.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.63.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.63.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.64.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.64.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.64.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.65.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.65.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.65.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.66.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.66.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.66.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.67.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.67.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.67.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.68.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.68.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.68.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.69.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.69.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.69.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.7.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.7.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.7.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.70.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.70.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.70.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.71.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.71.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.71.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.72.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.72.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.72.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.73.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.73.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.73.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.74.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.74.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.74.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.75.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.75.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.75.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.76.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.76.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.76.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.77.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.77.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.77.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.78.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.78.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.78.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.79.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.79.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.79.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.8.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.8.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.8.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.80.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.80.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.80.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.81.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.81.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.81.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.82.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.82.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.82.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.83.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.83.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.83.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.84.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.84.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.84.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.85.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.85.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.85.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.86.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.86.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.86.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.87.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.87.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.87.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.88.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.88.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.88.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.89.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.89.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.89.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.9.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.9.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.9.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.90.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.90.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.90.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.91.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.91.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.91.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.92.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.92.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.92.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.93.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.93.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.93.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.94.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.94.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.94.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.95.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.95.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.95.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.96.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.96.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.96.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.97.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.97.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.97.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.98.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.98.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.98.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.99.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.99.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.experts.99.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.gate.e_score_correction_bias": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.gate.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.down_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.gate_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.mlp.shared_experts.up_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.post_attention_layernorm.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.k_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.o_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.q_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.6.self_attn.v_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.7.input_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.0.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.0.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.0.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.1.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.1.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.1.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.10.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.10.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.10.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.100.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.100.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.100.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.101.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.101.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.101.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.102.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.102.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.102.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.103.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.103.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.103.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.104.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.104.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.104.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.105.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.105.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.105.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.106.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.106.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.106.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.107.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.107.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.107.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.108.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.108.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.108.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.109.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.109.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.109.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.11.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.11.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.11.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.110.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.110.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.110.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.111.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.111.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.111.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.112.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.112.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.112.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.113.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.113.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.113.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.114.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.114.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.114.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.115.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.115.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.115.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.116.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.116.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.116.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.117.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.117.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.117.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.118.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.118.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.118.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.119.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.119.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.119.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.12.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.12.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.12.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.120.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.120.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.120.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.121.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.121.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.121.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.122.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.122.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.122.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.123.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.123.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.123.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.124.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.124.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.124.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.125.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.125.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.125.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.126.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.126.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.126.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.127.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.127.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.127.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.13.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.13.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.13.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.14.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.14.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.14.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.15.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.15.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.15.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.16.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.16.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.16.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.17.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.17.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.17.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.18.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.18.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.18.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.19.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.19.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.19.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.2.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.2.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.2.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.20.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.20.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.20.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.21.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.21.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.21.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.22.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.22.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.22.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.23.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.23.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.23.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.24.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.24.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.24.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.25.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.25.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.25.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.26.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.26.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.26.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.27.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.27.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.27.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.28.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.28.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.28.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.29.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.29.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.29.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.3.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.3.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.3.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.30.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.30.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.30.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.31.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.31.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.31.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.32.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.32.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.32.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.33.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.33.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.33.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.34.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.34.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.34.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.35.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.35.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.35.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.36.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.36.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.36.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.37.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.37.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.37.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.38.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.38.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.38.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.39.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.39.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.39.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.4.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.4.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.4.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.40.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.40.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.40.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.41.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.41.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.41.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.42.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.42.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.42.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.43.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.43.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.43.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.44.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.44.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.44.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.45.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.45.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.45.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.46.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.46.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.46.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.47.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.47.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.47.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.48.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.48.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.48.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.49.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.49.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.49.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.5.