nvidia/OpenCodeReasoning-Nemotron-1.1-32B
1
0
Fork 0
Code Issues Pull Requests Actions Projects Releases Wiki Activity

初始化项目，由ModelHub XC社区提供模型

Browse Source 
Model: nvidia/OpenCodeReasoning-Nemotron-1.1-32B
Source: Original Platform
This commit is contained in:
ModelHub XC
2026-07-25 15:30:18 +08:00
commit 9ad6046c32
24 changed files with 152786 additions and 0 deletions
Download Patch File Download Diff File Expand all files Collapse all files

37
.gitattributes vendored Normal file
View File

@@ -0,0 +1,37 @@
*.7z filter=lfs diff=lfs merge=lfs -text
*.arrow filter=lfs diff=lfs merge=lfs -text
*.bin filter=lfs diff=lfs merge=lfs -text
*.bz2 filter=lfs diff=lfs merge=lfs -text
*.ckpt filter=lfs diff=lfs merge=lfs -text
*.ftz filter=lfs diff=lfs merge=lfs -text
*.gz filter=lfs diff=lfs merge=lfs -text
*.h5 filter=lfs diff=lfs merge=lfs -text
*.joblib filter=lfs diff=lfs merge=lfs -text
*.lfs.* filter=lfs diff=lfs merge=lfs -text
*.mlmodel filter=lfs diff=lfs merge=lfs -text
*.model filter=lfs diff=lfs merge=lfs -text
*.msgpack filter=lfs diff=lfs merge=lfs -text
*.npy filter=lfs diff=lfs merge=lfs -text
*.npz filter=lfs diff=lfs merge=lfs -text
*.onnx filter=lfs diff=lfs merge=lfs -text
*.ot filter=lfs diff=lfs merge=lfs -text
*.parquet filter=lfs diff=lfs merge=lfs -text
*.pb filter=lfs diff=lfs merge=lfs -text
*.pickle filter=lfs diff=lfs merge=lfs -text
*.pkl filter=lfs diff=lfs merge=lfs -text
*.pt filter=lfs diff=lfs merge=lfs -text
*.pth filter=lfs diff=lfs merge=lfs -text
*.rar filter=lfs diff=lfs merge=lfs -text
*.safetensors filter=lfs diff=lfs merge=lfs -text
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
*.tar.* filter=lfs diff=lfs merge=lfs -text
*.tar filter=lfs diff=lfs merge=lfs -text
*.tflite filter=lfs diff=lfs merge=lfs -text
*.tgz filter=lfs diff=lfs merge=lfs -text
*.wasm filter=lfs diff=lfs merge=lfs -text
*.xz filter=lfs diff=lfs merge=lfs -text
*.zip filter=lfs diff=lfs merge=lfs -text
*.zst filter=lfs diff=lfs merge=lfs -text
*tfevents* filter=lfs diff=lfs merge=lfs -text
results.png filter=lfs diff=lfs merge=lfs -text
tokenizer.json filter=lfs diff=lfs merge=lfs -text

7
BIAS.md Normal file
View File

@@ -0,0 +1,7 @@
Field | Response
:---------------------------------------------------------------------------------------------------|:---------------
Participation considerations from adversely impacted groups [protected classes](https://www.senate.ca.gov/content/protected-classes) in model design and testing: | None
Measures taken to mitigate against unwanted bias: | None

