Upload folder using huggingface_hub

README.md

@@ -0,0 +1,61 @@
+---
+license: other
+license_name: deepseek
+license_link: LICENSE
+datasets:
+- unalignment/spicy-3.1
+---
+
+<p align="center">
+<img width="500px" alt="DeepSeek Chat" src="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/logo.png?raw=true">
+</p>
+<p align="center"><a href="https://www.deepseek.com/">[🏠Homepage]</a>  |  <a href="https://chat.deepseek.com/">[🤖 Chat with DeepSeek LLM]</a>  |  <a href="https://discord.gg/Tc7c45Zzu5">[Discord]</a>  |  <a href="https://github.com/deepseek-ai/DeepSeek-LLM/blob/main/images/qr.jpeg">[Wechat(微信)]</a> </p>
+<hr>
+
+# Fine-tune of Deepseek 67B
+
+Fine-tuned with jondurbin's unalignment/spicy-3.1 for 1 epoch.
+
+
+### 1. Introduction of Deepseek LLM
+
+Introducing DeepSeek LLM, an advanced language model comprising 67 billion parameters. It has been trained from scratch on a vast dataset of 2 trillion tokens in both English and Chinese. In order to foster research, we have made DeepSeek LLM 7B/67B Base and DeepSeek LLM 7B/67B Chat open source for the research community.
+
+  
+### 2. Model Summary
+`deepseek-llm-67b-base` is a 67B parameter model with Grouped-Query Attention trained on 2 trillion tokens from scratch.
+- **Home Page:** [DeepSeek](https://deepseek.com/)
+- **Repository:** [deepseek-ai/deepseek-LLM](https://github.com/deepseek-ai/deepseek-LLM)
+- **Chat With DeepSeek LLM:** [DeepSeek-LLM](https://chat.deepseek.com/)
+
+
+### 3. How to Use
+Here give some examples of how to use our model.
+#### Text Completion
+```python
+import torch
+from transformers import AutoTokenizer, AutoModelForCausalLM, GenerationConfig
+
+model_name = "deepseek-ai/deepseek-llm-67b-base"
+tokenizer = AutoTokenizer.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
+model.generation_config = GenerationConfig.from_pretrained(model_name)
+model.generation_config.pad_token_id = model.generation_config.eos_token_id
+
+text = "An attention function can be described as mapping a query and a set of key-value pairs to an output, where the query, keys, values, and output are all vectors. The output is"
+inputs = tokenizer(text, return_tensors="pt")
+outputs = model.generate(**inputs.to(model.device), max_new_tokens=100)
+
+result = tokenizer.decode(outputs[0], skip_special_tokens=True)
+print(result)
+```
+
+### 4. License
+This code repository is licensed under the MIT License. The use of DeepSeek LLM models is subject to the Model License. DeepSeek LLM supports commercial use.
+
+See the [LICENSE-MODEL](https://github.com/deepseek-ai/deepseek-LLM/blob/main/LICENSE-MODEL) for more details.
+
+### 5. Contact
+
+If you have any questions, please raise an issue or contact us at [service@deepseek.com](mailto:service@deepseek.com).
+

config.json

@@ -0,0 +1,27 @@
+{
+  "_name_or_path": "/aiml/models/deepseek-llm-67b-base",
+  "architectures": [
+    "LlamaForCausalLM"
+  ],
+  "attention_bias": false,
+  "bos_token_id": 1,
+  "eos_token_id": 2,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 22016,
+  "max_position_embeddings": 4096,
+  "model_type": "llama",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 95,
+  "num_key_value_heads": 8,
+  "pretraining_tp": 1,
+  "rms_norm_eps": 1e-06,
+  "rope_scaling": null,
+  "rope_theta": 10000.0,
+  "tie_word_embeddings": false,
+  "torch_dtype": "float16",
+  "transformers_version": "4.34.1",
+  "use_cache": true,
+  "vocab_size": 102400
+}

generation_config.json

@@ -0,0 +1,6 @@
+{
+  "_from_model_config": true,
+  "bos_token_id": 100000,
+  "eos_token_id": 100001,
+  "transformers_version": "4.34.1"
+}

output-00001-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:3373f7237423c80a73d7e65556c4ffcf99514edff62a43fb2ce2965d721a1785
+size 8540546576

