初始化项目，由ModelHub XC社区提供模型

Model: 922-CA/Llama-3-natsuki-ddlc-8b-v1
Source: Original Platform

.gitattributes

@@ -0,0 +1,35 @@
+*.7z filter=lfs diff=lfs merge=lfs -text
+*.arrow filter=lfs diff=lfs merge=lfs -text
+*.bin filter=lfs diff=lfs merge=lfs -text
+*.bz2 filter=lfs diff=lfs merge=lfs -text
+*.ckpt filter=lfs diff=lfs merge=lfs -text
+*.ftz filter=lfs diff=lfs merge=lfs -text
+*.gz filter=lfs diff=lfs merge=lfs -text
+*.h5 filter=lfs diff=lfs merge=lfs -text
+*.joblib filter=lfs diff=lfs merge=lfs -text
+*.lfs.* filter=lfs diff=lfs merge=lfs -text
+*.mlmodel filter=lfs diff=lfs merge=lfs -text
+*.model filter=lfs diff=lfs merge=lfs -text
+*.msgpack filter=lfs diff=lfs merge=lfs -text
+*.npy filter=lfs diff=lfs merge=lfs -text
+*.npz filter=lfs diff=lfs merge=lfs -text
+*.onnx filter=lfs diff=lfs merge=lfs -text
+*.ot filter=lfs diff=lfs merge=lfs -text
+*.parquet filter=lfs diff=lfs merge=lfs -text
+*.pb filter=lfs diff=lfs merge=lfs -text
+*.pickle filter=lfs diff=lfs merge=lfs -text
+*.pkl filter=lfs diff=lfs merge=lfs -text
+*.pt filter=lfs diff=lfs merge=lfs -text
+*.pth filter=lfs diff=lfs merge=lfs -text
+*.rar filter=lfs diff=lfs merge=lfs -text
+*.safetensors filter=lfs diff=lfs merge=lfs -text
+saved_model/**/* filter=lfs diff=lfs merge=lfs -text
+*.tar.* filter=lfs diff=lfs merge=lfs -text
+*.tar filter=lfs diff=lfs merge=lfs -text
+*.tflite filter=lfs diff=lfs merge=lfs -text
+*.tgz filter=lfs diff=lfs merge=lfs -text
+*.wasm filter=lfs diff=lfs merge=lfs -text
+*.xz 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

README.md

@@ -0,0 +1,164 @@
+---
+language:
+- en
+license: llama3
+tags:
+- text-generation-inference
+- transformers
+- unsloth
+- llama
+- trl
+base_model: unsloth/llama-3-8b-bnb-4bit
+model-index:
+- name: Llama-3-natsuki-ddlc-8b-v1
+  results:
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: AI2 Reasoning Challenge (25-Shot)
+      type: ai2_arc
+      config: ARC-Challenge
+      split: test
+      args:
+        num_few_shot: 25
+    metrics:
+    - type: acc_norm
+      value: 60.32
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/Llama-3-natsuki-ddlc-8b-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: HellaSwag (10-Shot)
+      type: hellaswag
+      split: validation
+      args:
+        num_few_shot: 10
+    metrics:
+    - type: acc_norm
+      value: 80.99
+      name: normalized accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/Llama-3-natsuki-ddlc-8b-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: MMLU (5-Shot)
+      type: cais/mmlu
+      config: all
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 64.75
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/Llama-3-natsuki-ddlc-8b-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: TruthfulQA (0-shot)
+      type: truthful_qa
+      config: multiple_choice
+      split: validation
+      args:
+        num_few_shot: 0
+    metrics:
+    - type: mc2
+      value: 45.41
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/Llama-3-natsuki-ddlc-8b-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: Winogrande (5-shot)
+      type: winogrande
+      config: winogrande_xl
+      split: validation
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 78.77
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/Llama-3-natsuki-ddlc-8b-v1
+      name: Open LLM Leaderboard
+  - task:
+      type: text-generation
+      name: Text Generation
+    dataset:
+      name: GSM8k (5-shot)
+      type: gsm8k
+      config: main
+      split: test
+      args:
+        num_few_shot: 5
+    metrics:
+    - type: acc
+      value: 41.85
+      name: accuracy
+    source:
+      url: >-
+        https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard?query=922-CA/Llama-3-natsuki-ddlc-8b-v1
+      name: Open LLM Leaderboard
+datasets:
+- 922-CA/NaChA_v1
+---
+
+# Llama-3-Natsuki-DDLC-8b-v1
+* Model fine-tuned for Natsuki character from DDLC
+* Base: [LLaMA-3](https://huggingface.co/meta-llama/Meta-Llama-3-8B)
+* [GGUFs](https://huggingface.co/922-CA/Llama-3-natsuki-ddlc-8b-v1-gguf)
+
+### USAGE
+For best results: replace "Human" and "Assistant" with "Player" and "Natsuki" like so:
+
+\nPlayer: (prompt)\nNatsuki:
+
+### HYPERPARAMS
+* Trained for 1 epoch
+* rank: 32
+* lora alpha: 32
+* lora dropout: 0
+* lr: 2e-4
+* batch size: 2
+* grad steps: 4
+
+This llama model was trained 2x faster with [Unsloth](https://github.com/unslothai/unsloth) and Huggingface's TRL library.
+
+[<img src="https://raw.githubusercontent.com/unslothai/unsloth/main/images/unsloth%20made%20with%20love.png" width="200"/>](https://github.com/unslothai/unsloth)
+
+### WARNINGS AND DISCLAIMERS
+This model is meant to closely reflect the characteristics of Natsuki. Despite this, there is always the chance that "Natsuki" will hallucinate and get information about herself wrong or act out of character.
+
+Finally, this model is not guaranteed to output aligned or safe outputs, use at your own risk.
+
+# [Open LLM Leaderboard Evaluation Results](https://huggingface.co/spaces/HuggingFaceH4/open_llm_leaderboard)
+Detailed results can be found [here](https://huggingface.co/datasets/open-llm-leaderboard/details_922-CA__Llama-3-natsuki-ddlc-8b-v1)
+
+|             Metric              |Value|
+|---------------------------------|----:|
+|Avg.                             |62.02|
+|AI2 Reasoning Challenge (25-Shot)|60.32|
+|HellaSwag (10-Shot)              |80.99|
+|MMLU (5-Shot)                    |64.75|
+|TruthfulQA (0-shot)              |45.41|
+|Winogrande (5-shot)              |78.77|
+|GSM8k (5-shot)                   |41.85|

