Upload 10 files

LICENSE

@@ -0,0 +1,53 @@
+Tongyi Qianwen LICENSE AGREEMENT
+
+Tongyi Qianwen Release Date: August 3, 2023
+
+By clicking to agree or by using or distributing any portion or element of the Tongyi Qianwen Materials, you will be deemed to have recognized and accepted the content of this Agreement, which is effective immediately.
+
+1. Definitions
+    a. This Tongyi Qianwen LICENSE AGREEMENT (this "Agreement") shall mean the terms and conditions for use, reproduction, distribution and modification of the Materials as defined by this Agreement.
+    b. "We"(or "Us") shall mean Alibaba Cloud.
+    c. "You" (or "Your") shall mean a natural person or legal entity exercising the rights granted by this Agreement and/or using the Materials for any purpose and in any field of use.
+    d. "Third Parties" shall mean individuals or legal entities that are not under common control with Us or You.
+    e. "Tongyi Qianwen" shall mean the large language models (including Qwen model and Qwen-Chat model), and software and algorithms, consisting of trained model weights, parameters (including optimizer states), machine-learning model code, inference-enabling code, training-enabling code, fine-tuning enabling code and other elements of the foregoing distributed by Us.
+    f. "Materials" shall mean, collectively, Alibaba Cloud's proprietary Tongyi Qianwen and Documentation (and any portion thereof) made available under this Agreement.
+    g. "Source" form shall mean the preferred form for making modifications, including but not limited to model source code, documentation source, and configuration files.
+    h. "Object" form shall mean any form resulting from mechanical transformation or translation of a Source form, including but not limited to compiled object code, generated documentation,
+ and conversions to other media types.
+
+2. Grant of Rights
+You are granted a non-exclusive, worldwide, non-transferable and royalty-free limited license under Alibaba Cloud's intellectual property or other rights owned by Us embodied in the Materials to use, reproduce, distribute, copy, create derivative works of, and make modifications to the Materials.
+
+3. Redistribution
+You may reproduce and distribute copies of the Materials or derivative works thereof in any medium, with or without modifications, and in Source or Object form, provided that You meet the following conditions:
+    a. You shall give any other recipients of the Materials or derivative works a copy of this Agreement;
+    b. You shall cause any modified files to carry prominent notices stating that You changed the files;
+    c. You shall retain in all copies of the Materials that You distribute the following attribution notices within a "Notice" text file distributed as a part of such copies: "Tongyi Qianwen is licensed under the Tongyi Qianwen LICENSE AGREEMENT, Copyright (c) Alibaba Cloud. All Rights Reserved."; and
+    d. You may add Your own copyright statement to Your modifications and may provide additional or different license terms and conditions for use, reproduction, or distribution of Your modifications, or for any such derivative works as a whole, provided Your use, reproduction, and distribution of the work otherwise complies with the terms and conditions of this Agreement.
+
+4. Restrictions
+If you are commercially using the Materials, and your product or service has more than 100 million monthly active users, You shall request a license from Us. You cannot exercise your rights under this Agreement without our express authorization.
+
+5. Rules of use
+    a. The Materials may be subject to export controls or restrictions in China, the United States or other countries or regions. You shall comply with applicable laws and regulations in your use of the Materials.
+    b. You can not use the Materials or any output therefrom to improve any other large language model (excluding Tongyi Qianwen or derivative works thereof).
+
+6. Intellectual Property
+    a. We retain ownership of all intellectual property rights in and to the Materials and derivatives made by or for Us. Conditioned upon compliance with the terms and conditions of this Agreement, with respect to any derivative works and modifications of the Materials that are made by you, you are and will be the owner of such derivative works and modifications.
+    b. No trademark license is granted to use the trade names, trademarks, service marks, or product names of Us, except as required to fulfill notice requirements under this Agreement or as required for reasonable and customary use in describing and redistributing the Materials.
+    c. If you commence a lawsuit or other proceedings (including a cross-claim or counterclaim in a lawsuit) against Us or any entity alleging that the Materials or any output therefrom, or any part of the foregoing, infringe any intellectual property or other right owned or licensable by you, then all licences granted to you under this Agreement shall terminate as of the date such lawsuit or other proceeding is commenced or brought.
+
+7. Disclaimer of Warranty and Limitation of Liability
+
+    a. We are not obligated to support, update, provide training for, or develop any further version of the Tongyi Qianwen Materials or to grant any license thereto.
+    b. THE MATERIALS ARE PROVIDED "AS IS" WITHOUT ANY EXPRESS OR IMPLIED WARRANTY OF ANY KIND INCLUDING WARRANTIES OF MERCHANTABILITY, NONINFRINGEMENT, OR FITNESS FOR A PARTICULAR PURPOSE. WE MAKE NO WARRANTY AND ASSUME NO RESPONSIBILITY FOR THE SAFETY OR STABILITY OF THE MATERIALS AND ANY OUTPUT THEREFROM.
+    c. IN NO EVENT SHALL WE BE LIABLE TO YOU FOR ANY DAMAGES, INCLUDING, BUT NOT LIMITED TO ANY DIRECT, OR INDIRECT, SPECIAL OR CONSEQUENTIAL DAMAGES ARISING FROM YOUR USE OR INABILITY TO USE THE MATERIALS OR ANY OUTPUT OF IT, NO MATTER HOW IT’S CAUSED.
+    d. You will defend, indemnify and hold harmless Us from and against any claim by any third party arising out of or related to your use or distribution of the Materials.
+
+8. Survival and Termination.
+    a. The term of this Agreement shall commence upon your acceptance of this Agreement or access to the Materials and will continue in full force and effect until terminated in accordance with the terms and conditions herein.
+    b. We may terminate this Agreement if you breach any of the terms or conditions of this Agreement. Upon termination of this Agreement, you must delete and cease use of the Materials. Sections 7 and 9 shall survive the termination of this Agreement.
+
+9. Governing Law and Jurisdiction.
+    a. This Agreement and any dispute arising out of or relating to it will be governed by the laws of China, without regard to conflict of law principles, and the UN Convention on Contracts for the International Sale of Goods does not apply to this Agreement.
+    b. The People's Courts in Hangzhou City shall have exclusive jurisdiction over any dispute arising out of this Agreement.

