chore: add default Hugging Face project files

.gitattributes

@@ -33,3 +33,5 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
 *.zip filter=lfs diff=lfs merge=lfs -text
 *.zst filter=lfs diff=lfs merge=lfs -text
 *tfevents* filter=lfs diff=lfs merge=lfs -text
+tokenizer.json filter=lfs diff=lfs merge=lfs -text
+calme_3.png filter=lfs diff=lfs merge=lfs -text

README.md

@@ -1,5 +1,183 @@
----
-license: other
-license_name: qwen
-license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/resolve/main/LICENSE
----
+---
+language:
+- en
+license: other
+library_name: transformers
+tags:
+- chat
+- qwen
+- qwen2.5
+- finetune
+- english
+base_model: MaziyarPanahi/calme-3-selfmerge-qwen2-78b
+model_name: calme-3.2-instruct-78b
+license_name: qwen
+license_link: https://huggingface.co/Qwen/Qwen2.5-72B-Instruct/blob/main/LICENSE
+pipeline_tag: text-generation
+inference: false
+model_creator: MaziyarPanahi
+quantized_by: MaziyarPanahi
+model-index:
+- name: calme-3.2-instruct-78b
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: IFEval (0-Shot)
+      type: HuggingFaceH4/ifeval
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: inst_level_strict_acc and prompt_level_strict_acc
+      value: 80.63
+      name: strict accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-78b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: BBH (3-Shot)
+      type: BBH
+      args:
+        num_few_shot: 3
+    metrics:
+    - type: acc_norm
+      value: 62.61
+      name: normalized accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-78b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MATH Lvl 5 (4-Shot)
+      type: hendrycks/competition_math
+      args:
+        num_few_shot: 4
+    metrics:
+    - type: exact_match
+      value: 39.95
+      name: exact match
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-78b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GPQA (0-shot)
+      type: Idavidrein/gpqa
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 20.36
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-78b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MuSR (0-shot)
+      type: TAUR-Lab/MuSR
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: acc_norm
+      value: 38.53
+      name: acc_norm
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-78b
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU-PRO (5-shot)
+      type: TIGER-Lab/MMLU-Pro
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 70.03
+      name: accuracy
+    source:
+      url: https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard?query=MaziyarPanahi/calme-3.2-instruct-78b
+      name: Open LLM Leaderboard
+---
+
+<img src="./calme_3.png" alt="Calme-3 Models" width="800" style="margin-left:'auto' margin-right:'auto' display:'block'"/>
+
+> [!TIP]
+> This is an experimental model, so it might not perform well for some prompts and may be sensitive to hyper parameters. I would appreciate any feedback to see if I can fix any issues in the next iteration. ❤️
+
+# MaziyarPanahi/calme-3.2-instruct-78b
+
+This model is an advanced iteration of the powerful `Qwen/Qwen2.5-72B`, specifically fine-tuned to enhance its capabilities in generic domains. The `Qwen2.5-72B` base model was merged with itself to create a larger model. After that, the model was fine-tuned on a custom datasets.
+
+# ⚡ Quantized GGUF
+
+Here are the GGUF models thanks to [https://huggingface.co/bartowski](https://huggingface.co/bartowski): [calme-3.2-instruct-78b-GGUF](https://huggingface.co/bartowski/calme-3.2-instruct-78b-GGUF)
+
+# 🏆 [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/open-llm-leaderboard/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_MaziyarPanahi__calme-3.2-instruct-78b)
+
+|      Metric       |Value|
+|-------------------|----:|
+|Avg.               |52.02|
+|IFEval (0-Shot)    |80.63|
+|BBH (3-Shot)       |62.61|
+|MATH Lvl 5 (4-Shot)|39.95|
+|GPQA (0-shot)      |20.36|
+|MuSR (0-shot)      |38.53|
+|MMLU-PRO (5-shot)  |70.03|
+
+# Prompt Template
+
+This model uses `ChatML` prompt template:
+
+```sh
+<|im_start|>system
+{System}
+<|im_end|>
+<|im_start|>user
+{User}
+<|im_end|>
+<|im_start|>assistant
+{Assistant}
+````
+
+# How to use
+
+```python
+
+# Use a pipeline as a high-level helper
+
+from transformers import pipeline
+
+messages = [
+    {"role": "user", "content": "Who are you?"},
+]
+pipe = pipeline("text-generation", model="MaziyarPanahi/calme-3.2-instruct-78b")
+pipe(messages)
+
+
+# Load model directly
+
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("MaziyarPanahi/calme-3.2-instruct-78b")
+model = AutoModelForCausalLM.from_pretrained("MaziyarPanahi/calme-3.2-instruct-78b")
+```
+
+# Ethical Considerations
+
+As with any large language model, users should be aware of potential biases and limitations. We recommend implementing appropriate safeguards and human oversight when deploying this model in production environments.

added_tokens.json

@@ -0,0 +1,5 @@
+{
+  "<|endoftext|>": 151643,
+  "<|im_end|>": 151645,
+  "<|im_start|>": 151644
+}

config.json

@@ -0,0 +1,28 @@
+{
+  "_name_or_path": "MaziyarPanahi/calme-3-selfmerge-qwen2-78b",
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 86,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 1000000.0,
+  "sliding_window": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.46.1",
+  "use_cache": false,
+  "use_sliding_window": false,
+  "vocab_size": 151646
+}

model.safetensors.index.json

@@ -0,0 +1 @@
+{"metadata": {"mergekit_version": "0.0.4.4", "total_size": 311861854208}, "weight_map": {"lm_head.weight": "model-00001-of-00067.safetensors", "model.embed_tokens.weight": "model-00002-of-00067.safetensors", "model.layers.0.input_layernorm.weight": "model-00002-of-00067.safetensors", "model.layers.0.mlp.down_proj.weight": "model-00003-of-00067.safetensors", "model.layers.0.mlp.gate_proj.weight": "model-00003-of-00067.safetensors", "model.layers.0.mlp.up_proj.weight": "model-00003-of-00067.safetensors", "model.layers.0.post_attention_layernorm.weight": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.k_proj.bias": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.k_proj.weight": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.o_proj.weight": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.q_proj.bias": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.q_proj.weight": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.v_proj.bias": "model-00003-of-00067.safetensors", "model.layers.0.self_attn.v_proj.weight": "model-00003-of-00067.safetensors", "model.layers.1.input_layernorm.weight": "model-00003-of-00067.safetensors", "model.layers.1.mlp.down_proj.weight": "model-00003-of-00067.safetensors", "model.layers.1.mlp.gate_proj.weight": "model-00004-of-00067.safetensors", "model.layers.1.mlp.up_proj.weight": "model-00004-of-00067.safetensors", "model.layers.1.post_attention_layernorm.weight": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.k_proj.bias": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.k_proj.weight": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.o_proj.weight": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.q_proj.bias": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.q_proj.weight": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.v_proj.bias": "model-00004-of-00067.safetensors", "model.layers.1.self_attn.v_proj.weight": "model-00004-of-00067.safetensors", "model.layers.10.input_layernorm.weight": "model-00004-of-00067.safetensors", "model.layers.10.mlp.down_proj.weight": "model-00004-of-00067.safetensors", "model.layers.10.mlp.gate_proj.weight": "model-00004-of-00067.safetensors", "model.layers.10.mlp.up_proj.weight": "model-00005-of-00067.safetensors", "model.layers.10.post_attention_layernorm.weight": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.k_proj.bias": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.k_proj.weight": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.o_proj.weight": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.q_proj.bias": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.q_proj.weight": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.v_proj.bias": "model-00005-of-00067.safetensors", "model.layers.10.self_attn.v_proj.weight": "model-00005-of-00067.safetensors", "model.layers.11.input_layernorm.weight": "model-00005-of-00067.safetensors", "model.layers.11.mlp.down_proj.weight": "model-00005-of-00067.safetensors", "model.layers.11.mlp.gate_proj.weight": "model-00005-of-00067.safetensors", "model.layers.11.mlp.up_proj.weight": "model-00005-of-00067.safetensors", "model.layers.11.post_attention_layernorm.weight": "model-00005-of-00067.safetensors", "model.layers.11.self_attn.k_proj.bias": "model-00005-of-00067.safetensors", "model.layers.11.self_attn.k_proj.weight": "model-00005-of-00067.safetensors", "model.layers.11.self_attn.o_proj.weight": "model-00005-of-00067.safetensors", "model.layers.11.self_attn.q_proj.bias": "model-00005-of-00067.safetensors", "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00067.safetensors", "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00067.safetensors", "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.input_layernorm.weight": "model-00006-of-00067.safetensors", "model.layers.12.mlp.down_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.mlp.gate_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.mlp.up_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.post_attention_layernorm.weight": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.k_proj.bias": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.k_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.o_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.q_proj.bias": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.q_proj.weight": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.v_proj.bias": "model-00006-of-00067.safetensors", "model.layers.12.self