Training in progress, step 63

README.md

@@ -1,7 +1,7 @@
 ---
-base_model: mistralai/Ministral-8B-Instruct-2410
+base_model: mistralai/Mistral-Small-Instruct-2409
 library_name: transformers
-model_name: self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1
+model_name: self-correct_mistral-small-it_mMQA_dpo_iter1
 tags:
 - generated_from_trainer
 - trl
@@ -9,9 +9,9 @@ tags:
 licence: license
 ---
 
-# Model Card for self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1
+# Model Card for self-correct_mistral-small-it_mMQA_dpo_iter1
 
-This model is a fine-tuned version of [mistralai/Ministral-8B-Instruct-2410](https://huggingface.co/mistralai/Ministral-8B-Instruct-2410).
+This model is a fine-tuned version of [mistralai/Mistral-Small-Instruct-2409](https://huggingface.co/mistralai/Mistral-Small-Instruct-2409).
 It has been trained using [TRL](https://github.com/huggingface/trl).
 
 ## Quick start
@@ -20,14 +20,14 @@ It has been trained using [TRL](https://github.com/huggingface/trl).
 from transformers import pipeline
 
 question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
-generator = pipeline("text-generation", model="RyanYr/self-correct_Ministral-8B-Instruct-2410_metaMathQA_dpo_iter1", device="cuda")
+generator = pipeline("text-generation", model="RyanYr/self-correct_mistral-small-it_mMQA_dpo_iter1", device="cuda")
 output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
 print(output["generated_text"])
 ```
 
 ## Training procedure
 
-[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yyr/huggingface/runs/rdf560eo)
+[<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/yyr/huggingface/runs/y5iah9gz)
 
 This model was trained with DPO, a method introduced in [Direct Preference Optimization: Your Language Model is Secretly a Reward Model](https://huggingface.co/papers/2305.18290).
 
@@ -36,7 +36,7 @@ This model was trained with DPO, a method introduced in [Direct Preference Optim
 - TRL: 0.12.0.dev0
 - Transformers: 4.45.2
 - Pytorch: 2.4.0
-- Datasets: 3.0.2
+- Datasets: 3.1.0
 - Tokenizers: 0.20.1
 
 ## Citations

added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32768
+}

last_checkpoint/added_tokens.json

@@ -0,0 +1,3 @@
+{
+  "[PAD]": 32768
+}

last_checkpoint/config.json

@@ -1,5 +1,5 @@
 {
-  "_name_or_path": "mistralai/Ministral-8B-Instruct-2410",
+  "_name_or_path": "mistralai/Mistral-Small-Instruct-2409",
   "architectures": [
     "MistralForCausalLM"
   ],
@@ -8,21 +8,21 @@
   "eos_token_id": 2,
   "head_dim": 128,
   "hidden_act": "silu",
-  "hidden_size": 4096,
+  "hidden_size": 6144,
   "initializer_range": 0.02,
-  "intermediate_size": 12288,
+  "intermediate_size": 16384,
   "max_position_embeddings": 32768,
   "model_type": "mistral",
-  "num_attention_heads": 32,
-  "num_hidden_layers": 36,
+  "num_attention_heads": 48,
+  "num_hidden_layers": 56,
   "num_key_value_heads": 8,
-  "pad_token_id": 131072,
+  "pad_token_id": 32768,
   "rms_norm_eps": 1e-05,
-  "rope_theta": 100000000.0,
-  "sliding_window": 32768,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
   "tie_word_embeddings": false,
   "torch_dtype": "bfloat16",
   "transformers_version": "4.45.2",
   "use_cache": false,
-  "vocab_size": 131073
+  "vocab_size": 32769
 }

last_checkpoint/model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeed4aa6b7c17fcffac0032e984eb89780fafaf36ec0c2e1dada35fcddb3e8b3
+size 4882311064

last_checkpoint/model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff18a680bbf93e0138772fe4b8f788e6c222638240878a32efb24ea1821df9e
+size 4983012160

last_checkpoint/model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c2f03042fd3ae5f5fe1f921890151b7e18da6620f2a0e18bc497c9d0b46685
+size 4957821336

last_checkpoint/model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c5091cd089808cd9f01df1f3d9646104191c1442fded7fd62579ecdd578100
+size 4882323744

last_checkpoint/model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fe3e3dfa53e31a422dac36b8b90434b506421979a1e4deb6f101646f50b082
+size 4983012192

last_checkpoint/model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba801e1ba41c5cb2f6a84853f6c4c815ac432c7254bfa3759fa0fad06023c9f
+size 4957821336

last_checkpoint/model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29235cde971d316703d9b7e990841680f877ab1aee6ac21f6606635e959ec56e
+size 4882323744

last_checkpoint/model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5177d619b2d5e51c5bd7d5aafb8f75133dc00e0a8258b453755437b4065d5e
+size 4983012192

last_checkpoint/model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb42b681a18a7add5077ba0332928909f0d6933d1412b16c66702509dde7aefc
+size 4983011344

last_checkpoint/model.safetensors.index.json

@@ -1,334 +1,514 @@
 {
   "metadata": {
-    "total_size": 16039632896
+    "total_size": 44494589952
   },
   "weight_map": {
-    "lm_head.weight": "model-00004-of-00004.safetensors",
-    "model.embed_tokens.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.1.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.10.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.10.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.11.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.11.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.12.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.13.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.14.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.15.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.16.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.17.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.18.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.19.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.2.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.2.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.20.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.20.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.21.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.input_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.22.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.23.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
-    "model.layers.23.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.24.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.25.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.26.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.27.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.28.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.29.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.3.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.3.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.30.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.30.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.31.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.32.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.33.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.34.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.input_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.35.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