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.5.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.5.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.50.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.50.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.50.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.51.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.51.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.51.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.52.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.52.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.52.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.53.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.53.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.53.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.54.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.54.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.54.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.55.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.55.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.55.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.56.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.56.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.56.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.57.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.57.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.57.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.58.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.58.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.58.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.59.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.59.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.59.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.6.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.6.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.6.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.60.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.60.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.60.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.61.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.61.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.61.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.62.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.62.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.62.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.63.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.63.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.63.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.64.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.64.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.64.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.65.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.65.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.65.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.66.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.66.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.66.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.67.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.67.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.67.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.68.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.68.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.68.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.69.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.69.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.69.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.7.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.7.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.7.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.70.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.70.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.70.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.71.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.71.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.71.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.72.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.72.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.72.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.73.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.73.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.73.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.74.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.74.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.74.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.75.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.75.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.75.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.76.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.76.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.76.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.77.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.77.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.77.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.78.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.78.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.78.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.79.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.79.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.79.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.8.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.8.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.8.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.80.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.80.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.80.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.81.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.81.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.81.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.82.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.82.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.82.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.83.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.83.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.83.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.84.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.84.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.84.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.85.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.85.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.85.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.86.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.86.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.86.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.87.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.87.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.87.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.88.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.88.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.88.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.89.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.89.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.89.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.9.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.9.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.9.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.90.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.90.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.90.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.91.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.91.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.91.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.92.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.92.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.92.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.93.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.93.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.93.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.94.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.94.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.94.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.95.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.95.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.95.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.96.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.96.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.96.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.97.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.97.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.97.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.98.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.98.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.98.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.99.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.99.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.experts.99.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.gate.e_score_correction_bias": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.gate.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.mlp.shared_experts.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.post_attention_layernorm.weight": "model-00007-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.k_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.o_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.q_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.bias": "model-00006-of-00043.safetensors", + "model.layers.7.self_attn.v_proj.weight": "model-00006-of-00043.safetensors", + "model.layers.8.input_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.0.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.0.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.0.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.1.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.1.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.1.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.10.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.10.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.10.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.100.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.100.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.100.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.101.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.101.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.101.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.102.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.102.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.102.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.103.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.103.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.103.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.104.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.104.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.104.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.105.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.105.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.105.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.106.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.106.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.106.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.107.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.107.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.107.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.108.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.108.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.108.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.109.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.109.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.109.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.11.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.11.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.11.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.110.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.110.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.110.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.111.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.111.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.111.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.112.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.112.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.112.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.113.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.113.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.113.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.114.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.114.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.114.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.115.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.115.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.115.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.116.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.116.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.116.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.117.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.117.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.117.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.118.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.118.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.118.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.119.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.119.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.119.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.12.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.12.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.12.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.120.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.120.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.120.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.121.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.121.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.121.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.122.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.122.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.122.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.123.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.123.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.123.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.124.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.124.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.124.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.125.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.125.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.125.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.126.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.126.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.126.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.127.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.127.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.127.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.13.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.13.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.13.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.14.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.14.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.14.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.15.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.15.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.15.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.16.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.16.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.16.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.17.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.17.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.17.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.18.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.18.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.18.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.19.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.19.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.19.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.2.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.2.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.2.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.20.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.20.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.20.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.21.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.21.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.21.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.22.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.22.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.22.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.23.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.23.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.23.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.24.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.24.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.24.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.25.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.25.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.25.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.26.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.26.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.26.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.27.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.27.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.27.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.28.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.28.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.28.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.29.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.29.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.29.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.3.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.3.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.3.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.30.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.30.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.30.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.31.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.31.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.31.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.32.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.32.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.32.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.33.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.33.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.33.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.34.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.34.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.34.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.35.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.35.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.35.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.36.