README.md

@@ -1,3 +1,169 @@
----
-license: apache-2.0
----
+---
+license: other
+license_name: tongyi-qianwen
+license_link: https://huggingface.co/Qwen/Qwen2-72B-Instruct/blob/main/LICENSE
+language:
+- en
+pipeline_tag: text-generation
+tags:
+- chat
+---
+
+# Qwen2-72B-Instruct
+
+## Introduction
+
+Qwen2 is the new series of Qwen large language models. For Qwen2, we release a number of base language models and instruction-tuned language models ranging from 0.5 to 72 billion parameters, including a Mixture-of-Experts model. This repo contains the instruction-tuned 72B Qwen2 model.
+
+Compared with the state-of-the-art opensource language models, including the previous released Qwen1.5, Qwen2 has generally surpassed most opensource models and demonstrated competitiveness against proprietary models across a series of benchmarks targeting for language understanding, language generation, multilingual capability, coding, mathematics, reasoning, etc.
+
+Qwen2-72B-Instruct supports a context length of up to 131,072 tokens, enabling the processing of extensive inputs. Please refer to [this section](#processing-long-texts) for detailed instructions on how to deploy Qwen2 for handling long texts.
+
+For more details, please refer to our [blog](https://qwenlm.github.io/blog/qwen2/), [GitHub](https://github.com/QwenLM/Qwen2), and [Documentation](https://qwen.readthedocs.io/en/latest/).
+<br>
+
+## Model Details
+Qwen2 is a language model series including decoder language models of different model sizes. For each size, we release the base language model and the aligned chat model. It is based on the Transformer architecture with SwiGLU activation, attention QKV bias, group query attention, etc. Additionally, we have an improved tokenizer adaptive to multiple natural languages and codes.
+
+## Training details
+We pretrained the models with a large amount of data, and we post-trained the models with both supervised finetuning and direct preference optimization.
+
+
+## Requirements
+The code of Qwen2 has been in the latest Hugging face transformers and we advise you to install `transformers>=4.37.0`, or you might encounter the following error:
+```
+KeyError: 'qwen2'
+```
+
+## Quickstart
+
+Here provides a code snippet with `apply_chat_template` to show you how to load the tokenizer and model and how to generate contents.
+
+```python
+from transformers import AutoModelForCausalLM, AutoTokenizer
+device = "cuda" # the device to load the model onto
+
+model = AutoModelForCausalLM.from_pretrained(
+    "Qwen/Qwen2-72B-Instruct",
+    torch_dtype="auto",
+    device_map="auto"
+)
+tokenizer = AutoTokenizer.from_pretrained("Qwen/Qwen2-72B-Instruct")
+
+prompt = "Give me a short introduction to large language model."
+messages = [
+    {"role": "system", "content": "You are a helpful assistant."},
+    {"role": "user", "content": prompt}
+]
+text = tokenizer.apply_chat_template(
+    messages,
+    tokenize=False,
+    add_generation_prompt=True
+)
+model_inputs = tokenizer([text], return_tensors="pt").to(device)
+
+generated_ids = model.generate(
+    model_inputs.input_ids,
+    max_new_tokens=512
+)
+generated_ids = [
+    output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
+]
+
+response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
+```
+
+### Processing Long Texts
+
+To handle extensive inputs exceeding 32,768 tokens, we utilize [YARN](https://arxiv.org/abs/2309.00071), a technique for enhancing model length extrapolation, ensuring optimal performance on lengthy texts.
+
+For deployment, we recommend using vLLM. You can enable the long-context capabilities by following these steps:
+
+1. **Install vLLM**: You can install vLLM by running the following command.
+
+```bash
+pip install "vllm>=0.4.3"
+```
+
+Or you can install vLLM from [source](https://github.com/vllm-project/vllm/).
+
+2. **Configure Model Settings**: After downloading the model weights, modify the `config.json` file by including the below snippet:
+    ```json
+        {
+            "architectures": [
+                "Qwen2ForCausalLM"
+            ],
+            // ...
+            "vocab_size": 152064,
+
+            // adding the following snippets
+            "rope_scaling": {
+                "factor": 4.0,
+                "original_max_position_embeddings": 32768,
+                "type": "yarn"
+            }
+        }
+    ```
+    This snippet enable YARN to support longer contexts.
+
+3. **Model Deployment**: Utilize vLLM to deploy your model. For instance, you can set up an openAI-like server using the command:
+
+    ```bash
+    python -m vllm.entrypoints.openai.api_server --served-model-name Qwen2-72B-Instruct --model path/to/weights
+    ```
+
+    Then you can access the Chat API by:
+
+    ```bash
+    curl http://localhost:8000/v1/chat/completions \
+        -H "Content-Type: application/json" \
+        -d '{
+        "model": "Qwen2-72B-Instruct",
+        "messages": [
+            {"role": "system", "content": "You are a helpful assistant."},
+            {"role": "user", "content": "Your Long Input Here."}
+        ]
+        }'
+    ```
+
+    For further usage instructions of vLLM, please refer to our [Github](https://github.com/QwenLM/Qwen2).
+
+**Note**: Presently, vLLM only supports static YARN, which means the scaling factor remains constant regardless of input length, **potentially impacting performance on shorter texts**. We advise adding the `rope_scaling` configuration only when processing long contexts is required.
+
+## Evaluation
+
+We briefly compare Qwen2-72B-Instruct with similar-sized instruction-tuned LLMs, including our previous Qwen1.5-72B-Chat. The results are shown as follows:
+
+| Datasets | Llama-3-70B-Instruct | Qwen1.5-72B-Chat | **Qwen2-72B-Instruct** |
+| :--- | :---: | :---: | :---: |
+| _**English**_ |  |  |  |
+| MMLU | 82.0 | 75.6 | **82.3** |
+| MMLU-Pro | 56.2 | 51.7 | **64.4** |
+| GPQA | 41.9 | 39.4 | **42.4** |
+| TheroemQA | 42.5 | 28.8 | **44.4** |
+| MT-Bench | 8.95 | 8.61 | **9.12** |
+| Arena-Hard | 41.1 | 36.1 | **48.1** |
+| IFEval (Prompt Strict-Acc.) | 77.3 | 55.8 | **77.6** |
+| _**Coding**_ |  |  |  |
+| HumanEval | 81.7 | 71.3 | **86.0** |
+| MBPP | **82.3** | 71.9 | 80.2 |
+| MultiPL-E | 63.4 | 48.1 | **69.2** |
+| EvalPlus | 75.2 | 66.9 | **79.0** |
+| LiveCodeBench | 29.3 | 17.9 | **35.7** |
+| _**Mathematics**_ |  |  |  |
+| GSM8K | **93.0** | 82.7 | 91.1 |
+| MATH | 50.4 | 42.5 | **59.7** |
+| _**Chinese**_ |  |  |  |
+| C-Eval | 61.6 | 76.1 | **83.8** |
+| AlignBench | 7.42 | 7.28 | **8.27** |
+
+## Citation
+
+If you find our work helpful, feel free to give us a cite.
