初始化项目，由ModelHub XC社区提供模型

Model: OpenLemur/lemur-70b-chat-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 +1,85 @@
+---
+pipeline_tag: text-generation
+inference: true
+widget:
+- text: "What's lemur's favorite fruit?"
+  example_title: Lemur favorite fruit
+  group: Python
+- text: 'Write a Python function to merge two sorted lists into one sorted list without using any built-in sort functions.'
+  example_title: Merge Sort
+  group: Python
+license: cc-by-nc-4.0
+library_name: transformers
+tags:
+- text-generation
+- code
+- text-generation-inference
+language:
+- en
+---
+
+# lemur-70b-chat-v1
+
+<p align="center">
+  <img src="https://huggingface.co/datasets/OpenLemur/assets/resolve/main/lemur_icon.png" width="300" height="300" alt="Lemur">
+</p>
+
+<div align="center">
+  <img src="https://huggingface.co/datasets/OpenLemur/assets/resolve/main/lemur_chat_radar.png">
+</div>
+
+📄Paper: https://arxiv.org/abs/2310.06830
+
+👩‍💻Code: https://github.com/OpenLemur/Lemur
+
+
+## Use
+
+### Setup
+
+First, we have to install all the libraries listed in `requirements.txt` in [GitHub](https://github.com/OpenLemur/lemur-v1):
+
+```bash
+pip install -r requirements.txt
+```
+
+### Generation
+
+```python
+from transformers import AutoTokenizer, AutoModelForCausalLM
+
+tokenizer = AutoTokenizer.from_pretrained("OpenLemur/lemur-70b-chat-v1")
+model = AutoModelForCausalLM.from_pretrained("OpenLemur/lemur-70b-chat-v1", device_map="auto", load_in_8bit=True)
+
+# Text Generation Example
+prompt = """<|im_start|>system
+You are a helpful, respectful, and honest assistant.
+<|im_end|>
+<|im_start|>user
+What's a lemur's favorite fruit?<|im_end|>
+<|im_start|>assistant
+"""
+input = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**input, max_length=50, num_return_sequences=1)
+generated_text = tokenizer.decode(output[0], skip_special_tokens=True)
+print(generated_text)
+
+# Code Generation Example
+prompt = """<|im_start|>system
+Below is an instruction that describes a task. Write a response that appropriately completes the request.
+<|im_end|>
+<|im_start|>user
+Write a Python function to merge two sorted lists into one sorted list without using any built-in sort functions.<|im_end|>
+<|im_start|>assistant
+"""
+input = tokenizer(prompt, return_tensors="pt")
+output = model.generate(**input, max_length=200, num_return_sequences=1)
+generated_code = tokenizer.decode(output[0], skip_special_tokens=True)
+print(generated_code)
+```
+
+# License
+The model is licensed under a CC BY-NC-4.0 license focused on research use cases.
+
+# Acknowledgements
+The Lemur project is an open collaborative research effort between [XLang Lab](https://www.xlang.ai/) and Salesforce Research. We thank Salesforce, Google Research and Amazon AWS for their gift support.

added_tokens.json

@@ -0,0 +1,7 @@
+{
+  "<pad>": 32000,
+  "<|diff_marker|>": 32004,
+  "<|im_end|>": 32002,
+  "<|im_sep|>": 32003,
+  "<|im_start|>": 32001
+}

config.json

@@ -0,0 +1,26 @@
+{
+  "_name_or_path": "OpenLemur/lemur-70b-chat-v1",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 28672,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "pad_token_id": 0,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-05,
+  "rope_scaling": null,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.32.0.dev0",
+  "use_cache": true,
+  "vocab_size": 32005
+}

generation_config.json

@@ -0,0 +1,10 @@
+{
+  "bos_token_id": 1,
+  "do_sample": true,
+  "eos_token_id": 2,
+  "max_length": 4096,
+  "pad_token_id": 0,
+  "temperature": 0.6,
+  "top_p": 0.9,
+  "transformers_version": "4.32.0.dev0"
+}