13
EXPLAINABILITY.md Normal file
View File

@@ -0,0 +1,13 @@
Field | Response
:------------------------------------------------------------------------------------------------------|:---------------------------------------------------------------------------------
Intended Task/Domain: | Reasoning for Code Generation
Model Type: | Transformer
Intended Users: | Solving competitive programming questions and evaluation for benchmark comparison.
Output: | Text
Describe how the model works: | he model generates a reasoning trace and responds with a final solution in response to a user prompting a programming question.
Name the adversely impacted groups this has been tested to deliver comparable outcomes regardless of: | Not Applicable
Technical Limitations & Mitigation: | This model is not applicable for Software Engineering tasks. It primarily should be used for competitive coding challenges that require optimized code solutions that can operate in appropriate space and time complexity.
Verified to have met prescribed NVIDIA quality standards: | Yes
Performance Metrics: | Pass@1 score
Potential Known Risks: | The model may provide incorrect code solutions that fail to solve the problem. The model may enter a feedback loop and constantly generate reasoning tokens without generating the final solution.
Licensing: | [NVIDIA Open Model License Agreement](https://developer.download.nvidia.com/licenses/nvidia-open-model-license-agreement-june-2024.pdf)

16
LICENSE Normal file
View File

@@ -0,0 +1,16 @@
/*
* SPDX-FileCopyrightText: Copyright (c) 2025 NVIDIA CORPORATION & AFFILIATES. All rights reserved.
* SPDX-License-Identifier: Apache-2.0
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/

9
PRIVACY.md Normal file
View File

@@ -0,0 +1,9 @@
Field | Response
:----------------------------------------------------------------------------------------------------------------------------------|:-----------------------------------------------
Generatable or reverse engineerable personal data? | No
Personal data used to create this model? | No
How often is the dataset reviewed? | Before Release
Is there provenance for all datasets used in training? | Yes
Does data labeling (annotation, metadata) comply with privacy laws? | Yes
Is data compliant with data subject requests for data correction or removal, if such a request was made? | No, not possible with externally-sourced data.
Applicable Privacy Policy | https://www.nvidia.com/en-us/about-nvidia/privacy-policy/