+
+```
+@article{qwen2,
+  title={Qwen2 Technical Report},
+  year={2024}
+}
+```

config.json

@@ -0,0 +1,27 @@
+{
+  "architectures": [
+    "Qwen2ForCausalLM"
+  ],
+  "attention_dropout": 0.0,
+  "bos_token_id": 151643,
+  "eos_token_id": 151645,
+  "hidden_act": "silu",
+  "hidden_size": 8192,
+  "initializer_range": 0.02,
+  "intermediate_size": 29568,
+  "max_position_embeddings": 32768,
+  "max_window_layers": 80,
+  "model_type": "qwen2",
+  "num_attention_heads": 64,
+  "num_hidden_layers": 80,
+  "num_key_value_heads": 8,
+  "rms_norm_eps": 1e-06,
+  "rope_theta": 1000000.0,
+  "sliding_window": 131072,
+  "tie_word_embeddings": false,
+  "torch_dtype": "bfloat16",
+  "transformers_version": "4.40.1",
+  "use_cache": true,
+  "use_sliding_window": false,
+  "vocab_size": 152064
+}

generation_config.json

@@ -0,0 +1,14 @@
+{
+  "bos_token_id": 151643,
+  "pad_token_id": 151643,
+  "do_sample": true,
+  "eos_token_id": [
+    151645,
+    151643
+  ],
+  "repetition_penalty": 1.05,
+  "temperature": 0.7,
+  "top_p": 0.8,
+  "top_k": 20,
+  "transformers_version": "4.37.0"
+}

model.safetensors.index.json

@@ -0,0 +1,970 @@
+{
+  "metadata": {
+    "total_size": 145412407296
+  },
+  "weight_map": {
+    "lm_head.weight": "model-00037-of-00037.safetensors",
+    "model.embed_tokens.weight": "model-00001-of-00037.safetensors",
+    "model.layers.0.input_layernorm.weight": "model-00002-of-00037.safetensors",
+    "model.layers.0.mlp.down_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00037.safetensors",
+    "model.layers.0.mlp.up_proj.weight": "model-00001-of-00037.safetensors",
+    "model.layers.0.post_attention_layernorm.weight": "model-00002-of-00037.safetensors",
+    "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00037.safetensors",
+    "model.layers.0.self_attn.k_proj.weight": "model-00001-of-00037.safetensors",
+    "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00037.safetensors",
+    "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00037.safetensors",
+    "model.layers.0.self_attn.q_proj.weight": "model-00001-of-00037.safetensors",
+    "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00037.safetensors",
+    "model.layers.0.self_attn.v_proj.weight": "model-00001-of-00037.safetensors",
+    "model.layers.1.input_layernorm.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.mlp.down_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.mlp.gate_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.mlp.up_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.post_attention_layernorm.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.k_proj.bias": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.k_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.o_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.q_proj.bias": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.q_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.v_proj.bias": "model-00002-of-00037.safetensors",
+    "model.layers.1.self_attn.v_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.10.input_layernorm.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.mlp.down_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.mlp.gate_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.mlp.up_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.post_attention_layernorm.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.k_proj.bias": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.k_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.q_proj.bias": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.q_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.v_proj.bias": "model-00006-of-00037.safetensors",
+    "model.layers.10.self_attn.v_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.input_layernorm.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.mlp.down_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.mlp.gate_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.mlp.up_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.post_attention_layernorm.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.k_proj.bias": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.k_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.o_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.q_proj.bias": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.q_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.v_proj.bias": "model-00006-of-00037.safetensors",
+    "model.layers.11.self_attn.v_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.12.input_layernorm.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.mlp.down_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.mlp.gate_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.mlp.up_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.post_attention_layernorm.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.k_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.k_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.q_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.q_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.v_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.12.self_attn.v_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.input_layernorm.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.mlp.down_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.mlp.gate_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.mlp.up_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.post_attention_layernorm.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.k_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.k_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.o_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.q_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.q_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.v_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.13.self_attn.v_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.14.input_layernorm.weight": "model-00008-of-00037.safetensors",
+    "model.layers.14.mlp.down_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.14.mlp.gate_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.14.mlp.up_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.14.post_attention_layernorm.weight": "model-00008-of-00037.safetensors",
+    "model.layers.14.self_attn.k_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.14.self_attn.k_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.14.self_attn.o_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.14.self_attn.q_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.14.self_attn.q_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.14.self_attn.v_proj.bias": "model-00007-of-00037.safetensors",
+    "model.layers.14.self_attn.v_proj.weight": "model-00007-of-00037.safetensors",
+    "model.layers.15.input_layernorm.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.mlp.down_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.mlp.gate_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.mlp.up_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.post_attention_layernorm.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.k_proj.bias": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.k_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.o_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.q_proj.bias": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.q_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.v_proj.bias": "model-00008-of-00037.safetensors",
+    "model.layers.15.self_attn.v_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.16.input_layernorm.weight": "model-00009-of-00037.safetensors",
+    "model.layers.16.mlp.down_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.16.mlp.gate_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.16.mlp.up_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.16.post_attention_layernorm.weight": "model-00009-of-00037.safetensors",
+    "model.layers.16.self_attn.k_proj.bias": "model-00008-of-00037.safetensors",
+    "model.layers.16.self_attn.k_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.16.self_attn.o_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.16.self_attn.q_proj.bias": "model-00008-of-00037.safetensors",
+    "model.layers.16.self_attn.q_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.16.self_attn.v_proj.bias": "model-00008-of-00037.safetensors",
+    "model.layers.16.self_attn.v_proj.weight": "model-00008-of-00037.safetensors",
+    "model.layers.17.input_layernorm.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.mlp.down_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.mlp.gate_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.mlp.up_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.post_attention_layernorm.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.k_proj.bias": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.k_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.o_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.q_proj.bias": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.q_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.v_proj.bias": "model-00009-of-00037.safetensors",
+    "model.layers.17.self_attn.v_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.18.input_layernorm.weight": "model-00010-of-00037.safetensors",
+    "model.layers.18.mlp.down_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.18.mlp.gate_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.18.mlp.up_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.18.post_attention_layernorm.weight": "model-00010-of-00037.safetensors",
+    "model.layers.18.self_attn.k_proj.bias": "model-00009-of-00037.safetensors",
+    "model.layers.18.self_attn.k_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.18.self_attn.o_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.18.self_attn.q_proj.bias": "model-00009-of-00037.safetensors",
+    "model.layers.18.self_attn.q_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.18.self_attn.v_proj.bias": "model-00009-of-00037.safetensors",
+    "model.layers.18.self_attn.v_proj.weight": "model-00009-of-00037.safetensors",
+    "model.layers.19.input_layernorm.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.mlp.down_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.mlp.gate_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.mlp.up_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.post_attention_layernorm.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.k_proj.bias": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.k_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.o_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.q_proj.bias": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.q_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.v_proj.bias": "model-00010-of-00037.safetensors",