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.36.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.36.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.37.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.37.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.37.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.38.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.38.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.38.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.39.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.39.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.39.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.4.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.4.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.4.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.40.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.40.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.40.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.41.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.41.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.41.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.42.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.42.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.42.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.43.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.43.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.43.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.44.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.44.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.44.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.45.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.45.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.45.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.46.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.46.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.46.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.47.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.47.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.47.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.48.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.48.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.48.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.49.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.49.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.49.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.5.down_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.5.gate_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.5.up_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.mlp.experts.50.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.50.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.50.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.51.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.51.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.51.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.52.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.52.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.52.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.53.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.53.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.53.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.54.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.54.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.54.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.55.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.55.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.55.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.56.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.56.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.56.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.57.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.57.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.57.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.58.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.58.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.58.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.59.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.59.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.59.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.6.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.6.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.6.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.60.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.60.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.60.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.61.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.61.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.61.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.62.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.62.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.62.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.63.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.63.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.63.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.64.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.64.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.64.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.65.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.65.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.65.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.66.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.66.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.66.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.67.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.67.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.67.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.68.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.68.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.68.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.69.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.69.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.69.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.7.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.7.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.7.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.70.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.70.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.70.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.71.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.71.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.71.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.72.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.72.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.72.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.73.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.73.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.73.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.74.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.74.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.74.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.75.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.75.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.75.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.76.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.76.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.76.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.77.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.77.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.77.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.78.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.78.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.78.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.79.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.79.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.79.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.8.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.8.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.8.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.80.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.80.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.80.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.81.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.81.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.81.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.82.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.82.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.82.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.83.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.83.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.83.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.84.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.84.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.84.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.85.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.85.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.85.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.86.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.86.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.86.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.87.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.87.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.87.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.88.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.88.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.88.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.89.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.89.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.89.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.9.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.9.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.9.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.90.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.90.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.90.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.91.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.91.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.91.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.92.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.92.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.92.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.93.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.93.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.93.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.94.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.94.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.94.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.95.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.95.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.95.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.96.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.96.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.96.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.97.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.97.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.97.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.98.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.98.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.98.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.99.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.99.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.experts.99.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.gate.e_score_correction_bias": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.gate.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.mlp.shared_experts.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.8.post_attention_layernorm.weight": "model-00008-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.k_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.o_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.q_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.bias": "model-00007-of-00043.safetensors", + "model.layers.8.self_attn.v_proj.weight": "model-00007-of-00043.safetensors", + "model.layers.9.input_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.0.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.0.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.0.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.1.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.1.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.1.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.10.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.10.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.10.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.100.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.100.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.100.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.101.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.101.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.101.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.102.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.102.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.102.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.103.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.103.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.103.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.104.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.104.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.104.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.105.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.105.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.105.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.106.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.106.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.106.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.107.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.107.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.107.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.108.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.108.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.108.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.109.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.109.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.109.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.11.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.11.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.11.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.110.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.110.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.110.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.111.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.111.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.111.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.112.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.112.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.112.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.113.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.113.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.113.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.114.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.114.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.114.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.115.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.115.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.115.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.116.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.116.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.116.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.117.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.117.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.117.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.118.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.118.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.118.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.119.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.119.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.119.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.12.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.12.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.12.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.120.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.120.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.120.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.121.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.121.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.121.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.122.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.122.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.122.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.123.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.123.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.123.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.124.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.124.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.124.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.125.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.125.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.125.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.126.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.126.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.126.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.127.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.127.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.127.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.13.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.13.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.13.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.14.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.14.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.14.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.15.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.15.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.15.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.16.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.16.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.16.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.17.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.17.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.17.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.18.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.18.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.18.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.19.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.19.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.19.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.2.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.2.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.2.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.20.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.20.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.20.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.21.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.21.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.21.