205
README.md Normal file
View File

@@ -0,0 +1,205 @@
---
base_model:
- Qwen/Qwen2.5-32B-Instruct
datasets:
- nvidia/OpenCodeReasoning
language:
- en
library_name: transformers
tags:
- nvidia
- code
pipeline_tag: text-generation
---
# OpenCodeReasoning-Nemotron-1.1-32B Overview
## Description: <br>
OpenCodeReasoning-Nemotron-1.1-32B is a large language model (LLM) which is a derivative of Qwen2.5-32B-Instruct (AKA the reference model). It is a reasoning model that is post-trained for reasoning for code generation. The model supports a context length of 64k tokens. <br>
This model is ready for commercial/non-commercial use. <br>
![Evaluation Results](./results.png)
## Results
Below results are the average of **64 evaluations** on LiveCodeBench (v5) [2408-2501].
| Model | Pass@1 |
|:---------------------------------------|:-------------------|
| DeepSeek-R1-0528 | 73.4 |
| DeepSeek-R1 | 65.6 |
| QwQ-32B | 61.3 |
| | |
| **Distilled 7B+ Models** | |
| | |
| Bespoke-Stratos-7B | 14.7 |
| OpenThinker-7B | 25.5 |
| R1-Distill-Qwen-7B | 38.0 |
| OlympicCoder-7B | 40.9 |
| **OpenCodeReasoning-Nemotron-7B** | **51.3** |
| **OpenCodeReasoning-Nemotron-1.1-7B** | **55.5** |
| | |
| **Distilled 14B+ Models** | |
| | |
| R1-Distill-Qwen-14B | 51.3 |
| **OpenCodeReasoning-Nemotron-14B** | **59.4** |
| **OpenCodeReasoning-Nemotron-1.1-14B** | **65.9** |
| | |
| **Distilled 32B+ Models** | |
| | |
| Bespoke-Stratos-32B | 30.1 |
| OpenThinker-32B | 54.1 |
| R1-Distill-Qwen-32B | 58.1 |
| OlympicCoder-32B | 57.4 |
| **OpenCodeReasoning-Nemotron-32B** | **61.7** |
| **OpenCodeReasoning-Nemotron-1.1-32B** | **69.9** |
## Reproducing our results
* [Models](https://huggingface.co/collections/nvidia/opencodereasoning-67ec462892673a326c0696c1)
* [Dataset](https://huggingface.co/datasets/nvidia/OpenCodeReasoning)
* [Paper](https://arxiv.org/abs/2504.01943)
## How to use the models?
To run inference on coding problems:
````python
import transformers
import torch
model_id = "nvidia/OpenCodeReasoning-Nemotron-1.1-32B"
pipeline = transformers.pipeline(
"text-generation",
model=model_id,
model_kwargs={"torch_dtype": torch.bfloat16},
device_map="auto",
)
prompt = """You are a helpful and harmless assistant. You should think step-by-step before responding to the instruction below.
Please use python programming language only.
You must use ```python for just the final solution code block with the following format:
```python
# Your code here
```
{user}
"""
messages = [
{
"role": "user",
"content": prompt.format(user="Write a program to calculate the sum of the first $N$ fibonacci numbers")
},
]
outputs = pipeline(
messages,
max_new_tokens=49152,
)
print(outputs[0]["generated_text"][-1]['content'])
````
## Citation
If you find the data useful, please cite:
```
@article{ahmad2025opencodereasoning,
title={OpenCodeReasoning: Advancing Data Distillation for Competitive Coding},
author={Wasi Uddin Ahmad, Sean Narenthiran, Somshubra Majumdar, Aleksander Ficek, Siddhartha Jain, Jocelyn Huang, Vahid Noroozi, Boris Ginsburg},
year={2025},
eprint={2504.01943},
archivePrefix={arXiv},
primaryClass={cs.CL},
url={https://arxiv.org/abs/2504.01943},
}
```
## Additional Information
## Model Architecture: <br>
Architecture Type: Dense decoder-only Transformer model
Network Architecture: Qwen-32B-Instruct
<br>
**This model was developed based on Qwen2.5-32B-Instruct and has 32B model parameters. <br>**
**OpenCodeReasoning-Nemotron-1.1-32B was developed based on Qwen2.5-32B-Instruct and has 32B model parameters. <br>**
## Input: <br>
**Input Type(s):** Text <br>
**Input Format(s):** String <br>
**Input Parameters:** One-Dimensional (1D) <br>
**Other Properties Related to Input:** Context length up to 65,536 tokens <br>
## Output: <br>
**Output Type(s):** Text <br>
**Output Format:** String <br>
**Output Parameters:** One-Dimensional (1D) <br>
**Other Properties Related to Output:** Context length up to 65,536 tokens <br>
Our AI models are designed and/or optimized to run on NVIDIA GPU-accelerated systems. By leveraging NVIDIA’s hardware (e.g. GPU cores) and software frameworks (e.g., CUDA libraries), the model achieves faster training and inference times compared to CPU-only solutions. <br>
## Software Integration : <br>
* Runtime Engine: NeMo 2.3.0 <br>
* Recommended Hardware Microarchitecture Compatibility: <br>
NVIDIA Ampere <br>
NVIDIA Hopper <br>
* Preferred/Supported Operating System(s): Linux <br>
## Model Version(s):
1.1 (07/08/2025) <br>
OpenCodeReasoning-Nemotron-1.1-7B<br>
OpenCodeReasoning-Nemotron-1.1-14B<br>
OpenCodeReasoning-Nemotron-1.1-32B<br>
# Training and Evaluation Datasets: <br>
## Training Dataset:
The training corpus for OpenCodeReasoning-Nemotron-1.1-32B is [OpenCodeReasoning](https://huggingface.co/datasets/nvidia/OpenCodeReasoning) dataset, which is composed of competitive programming questions and DeepSeek-R1-0528 generated responses.
Data Collection Method: Hybrid: Automated, Human, Synthetic <br>
Labeling Method: Hybrid: Automated, Human, Synthetic <br>
Properties: 1.165M samples from OpenCodeReasoning (https://huggingface.co/datasets/nvidia/OpenCodeReasoning)
## Evaluation Dataset:
We used the datasets listed in the next section to evaluate OpenCodeReasoning-Nemotron-1.1-32B. <br>
**Data Collection Method: Hybrid: Automated, Human, Synthetic <br>**
**Labeling Method: Hybrid: Automated, Human, Synthetic <br>**
### License/Terms of Use: <br>
GOVERNING TERMS: Use of this model is governed by the [NVIDIA Open Model License Agreement](https://www.nvidia.com/en-us/agreements/enterprise-software/nvidia-open-model-license/). Additional Information: [Apache License Version 2.0](https://huggingface.co/Qwen/Qwen2.5-32B/blob/main/LICENSE).
### Deployment Geography:
Global<br>
### Use Case: <br>
This model is intended for developers and researchers building LLMs. <br>
### Release Date: <br>
Huggingface [07/08/2025] via https://huggingface.co/nvidia/OpenCodeReasoning-Nemotron-1.1-32B/ <br>
## Reference(s):
[2504.01943] OpenCodeReasoning: Advancing Data Distillation for Competitive Coding
<br>
## Inference:
**Engine:** vLLM <br>
**Test Hardware** NVIDIA H100-80GB <br>
## Ethical Considerations:
NVIDIA believes Trustworthy AI is a shared responsibility and we have established policies and practices to enable development for a wide array of AI applications. When downloaded or used in accordance with our terms of service, developers should work with their internal model team to ensure this model meets requirements for the relevant industry and use case and addresses unforeseen product misuse.
For more detailed information on ethical considerations for this model, please see the Model Card++ Explainability, Bias, Safety & Security, and Privacy Subcards.
Please report security vulnerabilities or NVIDIA AI Concerns [here](https://www.nvidia.com/en-us/support/submit-security-vulnerability/).