+    "model.layers.19.self_attn.v_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.2.input_layernorm.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.mlp.down_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.mlp.gate_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.mlp.up_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.post_attention_layernorm.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.k_proj.bias": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.k_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.o_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.q_proj.bias": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.q_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.v_proj.bias": "model-00002-of-00037.safetensors",
+    "model.layers.2.self_attn.v_proj.weight": "model-00002-of-00037.safetensors",
+    "model.layers.20.input_layernorm.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.mlp.down_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.mlp.gate_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.mlp.up_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.post_attention_layernorm.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.k_proj.bias": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.k_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.o_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.q_proj.bias": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.q_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.v_proj.bias": "model-00010-of-00037.safetensors",
+    "model.layers.20.self_attn.v_proj.weight": "model-00010-of-00037.safetensors",
+    "model.layers.21.input_layernorm.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.mlp.down_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.mlp.gate_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.mlp.up_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.post_attention_layernorm.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.k_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.k_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.o_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.q_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.q_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.v_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.21.self_attn.v_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.input_layernorm.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.mlp.down_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.mlp.gate_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.mlp.up_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.post_attention_layernorm.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.k_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.k_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.o_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.q_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.q_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.v_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.22.self_attn.v_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.23.input_layernorm.weight": "model-00012-of-00037.safetensors",
+    "model.layers.23.mlp.down_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.23.mlp.gate_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.23.mlp.up_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.23.post_attention_layernorm.weight": "model-00012-of-00037.safetensors",
+    "model.layers.23.self_attn.k_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.23.self_attn.k_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.23.self_attn.o_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.23.self_attn.q_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.23.self_attn.q_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.23.self_attn.v_proj.bias": "model-00011-of-00037.safetensors",
+    "model.layers.23.self_attn.v_proj.weight": "model-00011-of-00037.safetensors",
+    "model.layers.24.input_layernorm.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.mlp.down_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.mlp.gate_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.mlp.up_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.post_attention_layernorm.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.k_proj.bias": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.k_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.o_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.q_proj.bias": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.q_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.v_proj.bias": "model-00012-of-00037.safetensors",
+    "model.layers.24.self_attn.v_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.25.input_layernorm.weight": "model-00013-of-00037.safetensors",
+    "model.layers.25.mlp.down_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.25.mlp.gate_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.25.mlp.up_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.25.post_attention_layernorm.weight": "model-00013-of-00037.safetensors",
+    "model.layers.25.self_attn.k_proj.bias": "model-00012-of-00037.safetensors",
+    "model.layers.25.self_attn.k_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.25.self_attn.o_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.25.self_attn.q_proj.bias": "model-00012-of-00037.safetensors",
+    "model.layers.25.self_attn.q_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.25.self_attn.v_proj.bias": "model-00012-of-00037.safetensors",
+    "model.layers.25.self_attn.v_proj.weight": "model-00012-of-00037.safetensors",
+    "model.layers.26.input_layernorm.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.mlp.down_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.mlp.gate_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.mlp.up_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.post_attention_layernorm.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.k_proj.bias": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.k_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.o_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.q_proj.bias": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.q_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.v_proj.bias": "model-00013-of-00037.safetensors",
+    "model.layers.26.self_attn.v_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.27.input_layernorm.weight": "model-00014-of-00037.safetensors",
+    "model.layers.27.mlp.down_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.27.mlp.gate_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.27.mlp.up_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.27.post_attention_layernorm.weight": "model-00014-of-00037.safetensors",
+    "model.layers.27.self_attn.k_proj.bias": "model-00013-of-00037.safetensors",
+    "model.layers.27.self_attn.k_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.27.self_attn.o_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.27.self_attn.q_proj.bias": "model-00013-of-00037.safetensors",
+    "model.layers.27.self_attn.q_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.27.self_attn.v_proj.bias": "model-00013-of-00037.safetensors",
+    "model.layers.27.self_attn.v_proj.weight": "model-00013-of-00037.safetensors",
+    "model.layers.28.input_layernorm.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.mlp.down_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.mlp.gate_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.mlp.up_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.post_attention_layernorm.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.k_proj.bias": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.k_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.o_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.q_proj.bias": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.q_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.v_proj.bias": "model-00014-of-00037.safetensors",
+    "model.layers.28.self_attn.v_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.input_layernorm.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.mlp.down_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.mlp.gate_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.mlp.up_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.post_attention_layernorm.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.k_proj.bias": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.k_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.o_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.q_proj.bias": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.q_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.v_proj.bias": "model-00014-of-00037.safetensors",
+    "model.layers.29.self_attn.v_proj.weight": "model-00014-of-00037.safetensors",
+    "model.layers.3.input_layernorm.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.mlp.down_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.mlp.gate_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.mlp.up_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.post_attention_layernorm.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.k_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.k_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.o_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.q_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.q_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.v_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.3.self_attn.v_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.30.input_layernorm.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.mlp.down_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.mlp.gate_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.mlp.up_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.post_attention_layernorm.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.k_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.k_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.o_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.q_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.q_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.v_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.30.self_attn.v_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.input_layernorm.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.mlp.down_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.mlp.gate_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.mlp.up_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.post_attention_layernorm.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.k_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.k_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.o_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.q_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.q_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.v_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.31.self_attn.v_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.32.input_layernorm.weight": "model-00016-of-00037.safetensors",
+    "model.layers.32.mlp.down_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.32.mlp.gate_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.32.mlp.up_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.32.post_attention_layernorm.weight": "model-00016-of-00037.safetensors",
