Duplicate from Benasd/Qwen2.5-VL-7B-Instruct-AWQ
Browse filesCo-authored-by: Ben Tso <[email protected]>
- .gitattributes +36 -0
- README.md +529 -0
- added_tokens.json +24 -0
- chat_template.json +3 -0
- config.json +59 -0
- generation_config.json +14 -0
- merges.txt +0 -0
- model-00001-of-00002.safetensors +3 -0
- model-00002-of-00002.safetensors +3 -0
- model.safetensors.index.json +1128 -0
- preprocessor_config.json +29 -0
- special_tokens_map.json +31 -0
- tokenizer.json +3 -0
- tokenizer_config.json +208 -0
- vocab.json +0 -0
.gitattributes
ADDED
|
@@ -0,0 +1,36 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
| 2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
| 3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
| 4 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
| 5 |
+
*.ckpt filter=lfs diff=lfs merge=lfs -text
|
| 6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
| 7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
| 8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
| 9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
| 10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
| 11 |
+
*.mlmodel filter=lfs diff=lfs merge=lfs -text
|
| 12 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
| 13 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
| 14 |
+
*.npy filter=lfs diff=lfs merge=lfs -text
|
| 15 |
+
*.npz filter=lfs diff=lfs merge=lfs -text
|
| 16 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
| 17 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
| 18 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
| 19 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
| 20 |
+
*.pickle filter=lfs diff=lfs merge=lfs -text
|
| 21 |
+
*.pkl filter=lfs diff=lfs merge=lfs -text
|
| 22 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
| 23 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
| 24 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
| 25 |
+
*.safetensors filter=lfs diff=lfs merge=lfs -text
|
| 26 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
| 27 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
| 28 |
+
*.tar filter=lfs diff=lfs merge=lfs -text
|
| 29 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
| 30 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
| 31 |
+
*.wasm filter=lfs diff=lfs merge=lfs -text
|
| 32 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
| 33 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
+
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
|
@@ -0,0 +1,529 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
license: apache-2.0
|
| 3 |
+
language:
|
| 4 |
+
- en
|
| 5 |
+
pipeline_tag: image-text-to-text
|
| 6 |
+
tags:
|
| 7 |
+
- multimodal
|
| 8 |
+
library_name: transformers
|
| 9 |
+
base_model:
|
| 10 |
+
- Qwen/Qwen2.5-VL-7B-Instruct
|
| 11 |
+
---
|
| 12 |
+
|
| 13 |
+
# Qwen2.5-VL-7B-Instruct
|
| 14 |
+
<a href="https://chat.qwenlm.ai/" target="_blank" style="margin: 2px;">
|
| 15 |
+
<img alt="Chat" src="https://img.shields.io/badge/%F0%9F%92%9C%EF%B8%8F%20Qwen%20Chat%20-536af5" style="display: inline-block; vertical-align: middle;"/>
|
| 16 |
+
</a>
|
| 17 |
+
|
| 18 |
+
## Introduction
|
| 19 |
+
|
| 20 |
+
In the past five months since Qwen2-VL’s release, numerous developers have built new models on the Qwen2-VL vision-language models, providing us with valuable feedback. During this period, we focused on building more useful vision-language models. Today, we are excited to introduce the latest addition to the Qwen family: Qwen2.5-VL.
|
| 21 |
+
|
| 22 |
+
#### Key Enhancements:
|
| 23 |
+
* **Understand things visually**: Qwen2.5-VL is not only proficient in recognizing common objects such as flowers, birds, fish, and insects, but it is highly capable of analyzing texts, charts, icons, graphics, and layouts within images.
|
| 24 |
+
|
| 25 |
+
* **Being agentic**: Qwen2.5-VL directly plays as a visual agent that can reason and dynamically direct tools, which is capable of computer use and phone use.
|
| 26 |
+
|
| 27 |
+
* **Understanding long videos and capturing events**: Qwen2.5-VL can comprehend videos of over 1 hour, and this time it has a new ability of cpaturing event by pinpointing the relevant video segments.