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "unsloth/llama-3-8b-bnb-4bit",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 128000,
+  "eos_token_id": 128001,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 8192,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 32,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 500000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.40.2",
+  "unsloth_version": "2024.5",
+  "use_cache": true,
+  "vocab_size": 128256
+}

generation_config.json

@@ -0,0 +1,9 @@
+{
+  "bos_token_id": 128000,
+  "do_sample": true,
+  "eos_token_id": 128001,
+  "max_length": 4096,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.40.2"
+}

model-00001-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2d2b6584a67ebd3fdbbabd15608717b3ee606c0440c0c6a99d9271e840764ca6
+size 4976698592

model-00002-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c8986700d6ed792fee4c5f6510a4e2185f741ae47f53445f00ce13b5d7ef99e4
+size 4999802616

model-00003-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:77c37705e07997af1ff109e80a5dc4ede92277f489bd4a2ecd0cef87f6ddf815
+size 4915916080

model-00004-of-00004.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0ded9266618f30f8f58fdf0530d4a5a1347be33b538ce47f54eb9be74d5ba6b4
+size 1168138808

model.safetensors.index.json

@@ -0,0 +1,298 @@
+{
+    "metadata": {
+        "total_size": 16060522496
+    },
+    "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-00002-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-00002-of-00004.safetensors",
+        "model.layers.10.self_attn.v_proj.weight": "model-00002-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-00003-of-00004.safetensors",
+        "model.layers.20.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.20.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.20.post_attention_layernorm.weight": "model-00003-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-00003-of-00004.safetensors",
+        "model.layers.21.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.21.self_attn.v_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.input_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.down_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.gate_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.mlp.up_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.post_attention_layernorm.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.k_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.o_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.q_proj.weight": "model-00003-of-00004.safetensors",
+        "model.layers.22.self_attn.v_proj.weight": "model-00003-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-00003-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-00004-of-00004.safetensors",
+        "model.layers.31.mlp.down_proj.weight": "model-00004-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-00004-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.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-00002-of-00004.safetensors",
+        "model.layers.9.mlp.down_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.gate_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.mlp.up_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.post_attention_layernorm.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.k_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.o_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.q_proj.weight": "model-00002-of-00004.safetensors",
+        "model.layers.9.self_attn.v_proj.weight": "model-00002-of-00004.safetensors",
+        "model.norm.weight": "model-00004-of-00004.safetensors"
+    }
+}

pytorch_model-00001-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8691aa3da0a98d501824bfd9b75c9ce7427c1af0037c907e05d2eb2174af5125
+size 4976718466

pytorch_model-00002-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c30a2d33de1da4c989847516e075cba03d0eeee6ce74d4357b84fd0c7fc87ab8
+size 4999827014

pytorch_model-00003-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:8b5f8ce201ac82213d8cae51822f5f7fe8bd9ac47eb2895ab0914b9285691752
+size 4915939082

pytorch_model-00004-of-00004.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:a4e541ef23048d2998c18a75696f20bf05a1f13b65571f966590317ac0da0959
+size 1168140873

pytorch_model.bin.index.json

@@ -0,0 +1,298 @@
+{
+  "metadata": {
+    "total_size": 16060522496
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00004-of-00004.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00004-of-00004.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00003-of-00004.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00001-of-00004.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00004.bin",
+    "model.norm.weight": "pytorch_model-00004-of-00004.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<|begin_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<|end_of_text|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<|reserved_special_token_250|>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}