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.22.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.22.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.22.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.23.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.23.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.23.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.24.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.24.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.24.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.25.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.25.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.25.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.26.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.26.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.26.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.27.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.27.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.27.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.28.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.28.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.28.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.29.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.29.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.29.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.3.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.3.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.3.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.30.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.30.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.30.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.31.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.31.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.31.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.32.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.32.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.32.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.33.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.33.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.33.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.34.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.34.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.34.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.35.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.35.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.35.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.36.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.36.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.36.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.37.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.37.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.37.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.38.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.38.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.38.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.39.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.39.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.39.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.4.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.4.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.4.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.40.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.40.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.40.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.41.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.41.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.41.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.42.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.42.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.42.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.43.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.43.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.43.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.44.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.44.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.44.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.45.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.45.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.45.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.46.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.46.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.46.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.47.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.47.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.47.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.48.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.48.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.48.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.49.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.49.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.49.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.5.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.5.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.5.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.50.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.50.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.50.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.51.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.51.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.51.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.52.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.52.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.52.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.53.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.53.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.53.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.54.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.54.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.54.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.55.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.55.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.55.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.56.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.56.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.56.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.57.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.57.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.57.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.58.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.58.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.58.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.59.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.59.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.59.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.6.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.6.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.6.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.60.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.60.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.60.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.61.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.61.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.61.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.62.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.62.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.62.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.63.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.63.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.63.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.64.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.64.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.64.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.65.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.65.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.65.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.66.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.66.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.66.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.67.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.67.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.67.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.68.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.68.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.68.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.69.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.69.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.69.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.7.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.7.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.7.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.70.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.70.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.70.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.71.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.71.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.71.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.72.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.72.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.72.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.73.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.73.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.73.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.74.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.74.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.74.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.75.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.75.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.75.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.76.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.76.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.76.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.77.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.77.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.77.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.78.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.78.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.78.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.79.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.79.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.79.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.8.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.8.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.8.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.80.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.80.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.80.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.81.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.81.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.81.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.82.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.82.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.82.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.83.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.83.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.83.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.84.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.84.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.84.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.85.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.85.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.85.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.86.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.86.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.86.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.87.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.87.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.87.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.88.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.88.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.88.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.89.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.89.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.89.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.9.down_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.9.gate_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.9.up_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.mlp.experts.90.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.90.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.90.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.91.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.91.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.91.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.92.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.92.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.92.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.93.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.93.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.93.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.94.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.94.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.94.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.95.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.95.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.95.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.96.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.96.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.96.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.97.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.97.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.97.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.98.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.98.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.98.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.99.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.99.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.experts.99.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.gate.e_score_correction_bias": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.gate.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.down_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.gate_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.mlp.shared_experts.up_proj.weight": "model-00009-of-00043.safetensors", + "model.layers.9.post_attention_layernorm.weight": "model-00009-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.k_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.o_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.q_proj.weight": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.bias": "model-00008-of-00043.safetensors", + "model.layers.9.self_attn.v_proj.weight": "model-00008-of-00043.safetensors", + "model.norm.weight": "model-00043-of-00043.safetensors" + } +} diff --git a/special_tokens_map.json b/special_tokens_map.json new file mode 100644 index 0000000000000000000000000000000000000000..9028cf84013844f17d7616bdec1d88e977924434 --- /dev/null +++ b/special_tokens_map.json @@ -0,0 +1,40 @@ +{ + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "eos_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + }, + "pad_token": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false + } +} diff --git a/tokenizer.json b/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..e3ed3c66baf1ec4de61840b0abf02142687bfed8 --- /dev/null +++ b/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bda8e2146c3bb7b7e0fc96dcc4f0aeff041c6c27952e3ace0665663ebff346ba +size 19970700 diff --git a/tokenizer_config.json b/tokenizer_config.json new file mode 100644 index 0000000000000000000000000000000000000000..75e11cfb2e0cc09f19391ec2278b4825a4c3fae9 --- /dev/null +++ b/tokenizer_config.json @@ -0,0 +1,325 @@ +{ + "added_tokens_decoder": { + "151329": { + "content": "<|endoftext|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151330": { + "content": "[MASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151331": { + "content": "[gMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151332": { + "content": "[sMASK]", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151333": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151334": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151335": { + "content": "<|system|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151336": { + "content": "<|user|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151337": { + "content": "<|assistant|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151338": { + "content": "<|observation|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151339": { + "content": "<|begin_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151340": { + "content": "<|end_of_image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151341": { + "content": "<|begin_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151342": { + "content": "<|end_of_video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151343": { + "content": "<|begin_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151344": { + "content": "<|end_of_audio|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151345": { + "content": "<|begin_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151346": { + "content": "<|end_of_transcription|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151347": { + "content": "<|code_prefix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151348": { + "content": "<|code_middle|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151349": { + "content": "<|code_suffix|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151350": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151351": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151352": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151353": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151354": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151355": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151356": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151357": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151358": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151359": { + "content": "", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151360": { + "content": "/nothink", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": true + }, + "151361": { + "content": "<|begin_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151362": { + "content": "<|end_of_box|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151363": { + "content": "<|image|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + }, + "151364": { + "content": "<|video|>", + "lstrip": false, + "normalized": false, + "rstrip": false, + "single_word": false, + "special": false + } + }, + "additional_special_tokens": [ + "<|endoftext|>", + "[MASK]", + "[gMASK]", + "[sMASK]", + "", + "", + "<|system|>", + "<|user|>", + "<|assistant|>", + "<|observation|>", + "<|begin_of_image|>", + "<|end_of_image|>", + "<|begin_of_video|>", + "<|end_of_video|>", + "<|begin_of_audio|>", + "<|end_of_audio|>", + "<|begin_of_transcription|>", + "<|end_of_transcription|>", + "<|code_prefix|>", + "<|code_middle|>", + "<|code_suffix|>", + "/nothink" + ], + "clean_up_tokenization_spaces": false, + "do_lower_case": false, + "eos_token": "<|endoftext|>", + "extra_special_tokens": {}, + "model_max_length": 128000, + "pad_token": "<|endoftext|>", + "padding_side": "left", + "remove_space": false, + "tokenizer_class": "PreTrainedTokenizerFast" +}