|
| 28 |
+
|
| 29 |
+
* **Capable of visual localization in different formats**: Qwen2.5-VL can accurately localize objects in an image by generating bounding boxes or points, and it can provide stable JSON outputs for coordinates and attributes.
|
| 30 |
+
|
| 31 |
+
* **Generating structured outputs**: for data like scans of invoices, forms, tables, etc. Qwen2.5-VL supports structured outputs of their contents, benefiting usages in finance, commerce, etc.
|
| 32 |
+
|
| 33 |
+
|
| 34 |
+
#### Model Architecture Updates:
|
| 35 |
+
|
| 36 |
+
* **Dynamic Resolution and Frame Rate Training for Video Understanding**:
|
| 37 |
+
|
| 38 |
+
We extend dynamic resolution to the temporal dimension by adopting dynamic FPS sampling, enabling the model to comprehend videos at various sampling rates. Accordingly, we update mRoPE in the time dimension with IDs and absolute time alignment, enabling the model to learn temporal sequence and speed, and ultimately acquire the ability to pinpoint specific moments.
|
| 39 |
+
|
| 40 |
+
<p align="center">
|
| 41 |
+
<img src="https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2.5-VL/qwen2.5vl_arc.jpeg" width="80%"/>
|
| 42 |
+
<p>
|
| 43 |
+
|
| 44 |
+
|
| 45 |
+
* **Streamlined and Efficient Vision Encoder**
|
| 46 |
+
|
| 47 |
+
We enhance both training and inference speeds by strategically implementing window attention into the ViT. The ViT architecture is further optimized with SwiGLU and RMSNorm, aligning it with the structure of the Qwen2.5 LLM.
|
| 48 |
+
|
| 49 |
+
|
| 50 |
+
We have three models with 3, 7 and 72 billion parameters. This repo contains the instruction-tuned 7B Qwen2.5-VL model. For more information, visit our [Blog](https://qwenlm.github.io/blog/qwen2.5-vl/) and [GitHub](https://github.com/QwenLM/Qwen2.5-VL).
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
## Evaluation
|
| 55 |
+
|
| 56 |
+
### Image benchmark
|
| 57 |
+
|
| 58 |
+
|
| 59 |
+
| Benchmark | InternVL2.5-8B | MiniCPM-o 2.6 | GPT-4o-mini | Qwen2-VL-7B |**Qwen2.5-VL-7B** |
|
| 60 |
+
| :--- | :---: | :---: | :---: | :---: | :---: |
|
| 61 |
+
| MMMU<sub>val</sub> | 56 | 50.4 | **60**| 54.1 | 58.6|
|
| 62 |
+
| MMMU-Pro<sub>val</sub> | 34.3 | - | 37.6| 30.5 | 41.0|
|
| 63 |
+
| DocVQA<sub>test</sub> | 93 | 93 | - | 94.5 | **95.7** |
|
| 64 |
+
| InfoVQA<sub>test</sub> | 77.6 | - | - |76.5 | **82.6** |
|
| 65 |
+
| ChartQA<sub>test</sub> | 84.8 | - |- | 83.0 |**87.3** |
|
| 66 |
+
| TextVQA<sub>val</sub> | 79.1 | 80.1 | -| 84.3 | **84.9**|
|
| 67 |
+
| OCRBench | 822 | 852 | 785 | 845 | **864** |
|
| 68 |
+
| CC_OCR | 57.7 | | | 61.6 | **77.8**|
|
| 69 |
+
| MMStar | 62.8| | |60.7| **63.9**|
|
| 70 |
+
| MMBench-V1.1-En<sub>test</sub> | 79.4 | 78.0 | 76.0| 80.7 | **82.6** |
|
| 71 |
+
| MMT-Bench<sub>test</sub> | - | - | - |**63.7** |63.6 |
|
| 72 |
+
| MMStar | **61.5** | 57.5 | 54.8 | 60.7 |63.9 |
|
| 73 |
+
| MMVet<sub>GPT-4-Turbo</sub> | 54.2 | 60.0 | 66.9 | 62.0 | **67.1**|
|
| 74 |
+
| HallBench<sub>avg</sub> | 45.2 | 48.1 | 46.1| 50.6 | **52.9**|
|
| 75 |
+
| MathVista<sub>testmini</sub> | 58.3 | 60.6 | 52.4 | 58.2 | **68.2**|
|
| 76 |
+
| MathVision | - | - | - | 16.3 | **25.07** |
|
| 77 |
+
|
| 78 |
+
### Video Benchmarks
|
| 79 |
+
|
| 80 |
+
| Benchmark | Qwen2-VL-7B | **Qwen2.5-VL-7B** |
|
| 81 |
+
| :--- | :---: | :---: |
|
| 82 |
+
| MVBench | 67.0 | **69.6** |
|
| 83 |
+
| PerceptionTest<sub>test</sub> | 66.9 | **70.5** |
|
| 84 |
+
| Video-MME<sub>wo/w subs</sub> | 63.3/69.0 | **65.1**/**71.6** |
|
| 85 |
+
| LVBench | | 45.3 |
|
| 86 |
+
| LongVideoBench | | 54.7 |
|
| 87 |
+
| MMBench-Video | 1.44 | 1.79 |
|
| 88 |
+
| TempCompass | | 71.7 |
|
| 89 |
+
| MLVU | | 70.2 |
|
| 90 |
+
| CharadesSTA/mIoU | 43.6|
|
| 91 |
+
|
| 92 |
+
### Agent benchmark
|
| 93 |
+
| Benchmarks | Qwen2.5-VL-7B |
|
| 94 |
+
|-------------------------|---------------|
|
| 95 |
+
| ScreenSpot | 84.7 |
|
| 96 |
+
| ScreenSpot Pro | 29.0 |
|
| 97 |
+
| AITZ_EM | 81.9 |
|
| 98 |
+
| Android Control High_EM | 60.1 |
|
| 99 |
+
| Android Control Low_EM | 93.7 |
|
| 100 |
+
| AndroidWorld_SR | 25.5 |
|
| 101 |
+
| MobileMiniWob++_SR | 91.4 |
|
| 102 |
+
|
| 103 |
+
## Requirements
|
| 104 |
+
The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
|
| 105 |
+
```
|
| 106 |
+
pip install git+https://github.com/huggingface/transformers accelerate
|
| 107 |
+
```
|
| 108 |
+
or you might encounter the following error:
|
| 109 |
+
```
|
| 110 |
+
KeyError: 'qwen2_5_vl'
|
| 111 |
+
```
|
| 112 |
+
|
| 113 |
+
|
| 114 |
+
## Quickstart
|
| 115 |
+
|
| 116 |
+
Below, we provide simple examples to show how to use Qwen2.5-VL with 🤖 ModelScope and 🤗 Transformers.
|
| 117 |
+
|
| 118 |
+
The code of Qwen2.5-VL has been in the latest Hugging face transformers and we advise you to build from source with command:
|
| 119 |
+
```
|
| 120 |
+
pip install git+https://github.com/huggingface/transformers accelerate
|
| 121 |
+
```
|
| 122 |
+
or you might encounter the following error:
|
| 123 |
+
```
|
| 124 |
+
KeyError: 'qwen2_5_vl'
|
| 125 |
+
```
|
| 126 |
+
|
| 127 |
+
|
| 128 |
+
We offer a toolkit to help you handle various types of visual input more conveniently, as if you were using an API. This includes base64, URLs, and interleaved images and videos. You can install it using the following command:
|
| 129 |
+
|
| 130 |
+
```bash
|
| 131 |
+
# It's highly recommanded to use `[decord]` feature for faster video loading.
|
| 132 |
+
pip install qwen-vl-utils[decord]==0.0.8
|
| 133 |
+
```
|
| 134 |
+
|
| 135 |
+
If you are not using Linux, you might not be able to install `decord` from PyPI. In that case, you can use `pip install qwen-vl-utils` which will fall back to using torchvision for video processing. However, you can still [install decord from source](https://github.com/dmlc/decord?tab=readme-ov-file#install-from-source) to get decord used when loading video.