+    "model.layers.32.self_attn.k_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.32.self_attn.k_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.32.self_attn.o_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.32.self_attn.q_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.32.self_attn.q_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.32.self_attn.v_proj.bias": "model-00015-of-00037.safetensors",
+    "model.layers.32.self_attn.v_proj.weight": "model-00015-of-00037.safetensors",
+    "model.layers.33.input_layernorm.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.mlp.down_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.mlp.gate_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.mlp.up_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.post_attention_layernorm.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.k_proj.bias": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.k_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.o_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.q_proj.bias": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.q_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.v_proj.bias": "model-00016-of-00037.safetensors",
+    "model.layers.33.self_attn.v_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.34.input_layernorm.weight": "model-00017-of-00037.safetensors",
+    "model.layers.34.mlp.down_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.34.mlp.gate_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.34.mlp.up_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.34.post_attention_layernorm.weight": "model-00017-of-00037.safetensors",
+    "model.layers.34.self_attn.k_proj.bias": "model-00016-of-00037.safetensors",
+    "model.layers.34.self_attn.k_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.34.self_attn.o_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.34.self_attn.q_proj.bias": "model-00016-of-00037.safetensors",
+    "model.layers.34.self_attn.q_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.34.self_attn.v_proj.bias": "model-00016-of-00037.safetensors",
+    "model.layers.34.self_attn.v_proj.weight": "model-00016-of-00037.safetensors",
+    "model.layers.35.input_layernorm.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.mlp.down_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.mlp.gate_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.mlp.up_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.post_attention_layernorm.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.k_proj.bias": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.k_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.o_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.q_proj.bias": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.q_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.v_proj.bias": "model-00017-of-00037.safetensors",
+    "model.layers.35.self_attn.v_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.36.input_layernorm.weight": "model-00018-of-00037.safetensors",
+    "model.layers.36.mlp.down_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.36.mlp.gate_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.36.mlp.up_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.36.post_attention_layernorm.weight": "model-00018-of-00037.safetensors",
+    "model.layers.36.self_attn.k_proj.bias": "model-00017-of-00037.safetensors",
+    "model.layers.36.self_attn.k_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.36.self_attn.o_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.36.self_attn.q_proj.bias": "model-00017-of-00037.safetensors",
+    "model.layers.36.self_attn.q_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.36.self_attn.v_proj.bias": "model-00017-of-00037.safetensors",
+    "model.layers.36.self_attn.v_proj.weight": "model-00017-of-00037.safetensors",
+    "model.layers.37.input_layernorm.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.mlp.down_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.mlp.gate_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.mlp.up_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.post_attention_layernorm.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.k_proj.bias": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.k_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.o_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.q_proj.bias": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.q_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.v_proj.bias": "model-00018-of-00037.safetensors",
+    "model.layers.37.self_attn.v_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.input_layernorm.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.mlp.down_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.mlp.gate_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.mlp.up_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.post_attention_layernorm.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.k_proj.bias": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.k_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.o_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.q_proj.bias": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.q_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.v_proj.bias": "model-00018-of-00037.safetensors",
+    "model.layers.38.self_attn.v_proj.weight": "model-00018-of-00037.safetensors",
+    "model.layers.39.input_layernorm.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.mlp.down_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.mlp.gate_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.mlp.up_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.post_attention_layernorm.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.k_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.k_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.o_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.q_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.q_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.v_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.39.self_attn.v_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.4.input_layernorm.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.mlp.down_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.mlp.gate_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.mlp.up_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.post_attention_layernorm.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.k_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.k_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.o_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.q_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.q_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.v_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.4.self_attn.v_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.40.input_layernorm.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.mlp.down_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.mlp.gate_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.mlp.up_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.post_attention_layernorm.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.k_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.k_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.o_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.q_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.q_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.v_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.40.self_attn.v_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.41.input_layernorm.weight": "model-00020-of-00037.safetensors",
+    "model.layers.41.mlp.down_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.41.mlp.gate_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.41.mlp.up_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.41.post_attention_layernorm.weight": "model-00020-of-00037.safetensors",
+    "model.layers.41.self_attn.k_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.41.self_attn.k_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.41.self_attn.o_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.41.self_attn.q_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.41.self_attn.q_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.41.self_attn.v_proj.bias": "model-00019-of-00037.safetensors",
+    "model.layers.41.self_attn.v_proj.weight": "model-00019-of-00037.safetensors",
+    "model.layers.42.input_layernorm.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.mlp.down_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.mlp.gate_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.mlp.up_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.post_attention_layernorm.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.k_proj.bias": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.k_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.o_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.q_proj.bias": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.q_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.v_proj.bias": "model-00020-of-00037.safetensors",
+    "model.layers.42.self_attn.v_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.43.input_layernorm.weight": "model-00021-of-00037.safetensors",
+    "model.layers.43.mlp.down_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.43.mlp.gate_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.43.mlp.up_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.43.post_attention_layernorm.weight": "model-00021-of-00037.safetensors",
+    "model.layers.43.self_attn.k_proj.bias": "model-00020-of-00037.safetensors",
+    "model.layers.43.self_attn.k_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.43.self_attn.o_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.43.self_attn.q_proj.bias": "model-00020-of-00037.safetensors",
+    "model.layers.43.self_attn.q_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.43.self_attn.v_proj.bias": "model-00020-of-00037.safetensors",
+    "model.layers.43.self_attn.v_proj.weight": "model-00020-of-00037.safetensors",
+    "model.layers.44.input_layernorm.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.mlp.down_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.mlp.gate_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.mlp.up_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.post_attention_layernorm.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.k_proj.bias": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.k_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.o_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.q_proj.bias": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.q_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.v_proj.bias": "model-00021-of-00037.safetensors",
+    "model.layers.44.self_attn.v_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.45.input_layernorm.weight": "model-00022-of-00037.safetensors",