-    "model.layers.4.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.4.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.5.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.6.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.7.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.8.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.input_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.down_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.gate_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.mlp.up_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.post_attention_layernorm.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.k_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.o_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.q_proj.weight": "model-00001-of-00004.safetensors",
-    "model.layers.9.self_attn.v_proj.weight": "model-00001-of-00004.safetensors",
-    "model.norm.weight": "model-00003-of-00004.safetensors"
+    "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-00003-of-00009.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00003-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-00003-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-00003-of-00009.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00003-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-00003-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-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00003-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-00004-of-00009.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00003-of-00009.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00004-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-00004-of-00009.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00004-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-00004-of-00009.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00004-of-00009.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00005-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-00005-of-00009.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00005-of-00009.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00006-of-00009.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00007-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-00007-of-00009.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00007-of-00009.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00002-of-00009.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00002-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-00002-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-00009-of-00009.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00008-of-00009.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00009-of-00009.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00009-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-00002-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-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00002-of-00009.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00002-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"
   }
 }

last_checkpoint/tokenizer.json

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:3537f74c84bc8e8cbb95a43947b1bdc89bb143d548bdd2a28ac2c3bbf51971ed
-size 17078318
+oid sha256:6a8f15a4c9e4a52886efc25270d80f981837ce29d29be476ff3c5a3caaf08379
+size 3672277

last_checkpoint/tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583

last_checkpoint/training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400bc9706fce17e116a6857ea7253a25d92833e63a6e908f57e64807a6a5b480
+oid sha256:26b7969b3af7288627f8b855398c93e98127d8f74fc9deec993b0ec8c6ec6cdc
 size 7992

model-00001-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:9e0bd47e413bc07d7e6534d1efe976f01bfc79f4b70e9e12f0b0781d3ccafa67
+oid sha256:3ef6a16d265e249a30116fc1f07680f849a3669d73c32db66c83f0190f7f7ff6
 size 4983016096

model-00001-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aeed4aa6b7c17fcffac0032e984eb89780fafaf36ec0c2e1dada35fcddb3e8b3
+size 4882311064

model-00002-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:959e6185c82df08eac73f477bb4bb39dc5d3cd5cf5be1540d61bb2a288adcff4
+oid sha256:bd9296fb9baf593c692983896af611f706a0ed5ce03302aa950aee853d2abb66
 size 4999836776

model-00002-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:1ff18a680bbf93e0138772fe4b8f788e6c222638240878a32efb24ea1821df9e
+size 4983012160

model-00003-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:8958afc48f5f1038addd9e2ce92b99979b2b950aefb7c3d628b86ad2ffeb9d12
+oid sha256:caa0401a470f76453bbbb16a275e0ee9ef748f2f0eb894ba99f47020814e11ef
 size 4983067960

model-00003-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f6c2f03042fd3ae5f5fe1f921890151b7e18da6620f2a0e18bc497c9d0b46685
+size 4957821336

model-00004-of-00004.safetensors

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:2d0034cec246aabc67c7ddaff7970eb8807c681e772aed8c0624c485461b02f1
+oid sha256:e612497253510f6c82dab186c51cc1d043ab1bd909f5f4916741e3a86107bb7e
 size 1073750144

model-00004-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c6c5091cd089808cd9f01df1f3d9646104191c1442fded7fd62579ecdd578100
+size 4882323744

model-00005-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b0fe3e3dfa53e31a422dac36b8b90434b506421979a1e4deb6f101646f50b082
+size 4983012192

model-00006-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aba801e1ba41c5cb2f6a84853f6c4c815ac432c7254bfa3759fa0fad06023c9f
+size 4957821336

model-00007-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:29235cde971d316703d9b7e990841680f877ab1aee6ac21f6606635e959ec56e
+size 4882323744

model-00008-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:4f5177d619b2d5e51c5bd7d5aafb8f75133dc00e0a8258b453755437b4065d5e
+size 4983012192

model-00009-of-00009.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:eb42b681a18a7add5077ba0332928909f0d6933d1412b16c66702509dde7aefc
+size 4983011344

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:59f95e28944c062244741268596badc900df86c7f5ded05088d2da22a7379e06
+size 587583

tokenizer_config.json

@@ -8017,7 +8017,7 @@
   "clean_up_tokenization_spaces": false,
   "eos_token": "</s>",
   "legacy": true,
-  "model_max_length": 4096,
+  "model_max_length": 16384,
   "pad_token": "[PAD]",
   "tokenizer_class": "LlamaTokenizer",
   "unk_token": "<unk>",

training_args.bin

@@ -1,3 +1,3 @@
 version https://git-lfs.github.com/spec/v1
-oid sha256:400bc9706fce17e116a6857ea7253a25d92833e63a6e908f57e64807a6a5b480
-size 7992
+oid sha256:ac214955cb91288d68a21fd2f2e295c7ec10c2fc54ca96163eb7cd98829a8eb4
+size 8056