|
| 136 |
+
|
| 137 |
+
### Using 🤗 Transformers to Chat
|
| 138 |
+
|
| 139 |
+
Here we show a code snippet to show you how to use the chat model with `transformers` and `qwen_vl_utils`:
|
| 140 |
+
|
| 141 |
+
```python
|
| 142 |
+
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
| 143 |
+
from qwen_vl_utils import process_vision_info
|
| 144 |
+
|
| 145 |
+
# default: Load the model on the available device(s)
|
| 146 |
+
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
| 147 |
+
"Qwen/Qwen2.5-VL-7B-Instruct", torch_dtype="auto", device_map="auto"
|
| 148 |
+
)
|
| 149 |
+
|
| 150 |
+
# We recommend enabling flash_attention_2 for better acceleration and memory saving, especially in multi-image and video scenarios.
|
| 151 |
+
# model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
| 152 |
+
# "Qwen/Qwen2.5-VL-7B-Instruct",
|
| 153 |
+
# torch_dtype=torch.bfloat16,
|
| 154 |
+
# attn_implementation="flash_attention_2",
|
| 155 |
+
# device_map="auto",
|
| 156 |
+
# )
|
| 157 |
+
|
| 158 |
+
# default processer
|
| 159 |
+
processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct")
|
| 160 |
+
|
| 161 |
+
# The default range for the number of visual tokens per image in the model is 4-16384.
|
| 162 |
+
# You can set min_pixels and max_pixels according to your needs, such as a token range of 256-1280, to balance performance and cost.
|
| 163 |
+
# min_pixels = 256*28*28
|
| 164 |
+
# max_pixels = 1280*28*28
|
| 165 |
+
# processor = AutoProcessor.from_pretrained("Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels)
|
| 166 |
+
|
| 167 |
+
messages = [
|
| 168 |
+
{
|
| 169 |
+
"role": "user",
|
| 170 |
+
"content": [
|
| 171 |
+
{
|
| 172 |
+
"type": "image",
|
| 173 |
+
"image": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen-VL/assets/demo.jpeg",
|
| 174 |
+
},
|
| 175 |
+
{"type": "text", "text": "Describe this image."},
|
| 176 |
+
],
|
| 177 |
+
}
|
| 178 |
+
]
|
| 179 |
+
|
| 180 |
+
# Preparation for inference
|
| 181 |
+
text = processor.apply_chat_template(
|
| 182 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 183 |
+
)
|
| 184 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 185 |
+
inputs = processor(
|
| 186 |
+
text=[text],
|
| 187 |
+
images=image_inputs,
|
| 188 |
+
videos=video_inputs,
|
| 189 |
+
padding=True,
|
| 190 |
+
return_tensors="pt",
|
| 191 |
+
)
|
| 192 |
+
inputs = inputs.to("cuda")
|
| 193 |
+
|
| 194 |
+
# Inference: Generation of the output
|
| 195 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 196 |
+
generated_ids_trimmed = [
|
| 197 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 198 |
+
]
|
| 199 |
+
output_text = processor.batch_decode(
|
| 200 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 201 |
+
)
|
| 202 |
+
print(output_text)
|
| 203 |
+
```
|
| 204 |
+
<details>
|
| 205 |
+
<summary>Multi image inference</summary>
|
| 206 |
+
|
| 207 |
+
```python
|
| 208 |
+
# Messages containing multiple images and a text query
|
| 209 |
+
messages = [
|
| 210 |
+
{
|
| 211 |
+
"role": "user",
|
| 212 |
+
"content": [
|
| 213 |
+
{"type": "image", "image": "file:///path/to/image1.jpg"},
|
| 214 |
+
{"type": "image", "image": "file:///path/to/image2.jpg"},
|
| 215 |
+
{"type": "text", "text": "Identify the similarities between these images."},
|
| 216 |
+
],
|
| 217 |
+
}
|
| 218 |
+
]
|
| 219 |
+
|
| 220 |
+
# Preparation for inference
|
| 221 |
+
text = processor.apply_chat_template(
|
| 222 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 223 |
+
)
|