7
SAFETY.md Normal file
View File

@@ -0,0 +1,7 @@
Field | Response
:---------------------------------------------------|:----------------------------------
Model Application Field(s): | Reasoning for Code Generation<br>
Describe the life critical impact (if present). | Not Applicable <br>
Use Case Restrictions: | Abide by NVIDIA Open Model License Agreement. <br>
Model and dataset restrictions: | The Principle of least privilege (PoLP) is applied limiting access for dataset generation and model development. Restrictions enforce dataset access during training, and dataset license constraints adhered to.

24
added_tokens.json Normal file
View File

@@ -0,0 +1,24 @@
{
"</tool_call>": 151658,
"<tool_call>": 151657,
"<|box_end|>": 151649,
"<|box_start|>": 151648,
"<|endoftext|>": 151643,
"<|file_sep|>": 151664,
"<|fim_middle|>": 151660,
"<|fim_pad|>": 151662,
"<|fim_prefix|>": 151659,
"<|fim_suffix|>": 151661,
"<|im_end|>": 151645,
"<|im_start|>": 151644,
"<|image_pad|>": 151655,
"<|object_ref_end|>": 151647,
"<|object_ref_start|>": 151646,
"<|quad_end|>": 151651,
"<|quad_start|>": 151650,
"<|repo_name|>": 151663,
"<|video_pad|>": 151656,
"<|vision_end|>": 151653,
"<|vision_pad|>": 151654,
"<|vision_start|>": 151652
}

29
config.json Normal file
View File

@@ -0,0 +1,29 @@
{
"_name_or_path": "Qwen/Qwen2.5-32B-Instruct",
"architectures": [
"Qwen2ForCausalLM"
],
"attention_dropout": 0.0,
"bos_token_id": 151643,
"eos_token_id": 151645,
"hidden_act": "silu",
"hidden_size": 5120,
"initializer_range": 0.02,
"intermediate_size": 27648,
"max_position_embeddings": 65536,
"max_window_layers": 70,
"model_type": "qwen2",
"num_attention_heads": 40,
"num_hidden_layers": 64,
"num_key_value_heads": 8,
"rms_norm_eps": 1e-06,
"rope_scaling": null,
"rope_theta": 1000000.0,
"sliding_window": null,
"tie_word_embeddings": false,
"torch_dtype": "bfloat16",
"transformers_version": "4.47.1",
"use_cache": true,
"use_sliding_window": false,
"vocab_size": 152064
}

