Upload folder using huggingface_hub

README.md

@@ -0,0 +1,169 @@
+---
+base_model: BeaverAI/Theia-21B-v2a
+tags:
+- axolotl
+- generated_from_trainer
+model-index:
+- name: Theia-21B-v2b-WS
+  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/axolotl-ai-cloud/axolotl/main/image/axolotl-badge-web.png" alt="Built with Axolotl" width="200" height="32"/>](https://github.com/axolotl-ai-cloud/axolotl)
+<details><summary>See axolotl config</summary>
+
+axolotl version: `0.4.1`
+```yaml
+base_model: BeaverAI/Theia-21B-v2a
+model_type: AutoModelForCausalLM
+tokenizer_type: AutoTokenizer
+
+load_in_8bit: false
+load_in_4bit: false
+strict: false
+sequence_len: 16384
+bf16: auto
+fp16:
+tf32: false
+flash_attention: true
+special_tokens:
+    pad_token: "<pad>"
+tokens:
+    - "<|im_start|>"
+    - "<|im_end|>"
+
+# PLAN
+# instruct = mistral
+# siayn = alpaca
+# RP = chatml
+
+# Data
+datasets:
+  - path: BeaverAI/saosauce-v2-creative-only
+    type: sharegpt
+    conversation: chatml
+warmup_steps: 150
+
+save_safetensors: true
+
+mlflow_tracking_uri: http://127.0.0.1:7860
+mlflow_experiment_name: Default
+# WandB
+#wandb_project: theia
+#wandb_entity:
+
+# Iterations
+num_epochs: 2
+
+# Output
+output_dir: ./Theia-21B-v2b-Workspace
+hub_model_id: BeaverAI/Theia-21B-v2b-WS
+hub_strategy: "all_checkpoints"
+
+# Sampling
+sample_packing: true
+pad_to_sequence_len: true
+
+# Batching
+gradient_accumulation_steps: 1
+micro_batch_size: 1
+gradient_checkpointing: true
+gradient_checkpointing_kwargs:
+   use_reentrant: true
+
+# Evaluation
+val_set_size: 0.025
+evals_per_epoch: 4
+eval_table_size:
+eval_max_new_tokens: 256
+eval_sample_packing: false
+eval_batch_size: 1
+
+# Optimizer
+optimizer: paged_adamw_8bit # adamw_8bit
+lr_scheduler: cosine
+learning_rate: 0.0000025
+lr_scheduler: cosine_with_min_lr
+lr_scheduler_kwargs:
+    min_lr: 0.00000025
+weight_decay: 0.01
+max_grad_norm: 10.0
+
+# Misc
+train_on_inputs: false
+group_by_length: false
+early_stopping_patience:
+local_rank:
+logging_steps: 1
+xformers_attention:
+debug:
+deepspeed: deepspeed_configs/zero3_bf16.json # previously blank
+fsdp:
+fsdp_config:
+
+# Checkpoints
+resume_from_checkpoint:
+saves_per_epoch: 1
+
+```
+
+</details><br>
+
+# Theia-21B-v2b-WS
+
+This model is a fine-tuned version of [BeaverAI/Theia-21B-v2a](https://huggingface.co/BeaverAI/Theia-21B-v2a) on the None dataset.
+It achieves the following results on the evaluation set:
+- Loss: 1.0491
+
+## 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: 2.5e-06
+- train_batch_size: 1
+- eval_batch_size: 1
+- seed: 42
+- distributed_type: multi-GPU
+- num_devices: 8
+- total_train_batch_size: 8
+- total_eval_batch_size: 8
+- optimizer: Adam with betas=(0.9,0.999) and epsilon=1e-08
+- lr_scheduler_type: cosine_with_min_lr
+- lr_scheduler_warmup_steps: 150
+- num_epochs: 2
+
+### Training results
+
+| Training Loss | Epoch  | Step | Validation Loss |
+|:-------------:|:------:|:----:|:---------------:|
+| 1.5956        | 0.0030 | 1    | 1.5014          |
+| 1.2309        | 0.2508 | 83   | 1.2064          |
+| 1.1063        | 0.5015 | 166  | 1.1376          |
+| 1.1885        | 0.7523 | 249  | 1.1021          |
+| 1.1518        | 1.0030 | 332  | 1.0772          |
+| 0.9328        | 1.2356 | 415  | 1.0693          |
+| 0.9149        | 1.4864 | 498  | 1.0569          |
+| 0.9377        | 1.7372 | 581  | 1.0491          |
+
+
+### Framework versions
+
+- Transformers 4.44.0.dev0
+- Pytorch 2.2.2
+- Datasets 2.19.1
+- Tokenizers 0.19.1

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "BeaverAI/Theia-21B-v2a",
+  "architectures": [
+    "MistralForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "head_dim": 128,
+  "hidden_act": "silu",
+  "hidden_size": 5120,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 1024000,
+  "model_type": "mistral",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 70,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-05,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.44.0.dev0",
+  "use_cache": false,
+  "vocab_size": 131074
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "transformers_version": "4.44.0.dev0"
+}

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7076b4a42c3b889f8a760e7430f4d9e86655724fd6d437bbad6e2d97b40dd4e
+size 4865542976

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:7993aa00009141d75e33ea9b5464995e4d23d864027afcfbca94b609824f1226
+size 4907529424

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:54e2997b2106342b562e59cdf95a877640c4da94cfea16c508a0be099183c3b4
+size 4907529456

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a7a161e28be861bc47952d7c297b15268242a8030e7db39314eb699f2ae738e0
+size 4907529456

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a2a36e48c23549f944d76df2e41ced6b3707828b742c67a03405f2c6c1094daf
+size 4907529456

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e2620927216d866ce33705c03c461bf90de8ac4a29f8ba96b47f670de77c4951
+size 4907529456

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:96102d51a38a27e1cc4ae31f3f5924e6eb44f3c4cec6fec50be4ae356e2b0c77
+size 4907529456

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f48a8419f2f8b8ca32a8f3ee92cbf4a163f27f85a6170d2989cab327b7cfb71b
+size 4907529456

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:efaa650c8ef5681e7e65de2371fe301d414c1927eda6d0a51aa82faf5e35383c
+size 1635830440

model.safetensors.index.json

@@ -0,0 +1,640 @@
+{
+  "metadata": {
+    "total_size": 40854005760
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00009-of-00009.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00009.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00009.safetensors",
+    "model.norm.weight": "model-00009-of-00009.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": "<pad>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0e286e9c8a8a509ee42037a8972e7d9e7efa88d8054ad452ca8457415340c4e8
+size 8120