+    "model.layers.45.mlp.down_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.45.mlp.gate_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.45.mlp.up_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.45.post_attention_layernorm.weight": "model-00022-of-00037.safetensors",
+    "model.layers.45.self_attn.k_proj.bias": "model-00021-of-00037.safetensors",
+    "model.layers.45.self_attn.k_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.45.self_attn.o_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.45.self_attn.q_proj.bias": "model-00021-of-00037.safetensors",
+    "model.layers.45.self_attn.q_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.45.self_attn.v_proj.bias": "model-00021-of-00037.safetensors",
+    "model.layers.45.self_attn.v_proj.weight": "model-00021-of-00037.safetensors",
+    "model.layers.46.input_layernorm.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.mlp.down_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.mlp.gate_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.mlp.up_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.post_attention_layernorm.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.k_proj.bias": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.k_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.o_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.q_proj.bias": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.q_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.v_proj.bias": "model-00022-of-00037.safetensors",
+    "model.layers.46.self_attn.v_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.input_layernorm.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.mlp.down_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.mlp.gate_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.mlp.up_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.post_attention_layernorm.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.k_proj.bias": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.k_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.o_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.q_proj.bias": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.q_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.v_proj.bias": "model-00022-of-00037.safetensors",
+    "model.layers.47.self_attn.v_proj.weight": "model-00022-of-00037.safetensors",
+    "model.layers.48.input_layernorm.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.mlp.down_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.mlp.gate_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.mlp.up_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.post_attention_layernorm.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.k_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.k_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.o_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.q_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.q_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.v_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.48.self_attn.v_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.input_layernorm.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.mlp.down_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.mlp.gate_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.mlp.up_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.post_attention_layernorm.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.k_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.k_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.o_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.q_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.q_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.v_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.49.self_attn.v_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.5.input_layernorm.weight": "model-00004-of-00037.safetensors",
+    "model.layers.5.mlp.down_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.5.mlp.gate_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.5.mlp.up_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.5.post_attention_layernorm.weight": "model-00004-of-00037.safetensors",
+    "model.layers.5.self_attn.k_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.5.self_attn.k_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.5.self_attn.o_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.5.self_attn.q_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.5.self_attn.q_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.5.self_attn.v_proj.bias": "model-00003-of-00037.safetensors",
+    "model.layers.5.self_attn.v_proj.weight": "model-00003-of-00037.safetensors",
+    "model.layers.50.input_layernorm.weight": "model-00024-of-00037.safetensors",
+    "model.layers.50.mlp.down_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.50.mlp.gate_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.50.mlp.up_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.50.post_attention_layernorm.weight": "model-00024-of-00037.safetensors",
+    "model.layers.50.self_attn.k_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.50.self_attn.k_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.50.self_attn.o_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.50.self_attn.q_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.50.self_attn.q_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.50.self_attn.v_proj.bias": "model-00023-of-00037.safetensors",
+    "model.layers.50.self_attn.v_proj.weight": "model-00023-of-00037.safetensors",
+    "model.layers.51.input_layernorm.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.mlp.down_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.mlp.gate_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.mlp.up_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.post_attention_layernorm.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.k_proj.bias": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.k_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.o_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.q_proj.bias": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.q_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.v_proj.bias": "model-00024-of-00037.safetensors",
+    "model.layers.51.self_attn.v_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.52.input_layernorm.weight": "model-00025-of-00037.safetensors",
+    "model.layers.52.mlp.down_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.52.mlp.gate_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.52.mlp.up_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.52.post_attention_layernorm.weight": "model-00025-of-00037.safetensors",
+    "model.layers.52.self_attn.k_proj.bias": "model-00024-of-00037.safetensors",
+    "model.layers.52.self_attn.k_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.52.self_attn.o_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.52.self_attn.q_proj.bias": "model-00024-of-00037.safetensors",
+    "model.layers.52.self_attn.q_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.52.self_attn.v_proj.bias": "model-00024-of-00037.safetensors",
+    "model.layers.52.self_attn.v_proj.weight": "model-00024-of-00037.safetensors",
+    "model.layers.53.input_layernorm.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.mlp.down_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.mlp.gate_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.mlp.up_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.post_attention_layernorm.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.k_proj.bias": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.k_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.o_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.q_proj.bias": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.q_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.v_proj.bias": "model-00025-of-00037.safetensors",
+    "model.layers.53.self_attn.v_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.54.input_layernorm.weight": "model-00026-of-00037.safetensors",
+    "model.layers.54.mlp.down_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.54.mlp.gate_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.54.mlp.up_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.54.post_attention_layernorm.weight": "model-00026-of-00037.safetensors",
+    "model.layers.54.self_attn.k_proj.bias": "model-00025-of-00037.safetensors",
+    "model.layers.54.self_attn.k_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.54.self_attn.o_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.54.self_attn.q_proj.bias": "model-00025-of-00037.safetensors",
+    "model.layers.54.self_attn.q_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.54.self_attn.v_proj.bias": "model-00025-of-00037.safetensors",
+    "model.layers.54.self_attn.v_proj.weight": "model-00025-of-00037.safetensors",
+    "model.layers.55.input_layernorm.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.mlp.down_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.mlp.gate_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.mlp.up_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.post_attention_layernorm.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.k_proj.bias": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.k_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.o_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.q_proj.bias": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.q_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.v_proj.bias": "model-00026-of-00037.safetensors",
+    "model.layers.55.self_attn.v_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.input_layernorm.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.mlp.down_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.mlp.gate_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.mlp.up_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.post_attention_layernorm.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.k_proj.bias": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.k_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.o_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.q_proj.bias": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.q_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.v_proj.bias": "model-00026-of-00037.safetensors",
+    "model.layers.56.self_attn.v_proj.weight": "model-00026-of-00037.safetensors",