pytorch_model-00001-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5da746b246c50cc44d670f317ef04d857bcd2c2c1edd09a2cbab5b6ac3e867c6
+size 9852683237

pytorch_model-00002-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:426ce9dd3092ae4f9d0c9e31f21358c2d539ff7b193a34fc9301ad37359344ae
+size 9798108893

pytorch_model-00003-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:f3a25704f915f131d0d75bb1cc43c21a8ce481b188018cf62597b083ada7f956
+size 9965880015

pytorch_model-00004-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:aae4b585293f89072437150da91b1149f0b653aedd7760eef92738a710108828
+size 9798075365

pytorch_model-00005-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:b9770849b53396f2760db04d90c652305c1f9c1386997430c085f61297c2ce17
+size 9798108809

pytorch_model-00006-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:d7b716b2ce7713f23f27b6574331bc0627d0fb1f29dc57cb235b159add7d98a3
+size 9798108893

pytorch_model-00007-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:61c46b69a1e159eb8dd6e84024e7c434bf1d2dd55a5cbb08a201b678ab4af52a
+size 9965880015

pytorch_model-00008-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:667e1faf035ce5611900af95298cd2f9cdf5348a37803a25cd14efc20510ecbb
+size 9798075365

pytorch_model-00009-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c66188a93dc2eef5677f72ea8b46e05279e43c37d92118bc6e4636cec51792e3
+size 9798108809

pytorch_model-00010-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6b1f4a496dc0e635214e1827d25f1a8cb685ded39b7945bd70d3ea16188dae3a
+size 9798108893

pytorch_model-00011-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:ead2b94f29a46ce0902261638721bb2bf72bc92c9b196c49279050f6230fdc68
+size 9965880015

pytorch_model-00012-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:444bb1fd8052bea6dd781589d27a1b689649d2116a7f0415739e92f75b4f6087
+size 9798075365

pytorch_model-00013-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3ad189f7bc055726134a75fe156bdc4b9c2601d258ad70afaa391ec95b7d0521
+size 9798108809

pytorch_model-00014-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:c21d04125b606d1f05c53dd0617e2db7496f12e8c65e21ba5365bac7c18724a7
+size 9496134339

pytorch_model-00015-of-00015.bin

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:25e10b9c23f6fa490124aef853019af5fd59fda447d02225043c4ced8fa9b108
+size 524370858

pytorch_model.bin.index.json

@@ -0,0 +1,730 @@
+{
+  "metadata": {
+    "total_size": 137953460224
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00015-of-00015.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00015.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00015.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00015.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00006-of-00015.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00007-of-00015.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00008-of-00015.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00015.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00009-of-00015.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00010-of-00015.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00011-of-00015.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00012-of-00015.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00013-of-00015.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00014-of-00015.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00015.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00015.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,12 @@
+{
+  "additional_special_tokens": [
+    "<|im_start|>",
+    "<|im_end|>",
+    "<|im_sep|>",
+    "<|diff_marker|>"
+  ],
+  "bos_token": "<s>",
+  "eos_token": "</s>",
+  "pad_token": "<pad>",
+  "unk_token": "<unk>"
+}

tokenizer_config.json

@@ -0,0 +1,35 @@
+{
+  "add_bos_token": true,
+  "add_eos_token": false,
+  "bos_token": {
+    "__type": "AddedToken",
+    "content": "<s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "clean_up_tokenization_spaces": false,
+  "eos_token": {
+    "__type": "AddedToken",
+    "content": "</s>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  },
+  "legacy": true,
+  "model_max_length": 1000000000000000019884624838656,
+  "pad_token": null,
+  "padding_side": "right",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": {
+    "__type": "AddedToken",
+    "content": "<unk>",
+    "lstrip": false,
+    "normalized": false,
+    "rstrip": false,
+    "single_word": false
+  }
+}