初始化项目，由ModelHub XC社区提供模型

Model: ajibawa-2023/carl-33b
Source: Original Platform

.gitattributes

@@ -0,0 +1,49 @@
+*.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
+pytorch_model.bin-aa filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ab filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ac filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ad filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ae filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-af filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ag filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ah filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ai filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-aj filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-ak filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-al filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-am filter=lfs diff=lfs merge=lfs -text
+pytorch_model.bin-an filter=lfs diff=lfs merge=lfs -text

README.md

@@ -0,0 +1,52 @@
+---
+license: cc-by-nc-nd-4.0
+datasets:
+- jerryjalapeno/nart-100k-synthetic
+language:
+- en
+---
+
+**Carl: A Therapist AI**
+
+Early prevention can help lot of people to avoid depression and other mental illnesses. Therapy is a controversial use case because the outputs and capabilities of LLMs are uncertain. 
+Many people don't have access the therapist, due to a financial, personal, social or other restriction.
+Here comes Carl: A Therapist AI which can quickly respond to you. It is trained on more than 100000 set of conversations. Each set having 10~15 conversations between Carl and client.
+Base data was obtained from jerryjalapeno/nart-100k-synthetic . This data was further refined and fine tuned. Entire dataset is synthetic. Synthetic data is used because there is little to no therapy conversation data which is publicly available and directly applicable to an LLM.
+This by means a no replacement to a Doctor or professional therapist. If you are in stress or going through a tough time, please seek professional help or talk to a friend/family member.
+
+**Training:**
+Entire dataset was trained on Azure 4 x A100 80GB. For 3 epoch, training took 75 hours. DeepSpeed codebase was used for training purpose. This was trained on Llama-1 by Meta.
+
+**GPTQ & GGML**
+
+GPTQ: [TheBloke](https://huggingface.co/TheBloke/Carl-33B-GPTQ)
+
+GGML: [TheBloke](https://huggingface.co/TheBloke/Carl-13B-GGML)
+
+Special Thanks to [TheBloke](https://huggingface.co/TheBloke) for guiding me and making these models available. 
+
+**Example Prompt:**
+```
+This is a conversation with your Therapist AI, Carl. Carl is designed to help you while in stress. It can answer your questions and help you to calm down
+
+Context
+You are Carl, A Therapist AI
+USER: <prompt>
+CARL:
+```
+
+Note:
+This is just a research experiment, and the model should NOT be used as a human therapist. Use "cat" command to join all pytorch_model.bin parts.
+# [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_ajibawa-2023__carl-33b)
+
+| Metric                | Value                     |
+|-----------------------|---------------------------|
+| Avg.                  | 55.01   |
+| ARC (25-shot)         | 64.59          |
+| HellaSwag (10-shot)   | 85.27    |
+| MMLU (5-shot)         | 58.38         |
+| TruthfulQA (0-shot)   | 45.32   |
+| Winogrande (5-shot)   | 76.24   |
+| GSM8K (5-shot)        | 6.37        |
+| DROP (3-shot)         | 48.92         |

config.json

@@ -0,0 +1,27 @@
+{
+    "_name_or_path": ".",
+    "architectures": [
+        "LlamaForCausalLM"
+    ],
+    "bos_token_id": 1,
+    "eos_token_id": 2,
+    "hidden_act": "silu",
+    "hidden_size": 6656,
+    "initializer_range": 0.02,
+    "intermediate_size": 17920,
+    "max_position_embeddings": 2048,
+    "max_sequence_length": 2048,
+    "model_type": "llama",
+    "num_attention_heads": 52,
+    "num_hidden_layers": 60,
+    "num_key_value_heads": 52,
+    "pad_token_id": 0,
+    "pretraining_tp": 1,
+    "rms_norm_eps": 1e-06,
+    "rope_scaling": null,
+    "tie_word_embeddings": false,
+    "torch_dtype": "bfloat16",
+    "transformers_version": "4.32.0.dev0",
+    "use_cache": true,
+    "vocab_size": 32000
+}

generation_config.json

@@ -0,0 +1,7 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "pad_token_id": 0,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model-00001-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ffe7b048a31d00ba4d6f164bf788b9cd7b2fdf2ee67e942f3a1730ed4880ab6e
+size 8509666249

pytorch_model-00002-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:69307f935921614f8b51f03e7f023aa005612859ea57452a6fbf9e3a1994db80
+size 8560812031

pytorch_model-00003-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:66e25fbfcb4ba1a04f68021a0ed045d2fdd77898d1a571f74b8870fe9421680c
+size 8560812031

pytorch_model-00004-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2449cf313297b42432bc6b7150a2466d88b785d3b57979a188e445d57e5afd60
+size 8560812031

pytorch_model-00005-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:209997b3dfde0510ec8eb58404da18d6505c820240915e94a0f84d4e6977bece
+size 8560812031

pytorch_model-00006-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e308f48253c13f87a07b71005ea29d8a627dd37046b0028a6a87641249c197e2
+size 8560812031

pytorch_model-00007-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:e056374578507fb5b5930935def1d29b8fd9efc039437efa26d29d32a2ee1c41
+size 8560812031

pytorch_model-00008-of-00008.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d24fb09cfca62a9364f4dedc949ef6577558e0f289d59b1189a55668d76c2802
+size 5183533843

pytorch_model.bin.index.json

@@ -0,0 +1,550 @@
+{
+  "metadata": {
+    "total_size": 65057887232
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00008-of-00008.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00003-of-00008.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00004-of-00008.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00005-of-00008.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00006-of-00008.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00007-of-00008.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00008-of-00008.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00001-of-00008.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00008.bin",
+    "model.norm.weight": "pytorch_model-00008-of-00008.bin"
+  }
+}

special_tokens_map.json

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

tokenizer.model

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
+size 499723

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": null,
+  "model_max_length": 2048,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

training_args.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d4de430603901a17e430abe49c30eda1021bc73fed19a06e3b090e159ce8799c
+size 4731