output-00002-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:5682b6c374b0cbe5171bc47842d9db9ac6c692746acf29bb4baebc3a3243c17e
+size 8521833360

output-00003-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:2e146c50933637b923cd0a2aa6f586eb8440043d2acc65d44a3f7a8c42dbc511
+size 8583209592

output-00004-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:15a0b54fd42c5e79a23c8299f8b4d2f51120d0d455ea39be839c57b767b39d8c
+size 8579707904

output-00005-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:6fbfb9f74a5bcd604e72e18e16bfadaad6ce0e863926ea947483ab0de31bfff3
+size 8586445192

output-00006-of-00006.safetensors

@@ -0,0 +1,3 @@
+version https://git-lfs.github.com/spec/v1
+oid sha256:52a300ffecd16dd9ff32bf6e1d08024777aad65afd7f0f0a557b35746fa28e82
+size 661094496

pytorch_model.bin.index.json

@@ -0,0 +1,865 @@
+{
+  "metadata": {
+    "total_size": 134850002944
+  },
+  "weight_map": {
+    "lm_head.weight": "pytorch_model-00014-of-00014.bin",
+    "model.embed_tokens.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.0.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.1.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.10.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.10.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.11.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.12.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.13.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.13.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.13.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.13.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.13.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.13.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.13.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.13.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.13.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.14.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.14.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.15.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.16.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.17.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.18.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.input_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.mlp.down_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.mlp.gate_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.mlp.up_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.post_attention_layernorm.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.19.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.2.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.2.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.20.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.20.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.20.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.20.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.20.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.20.self_attn.k_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.20.self_attn.o_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.20.self_attn.q_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.20.self_attn.v_proj.weight": "pytorch_model-00003-of-00014.bin",
+    "model.layers.21.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.21.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.22.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.23.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.24.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.25.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.input_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.mlp.down_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.mlp.gate_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.mlp.up_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.post_attention_layernorm.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.26.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.27.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.27.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.27.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.27.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.27.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.27.self_attn.k_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.27.self_attn.o_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.27.self_attn.q_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.27.self_attn.v_proj.weight": "pytorch_model-00004-of-00014.bin",
+    "model.layers.28.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.28.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.29.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.3.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.3.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.30.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.30.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.31.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.32.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.input_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.mlp.down_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.mlp.gate_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.mlp.up_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.post_attention_layernorm.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.33.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.34.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.34.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.34.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.34.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.34.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.34.self_attn.k_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.34.self_attn.o_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.34.self_attn.q_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.34.self_attn.v_proj.weight": "pytorch_model-00005-of-00014.bin",
+    "model.layers.35.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.35.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.36.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.37.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.38.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.39.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.4.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.4.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.40.input_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.mlp.down_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.mlp.gate_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.mlp.up_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.post_attention_layernorm.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.40.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.41.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.41.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.41.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.41.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.41.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.41.self_attn.k_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.41.self_attn.o_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.41.self_attn.q_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.41.self_attn.v_proj.weight": "pytorch_model-00006-of-00014.bin",
+    "model.layers.42.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.42.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.43.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.44.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.45.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.46.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.input_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.mlp.down_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.mlp.gate_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.mlp.up_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.post_attention_layernorm.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.47.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.48.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.48.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.48.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.48.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.48.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.48.self_attn.k_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.48.self_attn.o_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.48.self_attn.q_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.48.self_attn.v_proj.weight": "pytorch_model-00007-of-00014.bin",
+    "model.layers.49.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.49.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.5.input_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.mlp.down_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.mlp.gate_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.mlp.up_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.post_attention_layernorm.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.self_attn.k_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.self_attn.o_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.self_attn.q_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.5.self_attn.v_proj.weight": "pytorch_model-00001-of-00014.bin",
+    "model.layers.50.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.50.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.51.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.52.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.53.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.input_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.mlp.down_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.mlp.gate_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.mlp.up_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.post_attention_layernorm.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.54.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.55.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.55.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.55.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.55.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.55.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.55.self_attn.k_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.55.self_attn.o_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.55.self_attn.q_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.55.self_attn.v_proj.weight": "pytorch_model-00008-of-00014.bin",
+    "model.layers.56.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.56.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.57.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.58.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.59.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.6.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.6.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.60.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.60.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.input_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.mlp.down_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.mlp.gate_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.mlp.up_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.post_attention_layernorm.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.61.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.62.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.62.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.62.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.62.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.62.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.62.self_attn.k_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.62.self_attn.o_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.62.self_attn.q_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.62.self_attn.v_proj.weight": "pytorch_model-00009-of-00014.bin",
+    "model.layers.63.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.63.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.64.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.65.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.66.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.67.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.input_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.mlp.down_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.mlp.gate_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.mlp.up_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.post_attention_layernorm.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.68.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.69.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.69.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.69.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.69.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.69.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.69.self_attn.k_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.69.self_attn.o_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.69.self_attn.q_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.69.self_attn.v_proj.weight": "pytorch_model-00010-of-00014.bin",
+    "model.layers.7.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.7.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.70.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.70.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.71.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.72.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.73.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.74.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.input_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.mlp.down_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.mlp.gate_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.mlp.up_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.post_attention_layernorm.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.75.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.76.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.76.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.76.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.76.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.76.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.76.self_attn.k_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.76.self_attn.o_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.76.self_attn.q_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.76.self_attn.v_proj.weight": "pytorch_model-00011-of-00014.bin",
+    "model.layers.77.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.77.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.78.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.79.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.8.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.8.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.80.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.80.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.81.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.input_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.mlp.down_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.mlp.gate_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.mlp.up_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.post_attention_layernorm.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.82.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.83.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.83.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.83.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.83.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.83.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.83.self_attn.k_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.83.self_attn.o_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.83.self_attn.q_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.83.self_attn.v_proj.weight": "pytorch_model-00012-of-00014.bin",
+    "model.layers.84.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.84.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.85.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.86.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.87.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.88.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.input_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.mlp.down_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.mlp.gate_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.mlp.up_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.post_attention_layernorm.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.89.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.9.input_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.mlp.down_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.mlp.gate_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.mlp.up_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.post_attention_layernorm.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.self_attn.k_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.self_attn.o_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.self_attn.q_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.9.self_attn.v_proj.weight": "pytorch_model-00002-of-00014.bin",
+    "model.layers.90.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.90.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.90.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.90.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.90.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.90.self_attn.k_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.90.self_attn.o_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.90.self_attn.q_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.90.self_attn.v_proj.weight": "pytorch_model-00013-of-00014.bin",
+    "model.layers.91.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.91.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.92.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.93.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.input_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.mlp.down_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.mlp.gate_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.mlp.up_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.post_attention_layernorm.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.self_attn.k_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.self_attn.o_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.self_attn.q_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.layers.94.self_attn.v_proj.weight": "pytorch_model-00014-of-00014.bin",
+    "model.norm.weight": "pytorch_model-00014-of-00014.bin"
+  }
+}