+    "model.layers.57.input_layernorm.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.mlp.down_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.mlp.gate_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.mlp.up_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.post_attention_layernorm.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.k_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.k_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.o_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.q_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.q_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.v_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.57.self_attn.v_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.input_layernorm.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.mlp.down_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.mlp.gate_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.mlp.up_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.post_attention_layernorm.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.k_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.k_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.o_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.q_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.q_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.v_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.58.self_attn.v_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.59.input_layernorm.weight": "model-00028-of-00037.safetensors",
+    "model.layers.59.mlp.down_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.59.mlp.gate_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.59.mlp.up_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.59.post_attention_layernorm.weight": "model-00028-of-00037.safetensors",
+    "model.layers.59.self_attn.k_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.59.self_attn.k_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.59.self_attn.o_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.59.self_attn.q_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.59.self_attn.q_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.59.self_attn.v_proj.bias": "model-00027-of-00037.safetensors",
+    "model.layers.59.self_attn.v_proj.weight": "model-00027-of-00037.safetensors",
+    "model.layers.6.input_layernorm.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.mlp.down_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.mlp.gate_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.mlp.up_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.post_attention_layernorm.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.k_proj.bias": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.k_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.o_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.q_proj.bias": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.q_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.v_proj.bias": "model-00004-of-00037.safetensors",
+    "model.layers.6.self_attn.v_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.60.input_layernorm.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.mlp.down_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.mlp.gate_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.mlp.up_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.post_attention_layernorm.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.k_proj.bias": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.k_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.o_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.q_proj.bias": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.q_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.v_proj.bias": "model-00028-of-00037.safetensors",
+    "model.layers.60.self_attn.v_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.61.input_layernorm.weight": "model-00029-of-00037.safetensors",
+    "model.layers.61.mlp.down_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.61.mlp.gate_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.61.mlp.up_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.61.post_attention_layernorm.weight": "model-00029-of-00037.safetensors",
+    "model.layers.61.self_attn.k_proj.bias": "model-00028-of-00037.safetensors",
+    "model.layers.61.self_attn.k_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.61.self_attn.o_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.61.self_attn.q_proj.bias": "model-00028-of-00037.safetensors",
+    "model.layers.61.self_attn.q_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.61.self_attn.v_proj.bias": "model-00028-of-00037.safetensors",
+    "model.layers.61.self_attn.v_proj.weight": "model-00028-of-00037.safetensors",
+    "model.layers.62.input_layernorm.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.mlp.down_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.mlp.gate_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.mlp.up_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.post_attention_layernorm.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.k_proj.bias": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.k_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.o_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.q_proj.bias": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.q_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.v_proj.bias": "model-00029-of-00037.safetensors",
+    "model.layers.62.self_attn.v_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.63.input_layernorm.weight": "model-00030-of-00037.safetensors",
+    "model.layers.63.mlp.down_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.63.mlp.gate_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.63.mlp.up_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.63.post_attention_layernorm.weight": "model-00030-of-00037.safetensors",
+    "model.layers.63.self_attn.k_proj.bias": "model-00029-of-00037.safetensors",
+    "model.layers.63.self_attn.k_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.63.self_attn.o_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.63.self_attn.q_proj.bias": "model-00029-of-00037.safetensors",
+    "model.layers.63.self_attn.q_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.63.self_attn.v_proj.bias": "model-00029-of-00037.safetensors",
+    "model.layers.63.self_attn.v_proj.weight": "model-00029-of-00037.safetensors",
+    "model.layers.64.input_layernorm.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.mlp.down_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.mlp.gate_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.mlp.up_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.post_attention_layernorm.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.k_proj.bias": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.k_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.o_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.q_proj.bias": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.q_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.v_proj.bias": "model-00030-of-00037.safetensors",
+    "model.layers.64.self_attn.v_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.input_layernorm.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.mlp.down_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.mlp.gate_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.mlp.up_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.post_attention_layernorm.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.k_proj.bias": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.k_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.o_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.q_proj.bias": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.q_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.v_proj.bias": "model-00030-of-00037.safetensors",
+    "model.layers.65.self_attn.v_proj.weight": "model-00030-of-00037.safetensors",
+    "model.layers.66.input_layernorm.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.mlp.down_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.mlp.gate_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.mlp.up_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.post_attention_layernorm.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.k_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.k_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.o_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.q_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.q_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.v_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.66.self_attn.v_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.input_layernorm.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.mlp.down_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.mlp.gate_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.mlp.up_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.post_attention_layernorm.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.k_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.k_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.o_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.q_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.q_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.v_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.67.self_attn.v_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.68.input_layernorm.weight": "model-00032-of-00037.safetensors",
+    "model.layers.68.mlp.down_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.68.mlp.gate_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.68.mlp.up_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.68.post_attention_layernorm.weight": "model-00032-of-00037.safetensors",
+    "model.layers.68.self_attn.k_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.68.self_attn.k_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.68.self_attn.o_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.68.self_attn.q_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.68.self_attn.q_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.68.self_attn.v_proj.bias": "model-00031-of-00037.safetensors",
+    "model.layers.68.self_attn.v_proj.weight": "model-00031-of-00037.safetensors",
+    "model.layers.69.input_layernorm.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.mlp.down_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.mlp.gate_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.mlp.up_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.post_attention_layernorm.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.k_proj.bias": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.k_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.o_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.q_proj.bias": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.q_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.v_proj.bias": "model-00032-of-00037.safetensors",
+    "model.layers.69.self_attn.v_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.7.input_layernorm.weight": "model-00005-of-00037.safetensors",
+    "model.layers.7.mlp.down_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.7.mlp.gate_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.7.mlp.up_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.7.post_attention_layernorm.weight": "model-00005-of-00037.safetensors",
+    "model.layers.7.self_attn.k_proj.bias": "model-00004-of-00037.safetensors",
+    "model.layers.7.self_attn.k_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.7.self_attn.o_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.7.self_attn.q_proj.bias": "model-00004-of-00037.safetensors",