| 224 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 225 |
+
inputs = processor(
|
| 226 |
+
text=[text],
|
| 227 |
+
images=image_inputs,
|
| 228 |
+
videos=video_inputs,
|
| 229 |
+
padding=True,
|
| 230 |
+
return_tensors="pt",
|
| 231 |
+
)
|
| 232 |
+
inputs = inputs.to("cuda")
|
| 233 |
+
|
| 234 |
+
# Inference
|
| 235 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 236 |
+
generated_ids_trimmed = [
|
| 237 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 238 |
+
]
|
| 239 |
+
output_text = processor.batch_decode(
|
| 240 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 241 |
+
)
|
| 242 |
+
print(output_text)
|
| 243 |
+
```
|
| 244 |
+
</details>
|
| 245 |
+
|
| 246 |
+
<details>
|
| 247 |
+
<summary>Video inference</summary>
|
| 248 |
+
|
| 249 |
+
```python
|
| 250 |
+
# Messages containing a images list as a video and a text query
|
| 251 |
+
messages = [
|
| 252 |
+
{
|
| 253 |
+
"role": "user",
|
| 254 |
+
"content": [
|
| 255 |
+
{
|
| 256 |
+
"type": "video",
|
| 257 |
+
"video": [
|
| 258 |
+
"file:///path/to/frame1.jpg",
|
| 259 |
+
"file:///path/to/frame2.jpg",
|
| 260 |
+
"file:///path/to/frame3.jpg",
|
| 261 |
+
"file:///path/to/frame4.jpg",
|
| 262 |
+
],
|
| 263 |
+
},
|
| 264 |
+
{"type": "text", "text": "Describe this video."},
|
| 265 |
+
],
|
| 266 |
+
}
|
| 267 |
+
]
|
| 268 |
+
|
| 269 |
+
# Messages containing a local video path and a text query
|
| 270 |
+
messages = [
|
| 271 |
+
{
|
| 272 |
+
"role": "user",
|
| 273 |
+
"content": [
|
| 274 |
+
{
|
| 275 |
+
"type": "video",
|
| 276 |
+
"video": "file:///path/to/video1.mp4",
|
| 277 |
+
"max_pixels": 360 * 420,
|
| 278 |
+
"fps": 1.0,
|
| 279 |
+
},
|
| 280 |
+
{"type": "text", "text": "Describe this video."},
|
| 281 |
+
],
|
| 282 |
+
}
|
| 283 |
+
]
|
| 284 |
+
|
| 285 |
+
# Messages containing a video url and a text query
|
| 286 |
+
messages = [
|
| 287 |
+
{
|
| 288 |
+
"role": "user",
|
| 289 |
+
"content": [
|
| 290 |
+
{
|
| 291 |
+
"type": "video",
|
| 292 |
+
"video": "https://qianwen-res.oss-cn-beijing.aliyuncs.com/Qwen2-VL/space_woaudio.mp4",
|
| 293 |
+
},
|
| 294 |
+
{"type": "text", "text": "Describe this video."},
|
| 295 |
+
],
|
| 296 |
+
}
|
| 297 |
+
]
|
| 298 |
+
|
| 299 |
+
#In Qwen 2.5 VL, frame rate information is also input into the model to align with absolute time.
|
| 300 |
+
# Preparation for inference
|
| 301 |
+
text = processor.apply_chat_template(
|
| 302 |
+
messages, tokenize=False, add_generation_prompt=True
|
| 303 |
+
)
|
| 304 |
+
image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True)
|
| 305 |
+
inputs = processor(
|
| 306 |
+
text=[text],
|
| 307 |
+
images=image_inputs,
|
| 308 |
+
videos=video_inputs,
|
| 309 |
+
fps=fps,
|
| 310 |
+
padding=True,
|
| 311 |
+
return_tensors="pt",
|
| 312 |
+
**video_kwargs,
|
| 313 |
+
)
|
| 314 |
+
inputs = inputs.to("cuda")
|
| 315 |
+
|
| 316 |
+
# Inference
|
| 317 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 318 |
+
generated_ids_trimmed = [
|
| 319 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 320 |
+
]
|
| 321 |
+
output_text = processor.batch_decode(
|
| 322 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 323 |
+
)
|
| 324 |
+
print(output_text)
|
| 325 |
+
```
|
| 326 |
+
|
| 327 |
+
Video URL compatibility largely depends on the third-party library version. The details are in the table below. change the backend by `FORCE_QWENVL_VIDEO_READER=torchvision` or `FORCE_QWENVL_VIDEO_READER=decord` if you prefer not to use the default one.