6
generation_config.json Normal file
View File

@@ -0,0 +1,6 @@
{
"_from_model_config": true,
"bos_token_id": 151643,
"eos_token_id": 151645,
"transformers_version": "4.47.1"
}

151388
merges.txt Normal file
View File

File diff suppressed because it is too large Load Diff

3
model-00001-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:b4e23446c2f54e1367edf90bcbeba4a63ac3fca9f5c267b0dce24ef3582fa8a2
size 9767790336

3
model-00002-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:151faabac3acda0eee2e6e5f156da09c0a3c495d9dd7c5f1a64d5fe6dbd9e370
size 9752118784

3
model-00003-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:5def8981ed4472e529c5c0665002ab4cf8ee93a64f5bae62af805b714fa08861
size 9752118816

3
model-00004-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:3a2a95ce71f0a95c88df5eab7c38cc219660b80d37d29afd452ff962f720e8fe
size 9752118816

3
model-00005-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c69fbdcfdfbd20ae478760c227f25b9892f779cdde3de3cd60747f732df31313
size 9752118816

3
model-00006-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:c8baea323d826190bd318a34f8023d0c2fbaa172c95b6d5d87ae8729061ed48e
size 9752118816

3
model-00007-of-00007.safetensors Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:96f121e4aabde6b51e5250725c6ac1880cc61f91f9eb61bde497d358fc1577a4
size 6999457200