+    "model.layers.7.self_attn.q_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.7.self_attn.v_proj.bias": "model-00004-of-00037.safetensors",
+    "model.layers.7.self_attn.v_proj.weight": "model-00004-of-00037.safetensors",
+    "model.layers.70.input_layernorm.weight": "model-00033-of-00037.safetensors",
+    "model.layers.70.mlp.down_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.70.mlp.gate_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.70.mlp.up_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.70.post_attention_layernorm.weight": "model-00033-of-00037.safetensors",
+    "model.layers.70.self_attn.k_proj.bias": "model-00032-of-00037.safetensors",
+    "model.layers.70.self_attn.k_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.70.self_attn.o_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.70.self_attn.q_proj.bias": "model-00032-of-00037.safetensors",
+    "model.layers.70.self_attn.q_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.70.self_attn.v_proj.bias": "model-00032-of-00037.safetensors",
+    "model.layers.70.self_attn.v_proj.weight": "model-00032-of-00037.safetensors",
+    "model.layers.71.input_layernorm.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.mlp.down_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.mlp.gate_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.mlp.up_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.post_attention_layernorm.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.k_proj.bias": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.k_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.o_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.q_proj.bias": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.q_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.v_proj.bias": "model-00033-of-00037.safetensors",
+    "model.layers.71.self_attn.v_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.72.input_layernorm.weight": "model-00034-of-00037.safetensors",
+    "model.layers.72.mlp.down_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.72.mlp.gate_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.72.mlp.up_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.72.post_attention_layernorm.weight": "model-00034-of-00037.safetensors",
+    "model.layers.72.self_attn.k_proj.bias": "model-00033-of-00037.safetensors",
+    "model.layers.72.self_attn.k_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.72.self_attn.o_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.72.self_attn.q_proj.bias": "model-00033-of-00037.safetensors",
+    "model.layers.72.self_attn.q_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.72.self_attn.v_proj.bias": "model-00033-of-00037.safetensors",
+    "model.layers.72.self_attn.v_proj.weight": "model-00033-of-00037.safetensors",
+    "model.layers.73.input_layernorm.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.mlp.down_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.mlp.gate_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.mlp.up_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.post_attention_layernorm.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.k_proj.bias": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.k_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.o_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.q_proj.bias": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.q_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.v_proj.bias": "model-00034-of-00037.safetensors",
+    "model.layers.73.self_attn.v_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.input_layernorm.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.mlp.down_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.mlp.gate_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.mlp.up_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.post_attention_layernorm.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.k_proj.bias": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.k_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.o_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.q_proj.bias": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.q_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.v_proj.bias": "model-00034-of-00037.safetensors",
+    "model.layers.74.self_attn.v_proj.weight": "model-00034-of-00037.safetensors",
+    "model.layers.75.input_layernorm.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.mlp.down_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.mlp.gate_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.mlp.up_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.post_attention_layernorm.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.k_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.k_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.o_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.q_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.q_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.v_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.75.self_attn.v_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.input_layernorm.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.mlp.down_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.mlp.gate_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.mlp.up_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.post_attention_layernorm.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.k_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.k_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.o_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.q_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.q_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.v_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.76.self_attn.v_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.77.input_layernorm.weight": "model-00036-of-00037.safetensors",
+    "model.layers.77.mlp.down_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.77.mlp.gate_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.77.mlp.up_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.77.post_attention_layernorm.weight": "model-00036-of-00037.safetensors",
+    "model.layers.77.self_attn.k_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.77.self_attn.k_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.77.self_attn.o_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.77.self_attn.q_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.77.self_attn.q_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.77.self_attn.v_proj.bias": "model-00035-of-00037.safetensors",
+    "model.layers.77.self_attn.v_proj.weight": "model-00035-of-00037.safetensors",
+    "model.layers.78.input_layernorm.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.mlp.down_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.mlp.gate_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.mlp.up_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.post_attention_layernorm.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.k_proj.bias": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.k_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.o_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.q_proj.bias": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.q_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.v_proj.bias": "model-00036-of-00037.safetensors",
+    "model.layers.78.self_attn.v_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.79.input_layernorm.weight": "model-00037-of-00037.safetensors",
+    "model.layers.79.mlp.down_proj.weight": "model-00037-of-00037.safetensors",
+    "model.layers.79.mlp.gate_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.79.mlp.up_proj.weight": "model-00037-of-00037.safetensors",
+    "model.layers.79.post_attention_layernorm.weight": "model-00037-of-00037.safetensors",
+    "model.layers.79.self_attn.k_proj.bias": "model-00036-of-00037.safetensors",
+    "model.layers.79.self_attn.k_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.79.self_attn.o_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.79.self_attn.q_proj.bias": "model-00036-of-00037.safetensors",
+    "model.layers.79.self_attn.q_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.79.self_attn.v_proj.bias": "model-00036-of-00037.safetensors",
+    "model.layers.79.self_attn.v_proj.weight": "model-00036-of-00037.safetensors",
+    "model.layers.8.input_layernorm.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.mlp.down_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.mlp.gate_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.mlp.up_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.post_attention_layernorm.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.k_proj.bias": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.k_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.o_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.q_proj.bias": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.q_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.v_proj.bias": "model-00005-of-00037.safetensors",
+    "model.layers.8.self_attn.v_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.9.input_layernorm.weight": "model-00006-of-00037.safetensors",
+    "model.layers.9.mlp.down_proj.weight": "model-00006-of-00037.safetensors",
+    "model.layers.9.mlp.gate_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.9.mlp.up_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.9.post_attention_layernorm.weight": "model-00006-of-00037.safetensors",
+    "model.layers.9.self_attn.k_proj.bias": "model-00005-of-00037.safetensors",
+    "model.layers.9.self_attn.k_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.9.self_attn.o_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.9.self_attn.q_proj.bias": "model-00005-of-00037.safetensors",
+    "model.layers.9.self_attn.q_proj.weight": "model-00005-of-00037.safetensors",
+    "model.layers.9.self_attn.v_proj.bias": "model-00005-of-00037.safetensors",
+    "model.layers.9.self_attn.v_proj.weight": "model-00005-of-00037.safetensors",
+    "model.norm.weight": "model-00037-of-00037.safetensors"
+  }
+}

tokenizer_config.json

@@ -0,0 +1,40 @@
+{
+  "add_prefix_space": false,
+  "added_tokens_decoder": {
+    "151643": {
+      "content": "<|endoftext|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151644": {
+      "content": "<|im_start|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    },
+    "151645": {
+      "content": "<|im_end|>",
+      "lstrip": false,
+      "normalized": false,
+      "rstrip": false,
+      "single_word": false,
+      "special": true
+    }
+  },
+  "additional_special_tokens": ["<|im_start|>", "<|im_end|>"],
+  "bos_token": null,
+  "chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
+  "clean_up_tokenization_spaces": false,
+  "eos_token": "<|im_end|>",
+  "errors": "replace",
+  "model_max_length": 131072,
+  "pad_token": "<|endoftext|>",
+  "split_special_tokens": false,
+  "tokenizer_class": "Qwen2Tokenizer",
+  "unk_token": null
+}