初始化项目，由ModelHub XC社区提供模型

Model: abhishekchohan/SOLAR-10.7B-Instruct-Forest-DPO-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 +1,47 @@
+---
+license: apache-2.0
+datasets:
+- Intel/orca_dpo_pairs
+- nvidia/HelpSteer
+- jondurbin/truthy-dpo-v0.1
+language:
+- en
+library_name: transformers
+pipeline_tag: text-generation
+---
+
+### SOLAR-10.7B-Instruct-Forest-DPO
+Introducing SOLAR-10.7B-Instruct-Forest-DPO, a LLM fine-tuned with base model upstage/SOLAR-10.7B-Instruct-v1.0, using direct preference optimization.
+This model showcases exceptional prowess across a spectrum of natural language processing (NLP) tasks. 
+
+A mixture of the following datasets was used for fine-tuning.
+
+1. Intel/orca_dpo_pairs
+2. nvidia/HelpSteer
+3. jondurbin/truthy-dpo-v0.1
+
+
+💻 Usage
+
+```python
+!pip install -qU transformers bitsandbytes accelerate
+
+from transformers import AutoTokenizer
+import transformers
+import torch
+
+model = "abhishekchohan/SOLAR-10.7B-Instruct-Forest-DPO"
+
+tokenizer = AutoTokenizer.from_pretrained(model)
+pipeline = transformers.pipeline(
+    "text-generation",
+    model=model,
+    model_kwargs={"torch_dtype": torch.float16, "load_in_4bit": True},
+)
+
+messages = [{"role": "user", "content": "Explain what a Mixture of Experts is in less than 100 words."}]
+prompt = pipeline.tokenizer.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
+outputs = pipeline(prompt, max_new_tokens=256, do_sample=True, temperature=0.7, top_k=50, top_p=0.95)
+print(outputs[0]["generated_text"])
+
+```

config.json

@@ -0,0 +1,29 @@
+{
+  "_name_or_path": "models/upstage/SOLAR-10.7B-Instruct-v1.0-dpo/model",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "attention_dropout": 0.0,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 4096,
+  "initializer_range": 0.02,
+  "intermediate_size": 14336,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 32,
+  "num_hidden_layers": 48,
+  "num_key_value_heads": 8,
+  "pad_token_id": 2,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float32",
+  "transformers_version": "4.37.0",
+  "use_cache": true,
+  "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,8 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 2,
+  "transformers_version": "4.37.0",
+  "use_cache": false
+}

pytorch_model-00001-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:76d801cee90e951cc1d6379d4e4288cabfa2e8e2c9aa0816056232e3752a0f5d
+size 4987208876

pytorch_model-00002-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2bd6e1033410e18d01b05c3798252beb62d84b43f960064baa969f15d343bae0
+size 4899128178

pytorch_model-00003-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:0344b6c6f7f34779f7d0a1073262ee3afcfbf9156f2c014603255beeb1859248
+size 4999826024

pytorch_model-00004-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:edd2356e09b8cdf3992e80870ce548b3568ed35ede5d14f71e19c5e42de8ffaa
+size 4999826084

pytorch_model-00005-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:68c08f38540c038aad45fd371f529619ebeae80b781831ef64e4b36b4412b667
+size 4832019028

pytorch_model-00006-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9b5f5eff94fd87204c4a632fbd9a1bdeb8c53479a0999d4b4dde54cee447b251
+size 4999826024

pytorch_model-00007-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:fdf1f4d1e729477aa83822579cebccd271e74ad57ba8cc6fd491331f0d2416aa
+size 4999826084

pytorch_model-00008-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:924e510d5b6a6563de6b03f39f8d5ee73802d579310bc8a6c24596ce76d4f404
+size 4832019028

pytorch_model-00009-of-00009.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:91d07d68ddf8abfdbc08b45d680fe64a10d8c5c6cebe6a126f6b67f825312f48
+size 3376573674

pytorch_model.bin.index.json

@@ -0,0 +1,442 @@
+{
+  "metadata": {
+    "total_size": 42926096384
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00009-of-00009.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00009.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00009.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00009.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00009.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00009.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00009.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00009.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00009.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00009.bin",
+    "model.norm.weight": "pytorch_model-00009-of-00009.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,24 @@
+{
+  "bos_token": {
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": "</s>",
+  "unk_token": {
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,43 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "added_tokens_decoder": {
+    "0": {
+      "content": "<unk>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "1": {
+      "content": "<s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "2": {
+      "content": "</s>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": [],
+  "bos_token": "<s>",
+  "chat_template": "{% for message in messages %}{% if message['role'] == 'system' %}{% if message['content']%}{{'### System:\n' + message['content']+'\n\n'}}{% endif %}{% elif message['role'] == 'user' %}{{'### User:\n' + message['content']+'\n\n'}}{% elif message['role'] == 'assistant' %}{{'### Assistant:\n'  + message['content']}}{% endif %}{% if loop.last and add_generation_prompt %}{{ '### Assistant:\n' }}{% endif %}{% endfor %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "</s>",
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": "</s>",
+  "sp_model_kwargs": {},
+  "spaces_between_special_tokens": false,
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": "<unk>",
+  "use_default_system_prompt": true
+}