special_tokens_map.json

@@ -0,0 +1,23 @@
+{
+  "bos_token": {
+    "content": "<｜begin▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "eos_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  },
+  "pad_token": {
+    "content": "<｜end▁of▁sentence｜>",
+    "lstrip": false,
+    "normalized": true,
+    "rstrip": false,
+    "single_word": false
+  }
+}

tokenizer_config.json

@@ -0,0 +1,134 @@
+{
+  "added_tokens_decoder": {
+    "100000": {
+      "content": "<｜begin▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100001": {
+      "content": "<｜end▁of▁sentence｜>",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "100002": {
+      "content": "ø",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100003": {
+      "content": "ö",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100004": {
+      "content": "ú",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100005": {
+      "content": "ÿ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100006": {
+      "content": "õ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100007": {
+      "content": "÷",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100008": {
+      "content": "û",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100009": {
+      "content": "ý",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100010": {
+      "content": "À",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100011": {
+      "content": "ù",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100012": {
+      "content": "Á",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100013": {
+      "content": "þ",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    },
+    "100014": {
+      "content": "ü",
+      "lstrip": false,
+      "normalized": true,
+      "rstrip": false,
+      "single_word": false,
+      "special": false
+    }
+  },
+  "bos_token": "<｜begin▁of▁sentence｜>",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<｜end▁of▁sentence｜>",
+  "legacy": true,
+  "model_max_length": 4096,
+  "pad_token": "<｜end▁of▁sentence｜>",
+  "sp_model_kwargs": {},
+  "tokenizer_class": "LlamaTokenizer",
+  "unk_token": null,
+  "use_default_system_prompt": true
+}