_attn.v_proj.weight": "model-00006-of-00067.safetensors", "model.layers.13.input_layernorm.weight": "model-00006-of-00067.safetensors", "model.layers.13.mlp.down_proj.weight": "model-00006-of-00067.safetensors", "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00067.safetensors", "model.layers.13.mlp.up_proj.weight": "model-00007-of-00067.safetensors", "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00067.safetensors", "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00067.safetensors", "model.layers.14.input_layernorm.weight": "model-00007-of-00067.safetensors", "model.layers.14.mlp.down_proj.weight": "model-00007-of-00067.safetensors", "model.layers.14.mlp.gate_proj.weight": "model-00007-of-00067.safetensors", "model.layers.14.mlp.up_proj.weight": "model-00008-of-00067.safetensors", "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.k_proj.bias": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.k_proj.weight": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.o_proj.weight": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.q_proj.bias": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.q_proj.weight": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.v_proj.bias": "model-00008-of-00067.safetensors", "model.layers.14.self_attn.v_proj.weight": "model-00008-of-00067.safetensors", "model.layers.15.input_layernorm.weight": "model-00008-of-00067.safetensors", "model.layers.15.mlp.down_proj.weight": "model-00008-of-00067.safetensors", "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00067.safetensors", "model.layers.15.mlp.up_proj.weight": "model-00008-of-00067.safetensors", "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00067.safetensors", "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00067.safetensors", "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00067.safetensors", "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00067.safetensors", "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00067.safetensors", "model.layers.15.self_attn.q_proj.weight": "model-00009-of-00067.safetensors", "model.layers.15.self_attn.v_proj.bias": "model-00009-of-00067.safetensors", "model.layers.15.self_attn.v_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.input_layernorm.weight": "model-00009-of-00067.safetensors", "model.layers.16.mlp.down_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.mlp.gate_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.mlp.up_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.k_proj.bias": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.k_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.o_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.q_proj.bias": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.q_proj.weight": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.v_proj.bias": "model-00009-of-00067.safetensors", "model.layers.16.self_attn.v_proj.weight": "model-00009-of-00067.safetensors", "model.layers.17.input_layernorm.weight": "model-00009-of-00067.safetensors", "model.layers.17.mlp.down_proj.weight": "model-00009-of-00067.safetensors", "model.layers.17.mlp.gate_proj.weight": "model-00010-of-00067.safetensors", "model.layers.17.mlp.up_proj.weight": "model-00010-of-00067.safetensors", "model.layers.17.post_attention_layernorm.weight": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.k_proj.bias": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.k_proj.weight": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.o_proj.weight": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.q_proj.bias": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.q_proj.weight": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.v_proj.bias": "model-00010-of-00067.safetensors", "model.layers.17.self_attn.v_proj.weight": "model-00010-of-00067.safetensors", "model.layers.18.input_layernorm.weight": "model-00010-of-00067.safetensors", "model.layers.18.mlp.down_proj.weight": "model-00010-of-00067.safetensors", "model.layers.18.mlp.gate_proj.weight": "model-00010-of-00067.safetensors", "model.layers.18.mlp.up_proj.weight": "model-00011-of-00067.safetensors", "model.layers.18.post_attention_layernorm.weight": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.k_proj.bias": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.k_proj.weight": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.o_proj.weight": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.q_proj.bias": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.q_proj.weight": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.v_proj.bias": "model-00011-of-00067.safetensors", "model.layers.18.self_attn.v_proj.weight": "model-00011-of-00067.safetensors", "model.layers.19.input_layernorm.weight": "model-00011-of-00067.safetensors", "model.layers.19.mlp.down_proj.weight": "model-00011-of-00067.safetensors", "model.layers.19.mlp.gate_proj.weight": "model-00011-of-00067.safetensors", "model.layers.19.mlp.up_proj.weight": "model-00011-of-00067.safetensors", "model.layers.19.post_attention_layernorm.weight": "model-00011-of-00067.safetensors", "model.layers.19.self_attn.k_proj.bias": "model-00011-of-00067.safetensors", "model.layers.19.self_attn.k_proj.weight": "model-00011-of-00067.safetensors", "model.layers.19.self_attn.o_proj.weight": "model-00011-of-00067.safetensors", "model.layers.19.self_attn.q_proj.bias": "model-00011-of-00067.safetensors", "model.layers.19.self_attn.q_proj.weight": "model-00012-of-00067.safetensors", "model.layers.19.self_attn.v_proj.bias": "model-00012-of-00067.safetensors", "model.layers.19.self_attn.v_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.input_layernorm.weight": "model-00012-of-00067.safetensors", "model.layers.2.mlp.down_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.mlp.gate_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.mlp.up_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.post_attention_layernorm.weight": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.k_proj.bias": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.k_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.o_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.q_proj.bias": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.q_proj.weight": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.v_proj.bias": "model-00012-of-00067.safetensors", "model.layers.2.self_attn.v_proj.weight": "model-00012-of-00067.safetensors", "model.layers.20.input_layernorm.weight": "model-00012-of-00067.safetensors", "model.layers.20.mlp.down_proj.weight": "model-00012-of-00067.safetensors", "model.layers.20.mlp.gate_proj.weight": "model-00013-of-00067.safetensors", "model.layers.20.mlp.up_proj.weight": "model-00013-of-00067.safetensors", "model.layers.20.post_attention_layernorm.weight": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.k_proj.bias": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.k_proj.weight": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.q_proj.bias": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.q_proj.weight": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.v_proj.bias": "model-00013-of-00067.safetensors", "model.layers.20.self_attn.v_proj.weight": "model-00013-of-00067.safetensors", "model.layers.21.input_layernorm.weight": "model-00013-of-00067.safetensors", "model.layers.21.mlp.down_proj.weight": "model-00013-of-00067.safetensors", "model.layers.21.mlp.gate_proj.weight": "model-00013-of-00067.safetensors", "model.layers.21.mlp.up_proj.weight": "model-00014-of-00067.safetensors", "model.layers.21.post_attention_layernorm.weight": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.k_proj.bias": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.k_proj.weight": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.q_proj.bias": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.q_proj.weight": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.v_proj.bias": "model-00014-of-00067.safetensors", "model.layers.21.self_attn.v_proj.weight": "model-00014-of-00067.safetensors", "model.layers.22.input_layernorm.weight": "model-00014-of-00067.safetensors", "model.layers.22.mlp.down_proj.weight": "model-00014-of-00067.safetensors", "model.layers.22.mlp.gate_proj.weight": "model-00014-of-00067.safetensors", "model.layers.22.mlp.up_proj.weight": "model-00014-of-00067.safetensors", "model.layers.22.post_attention_layernorm.weight": "model-00014-of-00067.safetensors", "model.layers.22.self_attn.k_proj.bias": "model-00014-of-00067.safetensors", "model.layers.22.self_attn.k_proj.weight": "model-00014-of-00067.safetensors", "model.layers.22.self_attn.o_proj.weight": "model-00014-of-00067.safetensors", "model.layers.22.self_attn.q_proj.bias": "model-00014-of-00067.safetensors", "model.layers.22.self_attn.q_proj.weight": "model-00015-of-00067.safetensors", "model.layers.22.self_attn.v_proj.bias": "model-00015-of-00067.safetensors", "model.layers.22.self_attn.v_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.input_layernorm.weight": "model-00015-of-00067.safetensors", "model.layers.23.mlp.down_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.mlp.gate_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.mlp.up_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.post_attention_layernorm.weight": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.k_proj.bias": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.k_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.o_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.q_proj.bias": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.q_proj.weight": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.v_proj.bias": "model-00015-of-00067.safetensors", "model.layers.23.self_attn.v_proj.weight": "model-00015-of-00067.safetensors", "model.layers.24.input_layernorm.weight": "model-00015-of-00067.safetensors", "model.layers.24.mlp.down_proj.weight": "model-00015-of-00067.safetensors", "model.layers.24.mlp.gate_proj.weight": "model-00016-of-00067.safetensors", "model.layers.24.mlp.up_proj.weight": "model-00016-of-00067.safetensors", "model.layers.24.post_attention_layernorm.weight": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.k_proj.bias": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.k_proj.weight": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.q_proj.bias": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.q_proj.weight": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.v_proj.bias": "model-00016-of-00067.safetensors", "model.layers.24.self_attn.v_proj.weight": "model-00016-of-00067.safetensors", "model.layers.25.input_layernorm.weight": "model-00016-of-00067.safetensors", "model.layers.25.mlp.down_proj.weight": "model-00016-of-00067.safetensors", "model.layers.25.mlp.gate_proj.weight": "model-00016-of-00067.safetensors", "model.layers.25.mlp.up_proj.weight": "model-00017-of-00067.safetensors", "model.layers.25.post_attention_layernorm.weight": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.k_proj.bias": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.k_proj.weight": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.q_proj.bias": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.q_proj.weight": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.v_proj.bias": "model-00017-of-00067.safetensors", "model.layers.25.self_attn.v_proj.weight": "model-00017-of-00067.safetensors", "model.layers.26.input_layernorm.weight": "model-00017-of-00067.safetensors", "model.layers.26.mlp.down_proj.weight": "model-00017-of-00067.safetensors", "model.layers.26.mlp.gate_proj.weight": "model-00017-of-00067.safetensors", "model.layers.26.mlp.up_proj.weight": "model-00017-of-00067.safetensors", "model.layers.26.post_attention_layernorm.weight": "model-00017-of-00067.safetensors", "model.layers.26.self_attn.k_proj.bias": "model-00017-of-00067.safetensors", "model.layers.26.self_attn.k_proj.weight": "model-00017-of-00067.safetensors", "model.layers.26.self_attn.o_proj.weight": "model-00017-of-00067.safetensors", "model.layers.26.self_attn.q_proj.bias": "model-00017-of-00067.safetensors", "model.layers.26.self_attn.q_proj.weight": "model-00018-of-00067.safetensors", "model.layers.26.self_attn.v_proj.bias": "model-00018-of-00067.safetensors", "model.layers.26.self_attn.v_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.input_layernorm.weight": "model-00018-of-00067.safetensors", "model.layers.27.mlp.down_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.mlp.gate_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.mlp.up_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.post_attention_layernorm.weight": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.k_proj.bias": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.k_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.o_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.q_proj.bias": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.q_proj.weight": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.v_proj.bias": "model-00018-of-00067.safetensors", "model.layers.27.self_attn.v_proj.weight": "model-00018-of-00067.safetensors", "model.layers.28.input_layernorm.weight": "model-00018-of-00067.safetensors", "model.layers.28.mlp.down_proj.weight": "model-00018-of-00067.safetensors", "model.layers.28.mlp.gate_proj.weight": "model-00019-of-00067.safetensors", "model.layers.28.mlp.up_proj.weight": "model-00019-of-00067.safetensors", "model.layers.28.post_attention_layernorm.weight": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.k_proj.bias": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.k_proj.weight": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.q_proj.bias": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.q_proj.weight": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.v_proj.bias": "model-00019-of-00067.safetensors", "model.layers.28.self_attn.v_proj.weight": "model-00019-of-00067.safetensors", "model.layers.29.input_layernorm.weight": "model-00019-of-00067.safetensors", "model.layers.29.mlp.down_proj.weight": "model-00019-of-00067.safetensors", "model.layers.29.mlp.gate_proj.weight": "model-00019-of-00067.safetensors", "model.layers.29.mlp.up_proj.weight": "model-00020-of-00067.safetensors", "model.layers.29.post_attention_layernorm.weight": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.k_proj.bias": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.k_proj.weight": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.q_proj.bias": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.q_proj.weight": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.v_proj.bias": "model-00020-of-00067.safetensors", "model.layers.29.self_attn.v_proj.weight": "model-00020-of-00067.safetensors", "model.layers.3.input_layernorm.weight": "model-00020-of-00067.safetensors", "model.layers.3.mlp.down_proj.weight": "model-00020-of-00067.safetensors", "model.layers.3.mlp.gate_proj.weight": "model-00020-of-00067.safetensors", "model.layers.3.mlp.up_proj.weight": "model-00020-of-00067.safetensors", "model.layers.3.post_attention_layernorm.weight": "model-00020-of-00067.safetensors", "model.layers.3.self_attn.k_proj.bias": "model-00020-of-00067.safetensors", "model.layers.3.self_attn.k_proj.weight": "model-00020-of-00067.safetensors", "model.layers.3.self_attn.o_proj.weight": "model-00020-of-00067.safetensors", "model.layers.3.self_attn.q_proj.bias": "model-00020-of-00067.safetensors", "model.layers.3.self_attn.q_proj.weight": "model-00021-of-00067.safetensors", "model.layers.3.self_attn.v_proj.bias": "model-00021-of-00067.safetensors", "model.layers.3.self_attn.v_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.input_layernorm.weight": "model-00021-of-00067.safetensors", "model.layers.30.mlp.down_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.mlp.gate_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.mlp.up_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.post_attention_layernorm.weight": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.k_proj.bias": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.k_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.q_proj.bias": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.q_proj.weight": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.v_proj.bias": "model-00021-of-00067.safetensors", "model.layers.30.self_attn.v_proj.weight": "model-00021-of-00067.safetensors", "model.layers.31.input_layernorm.weight": "model-00021-of-00067.safetensors", "model.layers.31.mlp.down_proj.weight": "model-00021-of-00067.safetensors", "model.layers.31.mlp.gate_proj.weight": "model-00022-of-00067.safetensors", "model.layers.31.mlp.up_proj.weight": "model-00022-of-00067.safetensors", "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.k_proj.bias": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.k_proj.weight": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.q_proj.bias": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.q_proj.weight": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.v_proj.bias": "model-00022-of-00067.safetensors", "model.layers.31.self_attn.v_proj.weight": "model-00022-of-00067.safetensors", "model.layers.32.input_layernorm.weight": "model-00022-of-00067.safetensors", "model.layers.32.mlp.down_proj.weight": "model-00022-of-00067.safetensors", "model.layers.32.mlp.gate_proj.weight": "model-00022-of-00067.safetensors", "model.layers.32.mlp.up_proj.weight": "model-00023-of-00067.safetensors", "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.k_proj.bias": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.k_proj.weight": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.o_proj.weight": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.q_proj.bias": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.q_proj.weight": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.v_proj.bias": "model-00023-of-00067.safetensors", "model.layers.32.self_attn.v_proj.weight": "model-00023-of-00067.safetensors", "model.layers.33.input_layernorm.weight": "model-00023-of-00067.safetensors", "model.layers.33.mlp.down_proj.weight": "model-00023-of-00067.safetensors", "model.layers.33.mlp.gate_proj.weight": "model-00023-of-00067.safetensors", "model.layers.33.mlp.up_proj.weight": "model-00023-of-00067.safetensors", "model.layers.33.post_attention_layernorm.weight": "model-00023-of-00067.safetensors", "model.layers.33.self_attn.k_proj.bias": "model-00023-of-00067.safetensors", "model.layers.33.self_attn.k_proj.weight": "model-00023-of-00067.safetensors", "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00067.safetensors", "model.layers.33.self_attn.q_proj.bias": "model-00023-of-00067.safetensors", "model.layers.33.self_attn.q_proj.weight": "model-00024-of-00067.safetensors", "model.layers.33.self_attn.v_proj.bias": "model-00024-of-00067.safetensors", "model.layers.33.self_attn.v_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.input_layernorm.weight": "model-00024-of-00067.safetensors", "model.layers.34.mlp.down_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.mlp.gate_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.mlp.up_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.post_attention_layernorm.weight": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.k_proj.bias": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.k_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.q_proj.bias": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.q_proj.weight": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.v_proj.bias": "model-00024-of-00067.safetensors", "model.layers.34.self_attn.v_proj.weight": "model-00024-of-00067.safetensors", "model.layers.35.input_layernorm.weight": "model-00024-of-00067.safetensors", "model.layers.35.mlp.down_proj.weight": "model-00024-of-00067.safetensors", "model.layers.35.mlp.gate_proj.weight": "model-00025-of-00067.safetensors", "model.layers.35.mlp.up_proj.weight": "model-00025-of-00067.safetensors", "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.k_proj.bias": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.k_proj.weight": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.q_proj.bias": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.q_proj.weight": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.v_proj.bias": "model-00025-of-00067.safetensors", "model.layers.35.self_attn.v_proj.weight": "model-00025-of-00067.safetensors", "model.layers.36.input_layernorm.weight": "model-00025-of-00067.safetensors", "model.layers.36.mlp.down_proj.weight": "model-00025-of-00067.safetensors", "model.layers.36.mlp.gate_proj.weight": "model-00025-of-00067.safetensors", "model.layers.36.mlp.up_proj.weight": "model-00026-of-00067.safetensors", "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.k_proj.bias": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.k_proj.weight": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.o_proj.weight": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.q_proj.bias": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.q_proj.weight": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.v_proj.bias": "model-00026-of-00067.safetensors", "model.layers.36.self_attn.v_proj.weight": "model-00026-of-00067.safetensors", "model.layers.37.input_layernorm.weight": "model-00026-of-00067.safetensors", "model.layers.37.mlp.down_proj.weight": "model-00026-of-00067.safetensors", "model.layers.37.mlp.gate_proj.weight": "model-00026-of-00067.safetensors", "model.layers.37.mlp.up_proj.weight": "model-00026-of-00067.safetensors", "model.layers.37.post_attention_layernorm.weight": "model-00026-of-00067.safetensors", "model.layers.37.self_attn.k_proj.bias": "model-00026-of-00067.safetensors", "model.layers.37.self_attn.k_proj.weight": "model-00026-of-00067.safetensors", "model.layers.37.self_attn.o_proj.weight": "model-00026-of-00067.safetensors", "model.layers.37.self_attn.q_proj.bias": "model-00026-of-00067.safetensors", "model.layers.37.self_attn.q_proj.weight": "model-00027-of-00067.safetensors", "model.layers.37.self_attn.v_proj.bias": "model-00027-of-00067.safetensors", "model.layers.37.self_attn.v_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.input_layernorm.weight": "model-00027-of-00067.safetensors", "model.layers.38.mlp.down_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.mlp.gate_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.mlp.up_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.post_attention_layernorm.weight": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.k_proj.bias": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.k_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.o_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.q_proj.bias": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.q_proj.weight": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.v_proj.bias": "model-00027-of-00067.safetensors", "model.layers.38.self_attn.v_proj.weight": "model-00027-of-00067.safetensors", "model.layers.39.input_layernorm.weight": "model-00027-of-00067.safetensors", "model.layers.39.mlp.down_proj.weight": "model-00027-of-00067.safetensors", "model.layers.39.mlp.gate_proj.weight": "model-00028-of-00067.safetensors", "model.layers.39.mlp.up_proj.weight": "model-00028-of-00067.safetensors", "model.layers.39.post_attention_layernorm.weight": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.k_proj.bias": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.k_proj.weight": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.o_proj.weight": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.q_proj.bias": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.q_proj.weight": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.v_proj.bias": "model-00028-of-00067.safetensors", "model.layers.39.self_attn.v_proj.weight": "model-00028-of-00067.safetensors", "model.layers.4.input_layernorm.weight": "model-00028-of-00067.safetensors", "model.layers.4.mlp.down_proj.weight": "model-00028-of-00067.safetensors", "model.layers.4.mlp.gate_proj.weight": "model-00028-of-00067.safetensors", "model.layers.4.mlp.up_proj.weight": "model-00029-of-00067.safetensors", "model.layers.4.post_attention_layernorm.weight": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.k_proj.bias": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.k_proj.weight": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.o_proj.weight": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.q_proj.bias": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.q_proj.weight": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.v_proj.bias": "model-00029-of-00067.safetensors", "model.layers.4.self_attn.v_proj.weight": "model-00029-of-00067.safetensors", "model.layers.40.input_layernorm.weight": "model-00029-of-00067.safetensors", "model.layers.40.mlp.down_proj.weight": "model-00029-of-00067.safetensors", "model.layers.40.mlp.gate_proj.weight": "model-00029-of-00067.safetensors", "model.layers.40.mlp.up_proj.weight": "model-00029-of-00067.safetensors", "model.layers.40.post_attention_layernorm.weight": "model-00029-of-00067.safetensors", "model.layers.40.self_attn.k_proj.bias": "model-00029-of-00067.safetensors", "model.layers.40.self_attn.k_proj.weight": "model-00029-of-00067.safetensors", "model.layers.40.self_attn.o_proj.weight": "model-00029-of-00067.safetensors", "model.layers.40.self_attn.q_proj.bias": "model-00029-of-00067.safetensors", "model.layers.40.self_attn.q_proj.weight": "model-00030-of-00067.safetensors", "model.layers.40.self_attn.v_proj.bias": "model-00030-of-00067.safetensors", "model.layers.40.self_attn.v_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.input_layernorm.weight": "model-00030-of-00067.safetensors", "model.layers.41.mlp.down_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.mlp.gate_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.mlp.up_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.post_attention_layernorm.weight": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.k_proj.bias": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.k_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.o_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.q_proj.bias": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.q_proj.weight": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.v_proj.bias": "model-00030-of-00067.safetensors", "model.layers.41.self_attn.v_proj.weight": "model-00030-of-00067.safetensors", "model.layers.42.input_layernorm.weight": "model-00030-of-00067.safetensors", "model.layers.42.mlp.down_proj.weight": "model-00030-of-00067.safetensors", "model.layers.42.mlp.gate_proj.weight": "model-00031-of-00067.safetensors", "model.layers.42.mlp.up_proj.weight": "model-00031-of-00067.safetensors", "model.layers.42.post_attention_layernorm.weight": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.k_proj.bias": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.k_proj.weight": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.o_proj.weight": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.q_proj.bias": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.q_proj.weight": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.v_proj.bias": "model-00031-of-00067.safetensors", "model.layers.42.self_attn.v_proj.weight": "model-00031-of-00067.safetensors", "model.layers.43.input_layernorm.weight": "model-00031-of-00067.safetensors", "model.layers.43.mlp.down_proj.weight": "model-00031-of-00067.safetensors", "model.layers.43.mlp.gate_proj.weight": "model-00031-of-00067.safetensors", "model.layers.43.mlp.up_proj.weight": "model-00032-of-00067.safetensors", "model.layers.43.post_attention_layernorm.weight": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.k_proj.bias": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.k_proj.weight": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.o_proj.weight": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.q_proj.bias": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.q_proj.weight": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.v_proj.bias": "model-00032-of-00067.safetensors", "model.layers.43.self_attn.v_proj.weight": "model-00032-of-00067.safetensors", "model.layers.44.input_layernorm.weight": "model-00032-of-00067.safetensors", "model.layers.44.mlp.down_proj.weight": "model-00032-of-00067.safetensors", "model.layers.44.mlp.gate_proj.weight": "model-00032-of-00067.safetensors", "model.layers.44.mlp.up_proj.weight": "model-00032-of-00067.safetensors", "model.layers.44.post_attention_layernorm.weight": "model-00032-of-00067.safetensors", "model.layers.44.self_attn.k_proj.bias": "model-00032-of-00067.safetensors", "model.layers.44.self_attn.k_proj.weight": "model-00032-of-00067.safetensors", "model.layers.44.self_attn.o_proj.weight": "model-00032-of-00067.safetensors", "model.layers.44.self_attn.q_proj.bias": "model-00032-of-00067.safetensors", "model.layers.44.self_attn.q_proj.weight": "model-00033-of-00067.safetensors", "model.layers.44.self_attn.v_proj.bias": "model-00033-of-00067.safetensors", "model.layers.44.self_attn.v_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.input_layernorm.weight": "model-00033-of-00067.safetensors", "model.layers.45.mlp.down_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.mlp.gate_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.mlp.up_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.post_attention_layernorm.weight": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.k_proj.bias": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.k_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.o_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.q_proj.bias": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.q_proj.weight": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.v_proj.bias": "model-00033-of-00067.safetensors", "model.layers.45.self_attn.v_proj.weight": "model-00033-of-00067.safetensors", "model.layers.46.input_layernorm.weight": "model-00033-of-00067.safetensors", "model.layers.46.mlp.down_proj.weight": "model-00033-of-00067.safetensors", "model.layers.46.mlp.gate_proj.weight": "model-00034-of-00067.safetensors", "model.layers.46.mlp.up_proj.weight": "model-00034-of-00067.safetensors", "model.layers.46.post_attention_layernorm.weight": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.k_proj.bias": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.k_proj.weight": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.o_proj.weight": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.q_proj.bias": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.q_proj.weight": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.v_proj.bias": "model-00034-of-00067.safetensors", "model.layers.46.self_attn.v_proj.weight": "model-00034-of-00067.safetensors", "model.layers.47.input_layernorm.weight": "model-00034-of-00067.safetensors", "model.layers.47.mlp.down_proj.weight": "model-00034-of-00067.safetensors", "model.layers.47.mlp.gate_proj.weight": "model-00034-of-00067.safetensors", "model.layers.47.mlp.up_proj.weight": "model-00035-of-00067.safetensors", "model.layers.47.post_attention_layernorm.weight": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.k_proj.bias": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.k_proj.weight": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.o_proj.weight": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.q_proj.bias": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.q_proj.weight": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.v_proj.bias": "model-00035-of-00067.safetensors", "model.layers.47.self_attn.v_proj.weight": "model-00035-of-00067.safetensors", "model.layers.48.input_layernorm.weight": "model-00035-of-00067.safetensors", "model.layers.48.mlp.down_proj.weight": "model-00035-of-00067.safetensors", "model.layers.48.mlp.gate_proj.weight": "model-00035-of-00067.safetensors", "model.layers.48.mlp.up_proj.weight": "model-00035-of-00067.safetensors", "model.layers.48.post_attention_layernorm.weight": "model-00035-of-00067.safetensors", "model.layers.48.self_attn.k_proj.bias": "model-00035-of-00067.safetensors", "model.layers.48.self_attn.k_proj.weight": "model-00035-of-00067.safetensors", "model.layers.48.self_attn.o_proj.weight": "model-00035-of-00067.safetensors", "model.layers.48.self_attn.q_proj.bias": "model-00035-of-00067.safetensors", "model.layers.48.self_attn.q_proj.weight": "model-00036-of-00067.safetensors", "model.layers.48.self_attn.v_proj.bias": "model-00036-of-00067.safetensors", "model.layers.48.self_attn.v_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.input_layernorm.weight": "model-00036-of-00067.safetensors", "model.layers.49.mlp.down_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.mlp.gate_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.mlp.up_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.post_attention_layernorm.weight": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.k_proj.bias": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.k_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.o_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.q_proj.bias": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.q_proj.weight": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.v_proj.bias": "model-00036-of-00067.safetensors", "model.layers.49.self_attn.v_proj.weight": "model-00036-of-00067.safetensors", "model.layers.5.input_layernorm.weight": "model-00036-of-00067.safetensors", "model.layers.5.mlp.down_proj.weight": "model-00036-of-00067.safetensors", "model.layers.5.mlp.gate_proj.weight": "model-00037-of-00067.safetensors", "model.layers.5.mlp.up_proj.weight": "model-00037-of-00067.safetensors", "model.layers.5.post_attention_layernorm.weight": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.k_proj.bias": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.k_proj.weight": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.o_proj.weight": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.q_proj.bias": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.q_proj.weight": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.v_proj.bias": "model-00037-of-00067.safetensors", "model.layers.5.self_attn.v_proj.weight": "model-00037-of-00067.safetensors", "model.layers.50.input_layernorm.weight": "model-00037-of-00067.safetensors", "model.layers.50.mlp.down_proj.weight": "model-00037-of-00067.safetensors", "model.layers.50.mlp.gate_proj.weight": "model-00037-of-00067.safetensors", "model.layers.50.mlp.up_proj.weight": "model-00038-of-00067.safetensors", "model.layers.50.post_attention_layernorm.weight": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.k_proj.bias": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.k_proj.weight": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.o_proj.weight": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.q_proj.bias": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.q_proj.weight": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.v_proj.bias": "model-00038-of-00067.safetensors", "model.layers.50.self_attn.v_proj.weight": "model-00038-of-00067.safetensors", "model.layers.51.input_layernorm.weight": "model-00038-of-00067.safetensors", "model.layers.51.mlp.down_proj.weight": "model-00038-of-00067.safetensors", "model.layers.51.mlp.gate_proj.weight": "model-00038-of-00067.safetensors", "model.layers.51.mlp.up_proj.weight": "model-00038-of-00067.safetensors", "model.layers.51.post_attention_layernorm.weight": "model-00038-of-00067.safetensors", "model.layers.51.self_attn.k_proj.bias": "model-00038-of-00067.safetensors", "model.layers.51.self_attn.k_proj.weight": "model-00038-of-00067.safetensors", "model.layers.51.self_attn.o_proj.weight": "model-00038-of-00067.safetensors", "model.layers.51.self_attn.q_proj.bias": "model-00038-of-00067.safetensors", "model.layers.51.self_attn.q_proj.weight": "model-00039-of-00067.safetensors", "model.layers.51.self_attn.v_proj.bias": "model-00039-of-00067.safetensors", "model.layers.51.self_attn.v_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.input_layernorm.weight": "model-00039-of-00067.safetensors", "model.layers.52.mlp.down_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.mlp.gate_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.mlp.up_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.post_attention_layernorm.weight": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.k_proj.bias": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.k_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.o_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.q_proj.bias": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.q_proj.weight": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.v_proj.bias": "model-00039-of-00067.safetensors", "model.layers.52.self_attn.v_proj.weight": "model-00039-of-00067.safetensors", "model.layers.53.input_layernorm.weight": "model-00039-of-00067.safetensors", "model.layers.53.mlp.down_proj.weight": "model-00039-of-00067.safetensors", "model.layers.53.mlp.gate_proj.weight": "model-00040-of-00067.safetensors", "model.layers.53.mlp.up_proj.weight": "model-00040-of-00067.safetensors", "model.layers.53.post_attention_layernorm.weight": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.k_proj.bias": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.k_proj.weight": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.o_proj.weight": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.q_proj.bias": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.q_proj.weight": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.v_proj.bias": "model-00040-of-00067.safetensors", "model.layers.53.self_attn.v_proj.weight": "model-00040-of-00067.safetensors", "model.layers.54.input_layernorm.weight": "model-00040-of-00067.safetensors", "model.layers.54.mlp.down_proj.weight": "model-00040-of-00067.safetensors", "model.layers.54.mlp.gate_proj.weight": "model-00040-of-00067.safetensors", "model.layers.54.mlp.up_proj.weight": "model-00041-of-00067.safetensors", "model.layers.54.post_attention_layernorm.weight": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.k_proj.bias": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.k_proj.weight": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.o_proj.weight": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.q_proj.bias": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.q_proj.weight": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.v_proj.bias": "model-00041-of-00067.safetensors", "model.layers.54.self_attn.v_proj.weight": "model-00041-of-00067.safetensors", "model.layers.55.input_layernorm.weight": "model-00041-of-00067.safetensors", "model.layers.55.mlp.down_proj.weight": "model-00041-of-00067.safetensors", "model.layers.55.mlp.gate_proj.weight": "model-00041-of-00067.safetensors", "model.layers.55.mlp.up_proj.weight": "model-00041-of-00067.safetensors", "model.layers.55.post_attention_layernorm.weight": "model-00041-of-00067.safetensors", "model.layers.55.self_attn.k_proj.bias": "model-00041-of-00067.safetensors", "model.layers.55.self_attn.k_proj.weight": "model-00041-of-00067.safetensors", "model.layers.55.self_attn.o_proj.weight": "model-00041-of-00067.safetensors", "model.layers.55.self_attn.q_proj.bias": "model-00041-of-00067.safetensors", "model.layers.55.self_attn.q_proj.weight": "model-00042-of-00067.safetensors", "model.layers.55.self_attn.v_proj.bias": "model-00042-of-00067.safetensors", "model.layers.55.self_attn.v_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.input_layernorm.weight": "model-00042-of-00067.safetensors", "model.layers.56.mlp.down_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.mlp.gate_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.mlp.up_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.post_attention_layernorm.weight": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.k_proj.bias": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.k_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.o_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.q_proj.bias": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.q_proj.weight": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.v_proj.bias": "model-00042-of-00067.safetensors", "model.layers.56.self_attn.v_proj.weight": "model-00042-of-00067.safetensors", "model.layers.57.input_layernorm.weight": "model-00042-of-00067.safetensors", "model.layers.57.mlp.down_proj.weight": "model-00042-of-00067.safetensors", "model.layers.57.mlp.gate_proj.weight": "model-00043-of-00067.safetensors", "model.layers.57.mlp.up_proj.weight": "model-00043-of-00067.safetensors", "model.layers.57.post_attention_layernorm.weight": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.k_proj.bias": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.k_proj.weight": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.o_proj.weight": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.q_proj.bias": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.q_proj.weight": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.v_proj.bias": "model-00043-of-00067.safetensors", "model.layers.57.self_attn.v_proj.weight": "model-00043-of-00067.safetensors", "model.layers.58.input_layernorm.weight": "model-00043-of-00067.safetensors", "model.layers.58.mlp.down_proj.weight": "model-00043-of-00067.safetensors", "model.layers.58.mlp.gate_proj.weight": "model-00043-of-00067.safetensors", "model.layers.58.mlp.up_proj.weight": "model-00044-of-00067.safetensors", "model.layers.58.post_attention_layernorm.weight": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.k_proj.bias": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.k_proj.weight": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.o_proj.weight": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.q_proj.bias": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.q_proj.weight": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.v_proj.bias": "model-00044-of-00067.safetensors", "model.layers.58.self_attn.v_proj.weight": "model-00044-of-00067.safetensors", "model.layers.59.input_layernorm.weight": "model-00044-of-00067.safetensors", "model.layers.59.mlp.down_proj.weight": "model-00044-of-00067.safetensors", "model.layers.59.mlp.gate_proj.weight": "model-00044-of-00067.safetensors", "model.layers.59.mlp.up_proj.weight": "model-00044-of-00067.safetensors", "model.layers.59.post_attention_layernorm.weight": "model-00044-of-00067.safetensors", "model.layers.59.self_attn.k_proj.bias": "model-00044-of-00067.safetensors", "model.layers.59.self_attn.k_proj.weight": "model-00044-of-00067.safetensors", "model.layers.59.self_attn.o_proj.weight": "model-00044-of-00067.safetensors", "model.layers.59.self_attn.q_proj.bias": "model-00044-of-00067.safetensors", "model.layers.59.self_attn.q_proj.weight": "model-00045-of-00067.safetensors", "model.layers.59.self_attn.v_proj.bias": "model-00045-of-00067.safetensors", "model.layers.59.self_attn.v_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.input_layernorm.weight": "model-00045-of-00067.safetensors", "model.layers.6.mlp.down_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.mlp.gate_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.mlp.up_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.post_attention_layernorm.weight": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.k_proj.bias": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.k_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.o_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.q_proj.bias": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.q_proj.weight": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.v_proj.bias": "model-00045-of-00067.safetensors", "model.layers.6.self_attn.v_proj.weight": "model-00045-of-00067.safetensors", "model.layers.60.input_layernorm.weight": "model-00045-of-00067.safetensors", "model.layers.60.mlp.down_proj.weight": "model-00045-of-00067.safetensors", "model.layers.60.mlp.gate_proj.weight": "model-00046-of-00067.safetensors", "model.layers.60.mlp.up_proj.weight": "model-00046-of-00067.safetensors", "model.layers.60.post_attention_layernorm.weight": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.k_proj.bias": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.k_proj.weight": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.o_proj.weight": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.q_proj.bias": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.q_proj.weight": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.v_proj.bias": "model-00046-of-00067.safetensors", "model.layers.60.self_attn.v_proj.weight": "model-00046-of-00067.safetensors", "model.layers.61.input_layernorm.weight": "model-00046-of-00067.safetensors", "model.layers.61.mlp.down_proj.weight": "model-00046-of-00067.safetensors", "model.layers.61.mlp.gate_proj.weight": "model-00046-of-00067.safetensors", "model.layers.61.mlp.up_proj.weight": "model-00047-of-00067.safetensors", "model.layers.61.post_attention_layernorm.weight": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.k_proj.bias": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.k_proj.weight": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.o_proj.weight": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.q_proj.bias": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.q_proj.weight": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.v_proj.bias": "model-00047-of-00067.safetensors", "model.layers.61.self_attn.v_proj.weight": "model-00047-of-00067.safetensors", "model.layers.62.input_layernorm.weight": "model-00047-of-00067.safetensors", "model.layers.62.mlp.down_proj.weight": "model-00047-of-00067.safetensors", "model.layers.62.mlp.gate_proj.weight": "model-00047-of-00067.safetensors", "model.layers.62.mlp.up_proj.weight": "model-00047-of-00067.safetensors", "model.layers.62.post_attention_layernorm.weight": "model-00047-of-00067.safetensors", "model.layers.62.self_attn.k_proj.bias": "model-00047-of-00067.safetensors", "model.layers.62.self_attn.k_proj.weight": "model-00047-of-00067.safetensors", "model.layers.62.self_attn.o_proj.weight": "model-00047-of-00067.safetensors", "model.layers.62.self_attn.q_proj.bias": "model-00047-of-00067.safetensors", "model.layers.62.self_attn.q_proj.weight": "model-00048-of-00067.safetensors", "model.layers.62.self_attn.v_proj.bias": "model-00048-of-00067.safetensors", "model.layers.62.self_attn.v_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.input_layernorm.weight": "model-00048-of-00067.safetensors", "model.layers.63.mlp.down_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.mlp.gate_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.mlp.up_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.post_attention_layernorm.weight": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.k_proj.bias": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.k_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.o_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.q_proj.bias": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.q_proj.weight": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.v_proj.bias": "model-00048-of-00067.safetensors", "model.layers.63.self_attn.v_proj.weight": "model-00048-of-00067.safetensors", "model.layers.64.input_layernorm.weight": "model-00048-of-00067.safetensors", "model.layers.64.mlp.down_proj.weight": "model-00048-of-00067.safetensors", "model.layers.64.mlp.gate_proj.weight": "model-00049-of-00067.safetensors", "model.layers.64.mlp.up_proj.weight": "model-00049-of-00067.safetensors", "model.layers.64.post_attention_layernorm.weight": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.k_proj.bias": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.k_proj.weight": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.o_proj.weight": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.q_proj.bias": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.q_proj.weight": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.v_proj.bias": "model-00049-of-00067.safetensors", "model.layers.64.self_attn.v_proj.weight": "model-00049-of-00067.safetensors", "model.layers.65.input_layernorm.weight": "model-00049-of-00067.safetensors", "model.layers.65.mlp.down_proj.weight": "model-00049-of-00067.safetensors", "model.layers.65.mlp.gate_proj.weight": "model-00049-of-00067.safetensors", "model.layers.65.mlp.up_proj.weight": "model-00050-of-00067.safetensors", "model.layers.65.post_attention_layernorm.weight": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.k_proj.bias": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.k_proj.weight": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.o_proj.weight": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.q_proj.bias": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.q_proj.weight": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.v_proj.bias": "model-00050-of-00067.safetensors", "model.layers.65.self_attn.v_proj.weight": "model-00050-of-00067.safetensors", "model.layers.66.input_layernorm.weight": "model-00050-of-00067.safetensors", "model.layers.66.mlp.down_proj.weight": "model-00050-of-00067.safetensors", "model.layers.66.mlp.gate_proj.weight": "model-00050-of-00067.safetensors", "model.layers.66.mlp.up_proj.weight": "model-00050-of-00067.safetensors", "model.layers.66.post_attention_layernorm.weight": "model-00050-of-00067.safetensors", "model.layers.66.self_attn.k_proj.bias": "model-00050-of-00067.safetensors", "model.layers.66.self_attn.k_proj.weight": "model-00050-of-00067.safetensors", "model.layers.66.self_attn.o_proj.weight": "model-00050-of-00067.safetensors", "model.layers.66.self