778
model.safetensors.index.json Normal file
View File

@@ -0,0 +1,778 @@
{
"metadata": {
"total_size": 65527752704
},
"weight_map": {
"lm_head.weight": "model-00007-of-00007.safetensors",
"model.embed_tokens.weight": "model-00001-of-00007.safetensors",
"model.layers.0.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.0.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.1.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.10.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.10.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.11.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.12.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.12.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.13.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.13.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.14.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.14.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.15.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.15.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.16.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.16.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.17.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.17.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.18.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.18.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.18.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.18.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.18.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.18.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.18.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.18.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.18.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.18.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.18.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.18.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.19.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.19.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.19.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.2.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.2.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.20.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.20.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.20.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.20.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.20.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.20.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.21.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.21.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.22.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.22.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.23.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.23.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.24.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.24.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.25.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.25.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.26.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.26.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.input_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.27.mlp.down_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.mlp.up_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.post_attention_layernorm.weight": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.27.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.28.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.28.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.28.mlp.gate_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.28.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.28.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.28.self_attn.k_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.28.self_attn.k_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.28.self_attn.o_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.28.self_attn.q_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.28.self_attn.q_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.28.self_attn.v_proj.bias": "model-00003-of-00007.safetensors",
"model.layers.28.self_attn.v_proj.weight": "model-00003-of-00007.safetensors",
"model.layers.29.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.29.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.29.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.29.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.29.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.29.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.3.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.3.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.30.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.30.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.30.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.30.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.30.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.30.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.31.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.31.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.32.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.32.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.33.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.33.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.34.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.34.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.35.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.35.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.36.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.36.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.input_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.37.mlp.down_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.mlp.up_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.post_attention_layernorm.weight": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.37.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.38.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.38.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.38.mlp.gate_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.38.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.38.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.38.self_attn.k_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.38.self_attn.k_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.38.self_attn.o_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.38.self_attn.q_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.38.self_attn.q_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.38.self_attn.v_proj.bias": "model-00004-of-00007.safetensors",
"model.layers.38.self_attn.v_proj.weight": "model-00004-of-00007.safetensors",
"model.layers.39.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.39.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.39.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.39.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.39.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.39.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.4.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.4.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.40.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.40.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.40.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.40.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.40.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.40.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.41.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.41.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.42.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.42.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.43.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.43.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.44.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.44.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.45.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.45.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.46.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.46.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.input_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.47.mlp.down_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.mlp.up_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.post_attention_layernorm.weight": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.47.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.48.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.48.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.48.mlp.gate_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.48.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.48.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.48.self_attn.k_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.48.self_attn.k_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.48.self_attn.o_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.48.self_attn.q_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.48.self_attn.q_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.48.self_attn.v_proj.bias": "model-00005-of-00007.safetensors",
"model.layers.48.self_attn.v_proj.weight": "model-00005-of-00007.safetensors",
"model.layers.49.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.49.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.49.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.49.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.49.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.49.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.5.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.5.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.5.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.50.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.50.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.50.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.50.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.50.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.50.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.51.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.51.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.52.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.52.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.53.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.53.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.54.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.54.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.55.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.55.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.56.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.56.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.input_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.57.mlp.down_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.mlp.up_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.post_attention_layernorm.weight": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.57.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.58.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.58.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.58.mlp.gate_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.58.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.58.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.58.self_attn.k_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.58.self_attn.k_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.58.self_attn.o_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.58.self_attn.q_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.58.self_attn.q_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.58.self_attn.v_proj.bias": "model-00006-of-00007.safetensors",
"model.layers.58.self_attn.v_proj.weight": "model-00006-of-00007.safetensors",
"model.layers.59.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.59.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.59.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.59.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.59.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.59.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.6.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.6.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.6.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.60.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.60.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.60.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.60.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.60.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.60.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.61.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.61.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.62.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.62.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.input_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.63.mlp.down_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.mlp.gate_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.mlp.up_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.post_attention_layernorm.weight": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.k_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.k_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.o_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.q_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.q_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.v_proj.bias": "model-00007-of-00007.safetensors",
"model.layers.63.self_attn.v_proj.weight": "model-00007-of-00007.safetensors",
"model.layers.7.input_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.7.mlp.down_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.7.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.7.mlp.up_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.7.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.8.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.mlp.gate_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.8.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.8.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.8.self_attn.k_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.8.self_attn.o_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.8.self_attn.q_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00007.safetensors",
"model.layers.8.self_attn.v_proj.weight": "model-00001-of-00007.safetensors",
"model.layers.9.input_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.down_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.gate_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.mlp.up_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.post_attention_layernorm.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.k_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.k_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.o_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.q_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.q_proj.weight": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.v_proj.bias": "model-00002-of-00007.safetensors",
"model.layers.9.self_attn.v_proj.weight": "model-00002-of-00007.safetensors",
"model.norm.weight": "model-00007-of-00007.safetensors"
}
}

3
results.png Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:12bd064838a852acffc6eda3fd51c9c5a08292c324bd1760f5cf4dc5882ce219
size 116722

31
special_tokens_map.json Normal file
View File

@@ -0,0 +1,31 @@
{
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"eos_token": {
"content": "<|im_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
},
"pad_token": {
"content": "<|endoftext|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false
}
}

3
tokenizer.json Normal file
View File

@@ -0,0 +1,3 @@
version https://git-lfs.github.com/spec/v1
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
size 11421896

