Upload folder using huggingface_hub

README.md

@@ -0,0 +1,136 @@
+---
+license: apache-2.0
+base_model: four-two-labs/tinyllama-moe-nord-completion-6B
+tags:
+- generated_from_trainer
+model-index:
+- name: runs/model/tinyllama-moe-orpo
+  results: []
+---
+
+<!-- This model card has been generated automatically according to the information the Trainer had access to. You
+should probably proofread and complete it, then remove this comment. -->
+
+[<img src="https://raw.githubusercontent.com/OpenAccess-AI-Collective/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/OpenAccess-AI-Collective/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.0`
+```yaml
+base_model: four-two-labs/tinyllama-moe-nord-completion-6B
+
+model_type: AutoModelForCausalLM
+tokenizer_type: LlamaTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+
+rl: orpo
+orpo_alpha: 0.1
+remove_unused_columns: false
+
+chat_template: chatml
+datasets:
+  - path: four-two-labs/nord-dpo-mix-181k-axolotl
+    type: chat_template.argilla
+    split: train
+
+output_dir: ./runs/model/tinyllama-moe-orpo
+dataset_prepared_path: ./runs/data/tinyllama-dpo-data
+
+val_set_size: 0.01
+
+sequence_len: 2048
+sample_packing: false
+pad_to_sequence_len: false
+
+wandb_project: axolotl
+wandb_entity:
+wandb_watch:
+wandb_name:
+wandb_log_model:
+
+gradient_accumulation_steps: 1
+micro_batch_size: 2
+num_epochs: 3
+optimizer: paged_adamw_8bit
+lr_scheduler: cosine
+learning_rate: 3e-5
+
+train_on_inputs: false
+group_by_length: false
+bf16: true
+fp16:
+tf32: true
+
+gradient_checkpointing: true
+early_stopping_patience:
+resume_from_checkpoint:
+local_rank:
+logging_steps: 1
+xformers_attention:
+flash_attention: true
+
+loss_watchdog_threshold: 5.0
+loss_watchdog_patience: 3
+
+warmup_steps: 10
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 128
+saves_per_epoch: 1
+debug:
+deepspeed:
+weight_decay: 0.0
+fsdp:
+fsdp_config:
+special_tokens:
+
+```
+
+</details><br>
+
+# runs/model/tinyllama-moe-orpo
+
+This model is a fine-tuned version of [four-two-labs/tinyllama-moe-nord-completion-6B](https://huggingface.co/four-two-labs/tinyllama-moe-nord-completion-6B) on the None dataset.
+
+## Model description
+
+More information needed
+
+## Intended uses & limitations
+
+More information needed
+
+## Training and evaluation data
+
+More information needed
+
+## Training procedure
+
+### Training hyperparameters
+
+The following hyperparameters were used during training:
+- learning_rate: 3e-05
+- train_batch_size: 2
+- eval_batch_size: 8
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 10
+- total_train_batch_size: 20
+- total_eval_batch_size: 80
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine
+- lr_scheduler_warmup_steps: 10
+- training_steps: 27511
+
+### Training results
+
+
+
+### Framework versions
+
+- Transformers 4.40.0.dev0
+- Pytorch 2.1.2+cu118
+- Datasets 2.15.0
+- Tokenizers 0.15.0

config.json

@@ -0,0 +1,34 @@
+{
+  "_name_or_path": ".",
+  "architectures": [
+    "MixtralForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 2048,
+  "initializer_range": 0.02,
+  "intermediate_size": 5632,
+  "max_position_embeddings": 2048,
+  "model_type": "mixtral",
+  "num_attention_heads": 32,
+  "num_experts_per_tok": 2,
+  "num_hidden_layers": 22,
+  "num_key_value_heads": 4,
+  "num_local_experts": 4,
+  "output_router_logits": false,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "router_aux_loss_coef": 0.001,
+  "router_jitter_noise": 0.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.0.dev0",
+  "use_cache": false,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.40.0.dev0"
+}

model-00001-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96ec077fe64ebe93018ec12991b55084172bf7d011939e5e47a9b3b33e203503
+size 4996913648

model-00002-of-00002.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e9de32b8b74dde8382c5274427938d98bc93c3d6cfb64d0e690c6d6e927e9a74
+size 1771193272

model.safetensors.index.json

@@ -0,0 +1,428 @@
+{
+  "metadata": {
+    "total_size": 6768054272
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00002-of-00002.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.0.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.1.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.2.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w1.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w2.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.experts.3.w3.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.block_sparse_moe.gate.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.0.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.1.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.2.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w1.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w2.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.experts.3.w3.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.block_sparse_moe.gate.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
+    "model.norm.weight": "model-00002-of-00002.safetensors"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,30 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,45 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "add_prefix_space": true,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "bos_token": "<s>",
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": false,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "<s>",
+  "padding_side": "left",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": false,
+  "use_fast": true
+}