_attn.q_proj.bias": "model-00050-of-00067.safetensors", "model.layers.66.self_attn.q_proj.weight": "model-00051-of-00067.safetensors", "model.layers.66.self_attn.v_proj.bias": "model-00051-of-00067.safetensors", "model.layers.66.self_attn.v_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.input_layernorm.weight": "model-00051-of-00067.safetensors", "model.layers.67.mlp.down_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.mlp.gate_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.mlp.up_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.post_attention_layernorm.weight": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.k_proj.bias": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.k_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.o_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.q_proj.bias": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.q_proj.weight": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.v_proj.bias": "model-00051-of-00067.safetensors", "model.layers.67.self_attn.v_proj.weight": "model-00051-of-00067.safetensors", "model.layers.68.input_layernorm.weight": "model-00051-of-00067.safetensors", "model.layers.68.mlp.down_proj.weight": "model-00051-of-00067.safetensors", "model.layers.68.mlp.gate_proj.weight": "model-00052-of-00067.safetensors", "model.layers.68.mlp.up_proj.weight": "model-00052-of-00067.safetensors", "model.layers.68.post_attention_layernorm.weight": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.k_proj.bias": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.k_proj.weight": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.o_proj.weight": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.q_proj.bias": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.q_proj.weight": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.v_proj.bias": "model-00052-of-00067.safetensors", "model.layers.68.self_attn.v_proj.weight": "model-00052-of-00067.safetensors", "model.layers.69.input_layernorm.weight": "model-00052-of-00067.safetensors", "model.layers.69.mlp.down_proj.weight": "model-00052-of-00067.safetensors", "model.layers.69.mlp.gate_proj.weight": "model-00052-of-00067.safetensors", "model.layers.69.mlp.up_proj.weight": "model-00053-of-00067.safetensors", "model.layers.69.post_attention_layernorm.weight": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.k_proj.bias": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.k_proj.weight": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.o_proj.weight": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.q_proj.bias": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.q_proj.weight": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.v_proj.bias": "model-00053-of-00067.safetensors", "model.layers.69.self_attn.v_proj.weight": "model-00053-of-00067.safetensors", "model.layers.7.input_layernorm.weight": "model-00053-of-00067.safetensors", "model.layers.7.mlp.down_proj.weight": "model-00053-of-00067.safetensors", "model.layers.7.mlp.gate_proj.weight": "model-00053-of-00067.safetensors", "model.layers.7.mlp.up_proj.weight": "model-00053-of-00067.safetensors", "model.layers.7.post_attention_layernorm.weight": "model-00053-of-00067.safetensors", "model.layers.7.self_attn.k_proj.bias": "model-00053-of-00067.safetensors", "model.layers.7.self_attn.k_proj.weight": "model-00053-of-00067.safetensors", "model.layers.7.self_attn.o_proj.weight": "model-00053-of-00067.safetensors", "model.layers.7.self_attn.q_proj.bias": "model-00053-of-00067.safetensors", "model.layers.7.self_attn.q_proj.weight": "model-00054-of-00067.safetensors", "model.layers.7.self_attn.v_proj.bias": "model-00054-of-00067.safetensors", "model.layers.7.self_attn.v_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.input_layernorm.weight": "model-00054-of-00067.safetensors", "model.layers.70.mlp.down_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.mlp.gate_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.mlp.up_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.post_attention_layernorm.weight": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.k_proj.bias": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.k_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.o_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.q_proj.bias": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.q_proj.weight": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.v_proj.bias": "model-00054-of-00067.safetensors", "model.layers.70.self_attn.v_proj.weight": "model-00054-of-00067.safetensors", "model.layers.71.input_layernorm.weight": "model-00054-of-00067.safetensors", "model.layers.71.mlp.down_proj.weight": "model-00054-of-00067.safetensors", "model.layers.71.mlp.gate_proj.weight": "model-00055-of-00067.safetensors", "model.layers.71.mlp.up_proj.weight": "model-00055-of-00067.safetensors", "model.layers.71.post_attention_layernorm.weight": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.k_proj.bias": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.k_proj.weight": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.o_proj.weight": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.q_proj.bias": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.q_proj.weight": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.v_proj.bias": "model-00055-of-00067.safetensors", "model.layers.71.self_attn.v_proj.weight": "model-00055-of-00067.safetensors", "model.layers.72.input_layernorm.weight": "model-00055-of-00067.safetensors", "model.layers.72.mlp.down_proj.weight": "model-00055-of-00067.safetensors", "model.layers.72.mlp.gate_proj.weight": "model-00055-of-00067.safetensors", "model.layers.72.mlp.up_proj.weight": "model-00056-of-00067.safetensors", "model.layers.72.post_attention_layernorm.weight": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.k_proj.bias": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.k_proj.weight": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.o_proj.weight": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.q_proj.bias": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.q_proj.weight": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.v_proj.bias": "model-00056-of-00067.safetensors", "model.layers.72.self_attn.v_proj.weight": "model-00056-of-00067.safetensors", "model.layers.73.input_layernorm.weight": "model-00056-of-00067.safetensors", "model.layers.73.mlp.down_proj.weight": "model-00056-of-00067.safetensors", "model.layers.73.mlp.gate_proj.weight": "model-00056-of-00067.safetensors", "model.layers.73.mlp.up_proj.weight": "model-00056-of-00067.safetensors", "model.layers.73.post_attention_layernorm.weight": "model-00056-of-00067.safetensors", "model.layers.73.self_attn.k_proj.bias": "model-00056-of-00067.safetensors", "model.layers.73.self_attn.k_proj.weight": "model-00056-of-00067.safetensors", "model.layers.73.self_attn.o_proj.weight": "model-00056-of-00067.safetensors", "model.layers.73.self_attn.q_proj.bias": "model-00056-of-00067.safetensors", "model.layers.73.self_attn.q_proj.weight": "model-00057-of-00067.safetensors", "model.layers.73.self_attn.v_proj.bias": "model-00057-of-00067.safetensors", "model.layers.73.self_attn.v_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.input_layernorm.weight": "model-00057-of-00067.safetensors", "model.layers.74.mlp.down_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.mlp.gate_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.mlp.up_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.post_attention_layernorm.weight": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.k_proj.bias": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.k_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.o_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.q_proj.bias": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.q_proj.weight": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.v_proj.bias": "model-00057-of-00067.safetensors", "model.layers.74.self_attn.v_proj.weight": "model-00057-of-00067.safetensors", "model.layers.75.input_layernorm.weight": "model-00057-of-00067.safetensors", "model.layers.75.mlp.down_proj.weight": "model-00057-of-00067.safetensors", "model.layers.75.mlp.gate_proj.weight": "model-00058-of-00067.safetensors", "model.layers.75.mlp.up_proj.weight": "model-00058-of-00067.safetensors", "model.layers.75.post_attention_layernorm.weight": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.k_proj.bias": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.k_proj.weight": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.o_proj.weight": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.q_proj.bias": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.q_proj.weight": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.v_proj.bias": "model-00058-of-00067.safetensors", "model.layers.75.self_attn.v_proj.weight": "model-00058-of-00067.safetensors", "model.layers.76.input_layernorm.weight": "model-00058-of-00067.safetensors", "model.layers.76.mlp.down_proj.weight": "model-00058-of-00067.safetensors", "model.layers.76.mlp.gate_proj.weight": "model-00058-of-00067.safetensors", "model.layers.76.mlp.up_proj.weight": "model-00059-of-00067.safetensors", "model.layers.76.post_attention_layernorm.weight": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.k_proj.bias": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.k_proj.weight": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.o_proj.weight": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.q_proj.bias": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.q_proj.weight": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.v_proj.bias": "model-00059-of-00067.safetensors", "model.layers.76.self_attn.v_proj.weight": "model-00059-of-00067.safetensors", "model.layers.77.input_layernorm.weight": "model-00059-of-00067.safetensors", "model.layers.77.mlp.down_proj.weight": "model-00059-of-00067.safetensors", "model.layers.77.mlp.gate_proj.weight": "model-00059-of-00067.safetensors", "model.layers.77.mlp.up_proj.weight": "model-00059-of-00067.safetensors", "model.layers.77.post_attention_layernorm.weight": "model-00059-of-00067.safetensors", "model.layers.77.self_attn.k_proj.bias": "model-00059-of-00067.safetensors", "model.layers.77.self_attn.k_proj.weight": "model-00059-of-00067.safetensors", "model.layers.77.self_attn.o_proj.weight": "model-00059-of-00067.safetensors", "model.layers.77.self_attn.q_proj.bias": "model-00059-of-00067.safetensors", "model.layers.77.self_attn.q_proj.weight": "model-00060-of-00067.safetensors", "model.layers.77.self_attn.v_proj.bias": "model-00060-of-00067.safetensors", "model.layers.77.self_attn.v_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.input_layernorm.weight": "model-00060-of-00067.safetensors", "model.layers.78.mlp.down_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.mlp.gate_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.mlp.up_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.post_attention_layernorm.weight": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.k_proj.bias": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.k_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.o_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.q_proj.bias": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.q_proj.weight": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.v_proj.bias": "model-00060-of-00067.safetensors", "model.layers.78.self_attn.v_proj.weight": "model-00060-of-00067.safetensors", "model.layers.79.input_layernorm.weight": "model-00060-of-00067.safetensors", "model.layers.79.mlp.down_proj.weight": "model-00060-of-00067.safetensors", "model.layers.79.mlp.gate_proj.weight": "model-00061-of-00067.safetensors", "model.layers.79.mlp.up_proj.weight": "model-00061-of-00067.safetensors", "model.layers.79.post_attention_layernorm.weight": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.k_proj.bias": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.k_proj.weight": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.o_proj.weight": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.q_proj.bias": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.q_proj.weight": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.v_proj.bias": "model-00061-of-00067.safetensors", "model.layers.79.self_attn.v_proj.weight": "model-00061-of-00067.safetensors", "model.layers.8.input_layernorm.weight": "model-00061-of-00067.safetensors", "model.layers.8.mlp.down_proj.weight": "model-00061-of-00067.safetensors", "model.layers.8.mlp.gate_proj.weight": "model-00061-of-00067.safetensors", "model.layers.8.mlp.up_proj.weight": "model-00062-of-00067.safetensors", "model.layers.8.post_attention_layernorm.weight": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.k_proj.bias": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.k_proj.weight": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.o_proj.weight": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.q_proj.bias": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.q_proj.weight": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.v_proj.bias": "model-00062-of-00067.safetensors", "model.layers.8.self_attn.v_proj.weight": "model-00062-of-00067.safetensors", "model.layers.80.input_layernorm.weight": "model-00062-of-00067.safetensors", "model.layers.80.mlp.down_proj.weight": "model-00062-of-00067.safetensors", "model.layers.80.mlp.gate_proj.weight": "model-00062-of-00067.safetensors", "model.layers.80.mlp.up_proj.weight": "model-00062-of-00067.safetensors", "model.layers.80.post_attention_layernorm.weight": "model-00062-of-00067.safetensors", "model.layers.80.self_attn.k_proj.bias": "model-00062-of-00067.safetensors", "model.layers.80.self_attn.k_proj.weight": "model-00062-of-00067.safetensors", "model.layers.80.self_attn.o_proj.weight": "model-00062-of-00067.safetensors", "model.layers.80.self_attn.q_proj.bias": "model-00062-of-00067.safetensors", "model.layers.80.self_attn.q_proj.weight": "model-00063-of-00067.safetensors", "model.layers.80.self_attn.v_proj.bias": "model-00063-of-00067.safetensors", "model.layers.80.self_attn.v_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.input_layernorm.weight": "model-00063-of-00067.safetensors", "model.layers.81.mlp.down_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.mlp.gate_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.mlp.up_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.post_attention_layernorm.weight": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.k_proj.bias": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.k_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.o_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.q_proj.bias": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.q_proj.weight": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.v_proj.bias": "model-00063-of-00067.safetensors", "model.layers.81.self_attn.v_proj.weight": "model-00063-of-00067.safetensors", "model.layers.82.input_layernorm.weight": "model-00063-of-00067.safetensors", "model.layers.82.mlp.down_proj.weight": "model-00063-of-00067.safetensors", "model.layers.82.mlp.gate_proj.weight": "model-00064-of-00067.safetensors", "model.layers.82.mlp.up_proj.weight": "model-00064-of-00067.safetensors", "model.layers.82.post_attention_layernorm.weight": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.k_proj.bias": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.k_proj.weight": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.o_proj.weight": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.q_proj.bias": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.q_proj.weight": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.v_proj.bias": "model-00064-of-00067.safetensors", "model.layers.82.self_attn.v_proj.weight": "model-00064-of-00067.safetensors", "model.layers.83.input_layernorm.weight": "model-00064-of-00067.safetensors", "model.layers.83.mlp.down_proj.weight": "model-00064-of-00067.safetensors", "model.layers.83.mlp.gate_proj.weight": "model-00064-of-00067.safetensors", "model.layers.83.mlp.up_proj.weight": "model-00065-of-00067.safetensors", "model.layers.83.post_attention_layernorm.weight": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.k_proj.bias": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.k_proj.weight": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.o_proj.weight": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.q_proj.bias": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.q_proj.weight": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.v_proj.bias": "model-00065-of-00067.safetensors", "model.layers.83.self_attn.v_proj.weight": "model-00065-of-00067.safetensors", "model.layers.84.input_layernorm.weight": "model-00065-of-00067.safetensors", "model.layers.84.mlp.down_proj.weight": "model-00065-of-00067.safetensors", "model.layers.84.mlp.gate_proj.weight": "model-00065-of-00067.safetensors", "model.layers.84.mlp.up_proj.weight": "model-00065-of-00067.safetensors", "model.layers.84.post_attention_layernorm.weight": "model-00065-of-00067.safetensors", "model.layers.84.self_attn.k_proj.bias": "model-00065-of-00067.safetensors", "model.layers.84.self_attn.k_proj.weight": "model-00065-of-00067.safetensors", "model.layers.84.self_attn.o_proj.weight": "model-00065-of-00067.safetensors", "model.layers.84.self_attn.q_proj.bias": "model-00065-of-00067.safetensors", "model.layers.84.self_attn.q_proj.weight": "model-00066-of-00067.safetensors", "model.layers.84.self_attn.v_proj.bias": "model-00066-of-00067.safetensors", "model.layers.84.self_attn.v_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.input_layernorm.weight": "model-00066-of-00067.safetensors", "model.layers.85.mlp.down_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.mlp.gate_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.mlp.up_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.post_attention_layernorm.weight": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.k_proj.bias": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.k_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.o_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.q_proj.bias": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.q_proj.weight": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.v_proj.bias": "model-00066-of-00067.safetensors", "model.layers.85.self_attn.v_proj.weight": "model-00066-of-00067.safetensors", "model.layers.9.input_layernorm.weight": "model-00066-of-00067.safetensors", "model.layers.9.mlp.down_proj.weight": "model-00066-of-00067.safetensors", "model.layers.9.mlp.gate_proj.weight": "model-00067-of-00067.safetensors", "model.layers.9.mlp.up_proj.weight": "model-00067-of-00067.safetensors", "model.layers.9.post_attention_layernorm.weight": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.k_proj.bias": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.k_proj.weight": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.o_proj.weight": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.q_proj.bias": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.q_proj.weight": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.v_proj.bias": "model-00067-of-00067.safetensors", "model.layers.9.self_attn.v_proj.weight": "model-00067-of-00067.safetensors", "model.norm.weight": "model-00067-of-00067.safetensors"}}

special_tokens_map.json

@@ -0,0 +1,20 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "eos_token": {
+    "content": "<|im_end|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|endoftext|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>"
+  ],
+  "bos_token": null,
+  "chat_template": "{% if not add_generation_prompt is defined %}{% set add_generation_prompt = false %}{% endif %}{% for message in messages %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}