208
tokenizer_config.json Normal file
View File

@@ -0,0 +1,208 @@
{
"add_bos_token": false,
"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
},
"151646": {
"content": "<|object_ref_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151647": {
"content": "<|object_ref_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151648": {
"content": "<|box_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151649": {
"content": "<|box_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151650": {
"content": "<|quad_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151651": {
"content": "<|quad_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151652": {
"content": "<|vision_start|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151653": {
"content": "<|vision_end|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151654": {
"content": "<|vision_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151655": {
"content": "<|image_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151656": {
"content": "<|video_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"151657": {
"content": "<tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151658": {
"content": "</tool_call>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151659": {
"content": "<|fim_prefix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151660": {
"content": "<|fim_middle|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151661": {
"content": "<|fim_suffix|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151662": {
"content": "<|fim_pad|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151663": {
"content": "<|repo_name|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
},
"151664": {
"content": "<|file_sep|>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": false
}
},
"additional_special_tokens": [
"<|im_start|>",
"<|im_end|>",
"<|object_ref_start|>",
"<|object_ref_end|>",
"<|box_start|>",
"<|box_end|>",
"<|quad_start|>",
"<|quad_end|>",
"<|vision_start|>",
"<|vision_end|>",
"<|vision_pad|>",
"<|image_pad|>",
"<|video_pad|>"
],
"bos_token": null,
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- 'You are Qwen, created by Alibaba Cloud. You are a helpful assistant.' }}\n {%- endif %}\n {{- \"\\n\\n# Tools\\n\\nYou may call one or more functions to assist with the user query.\\n\\nYou are provided with function signatures within <tools></tools> XML tags:\\n<tools>\" }}\n {%- for tool in tools %}\n {{- \"\\n\" }}\n {{- tool | tojson }}\n {%- endfor %}\n {{- \"\\n</tools>\\n\\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\\n<tool_call>\\n{\\\"name\\\": <function-name>, \\\"arguments\\\": <args-json-object>}\\n</tool_call><|im_end|>\\n\" }}\n{%- else %}\n {%- if messages[0]['role'] == 'system' %}\n {{- '<|im_start|>system\\n' + messages[0]['content'] + '<|im_end|>\\n' }}\n {%- else %}\n {{- '<|im_start|>system\\nYou are Qwen, created by Alibaba Cloud. You are a helpful assistant.<|im_end|>\\n' }}\n {%- endif %}\n{%- endif %}\n{%- for message in messages %}\n {%- if (message.role == \"user\") or (message.role == \"system\" and not loop.first) or (message.role == \"assistant\" and not message.tool_calls) %}\n {{- '<|im_start|>' + message.role + '\\n' + message.content + '<|im_end|>' + '\\n' }}\n {%- elif message.role == \"assistant\" %}\n {{- '<|im_start|>' + message.role }}\n {%- if message.content %}\n {{- '\\n' + message.content }}\n {%- endif %}\n {%- for tool_call in message.tool_calls %}\n {%- if tool_call.function is defined %}\n {%- set tool_call = tool_call.function %}\n {%- endif %}\n {{- '\\n<tool_call>\\n{\"name\": \"' }}\n {{- tool_call.name }}\n {{- '\", \"arguments\": ' }}\n {{- tool_call.arguments | tojson }}\n {{- '}\\n</tool_call>' }}\n {%- endfor %}\n {{- '<|im_end|>\\n' }}\n {%- elif message.role == \"tool\" %}\n {%- if (loop.index0 == 0) or (messages[loop.index0 - 1].role != \"tool\") %}\n {{- '<|im_start|>user' }}\n {%- endif %}\n {{- '\\n<tool_response>\\n' }}\n {{- message.content }}\n {{- '\\n</tool_response>' }}\n {%- if loop.last or (messages[loop.index0 + 1].role != \"tool\") %}\n {{- '<|im_end|>\\n' }}\n {%- endif %}\n {%- endif %}\n{%- endfor %}\n{%- if add_generation_prompt %}\n {{- '<|im_start|>assistant\\n' }}\n{%- endif %}\n",
"clean_up_tokenization_spaces": false,
"eos_token": "<|im_end|>",
"errors": "replace",
"extra_special_tokens": {},
"model_max_length": 131072,
"pad_token": "<|endoftext|>",
"split_special_tokens": false,
"tokenizer_class": "Qwen2Tokenizer",
"unk_token": null
}

1
vocab.json Normal file
View File

File diff suppressed because one or more lines are too long