|
| 328 |
+
|
| 329 |
+
| Backend | HTTP | HTTPS |
|
| 330 |
+
|-------------|------|-------|
|
| 331 |
+
| torchvision >= 0.19.0 | ✅ | ✅ |
|
| 332 |
+
| torchvision < 0.19.0 | ❌ | ❌ |
|
| 333 |
+
| decord | ✅ | ❌ |
|
| 334 |
+
</details>
|
| 335 |
+
|
| 336 |
+
<details>
|
| 337 |
+
<summary>Batch inference</summary>
|
| 338 |
+
|
| 339 |
+
```python
|
| 340 |
+
# Sample messages for batch inference
|
| 341 |
+
messages1 = [
|
| 342 |
+
{
|
| 343 |
+
"role": "user",
|
| 344 |
+
"content": [
|
| 345 |
+
{"type": "image", "image": "file:///path/to/image1.jpg"},
|
| 346 |
+
{"type": "image", "image": "file:///path/to/image2.jpg"},
|
| 347 |
+
{"type": "text", "text": "What are the common elements in these pictures?"},
|
| 348 |
+
],
|
| 349 |
+
}
|
| 350 |
+
]
|
| 351 |
+
messages2 = [
|
| 352 |
+
{"role": "system", "content": "You are a helpful assistant."},
|
| 353 |
+
{"role": "user", "content": "Who are you?"},
|
| 354 |
+
]
|
| 355 |
+
# Combine messages for batch processing
|
| 356 |
+
messages = [messages1, messages2]
|
| 357 |
+
|
| 358 |
+
# Preparation for batch inference
|
| 359 |
+
texts = [
|
| 360 |
+
processor.apply_chat_template(msg, tokenize=False, add_generation_prompt=True)
|
| 361 |
+
for msg in messages
|
| 362 |
+
]
|
| 363 |
+
image_inputs, video_inputs = process_vision_info(messages)
|
| 364 |
+
inputs = processor(
|
| 365 |
+
text=texts,
|
| 366 |
+
images=image_inputs,
|
| 367 |
+
videos=video_inputs,
|
| 368 |
+
padding=True,
|
| 369 |
+
return_tensors="pt",
|
| 370 |
+
)
|
| 371 |
+
inputs = inputs.to("cuda")
|
| 372 |
+
|
| 373 |
+
# Batch Inference
|
| 374 |
+
generated_ids = model.generate(**inputs, max_new_tokens=128)
|
| 375 |
+
generated_ids_trimmed = [
|
| 376 |
+
out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)
|
| 377 |
+
]
|
| 378 |
+
output_texts = processor.batch_decode(
|
| 379 |
+
generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False
|
| 380 |
+
)
|
| 381 |
+
print(output_texts)
|
| 382 |
+
```
|
| 383 |
+
</details>
|
| 384 |
+
|
| 385 |
+
### 🤖 ModelScope
|
| 386 |
+
We strongly advise users especially those in mainland China to use ModelScope. `snapshot_download` can help you solve issues concerning downloading checkpoints.
|
| 387 |
+
|
| 388 |
+
|
| 389 |
+
### More Usage Tips
|
| 390 |
+
|
| 391 |
+
For input images, we support local files, base64, and URLs. For videos, we currently only support local files.
|
| 392 |
+
|
| 393 |
+
```python
|
| 394 |
+
# You can directly insert a local file path, a URL, or a base64-encoded image into the position where you want in the text.
|
| 395 |
+
## Local file path
|
| 396 |
+
messages = [
|
| 397 |
+
{
|
| 398 |
+
"role": "user",
|
| 399 |
+
"content": [
|
| 400 |
+
{"type": "image", "image": "file:///path/to/your/image.jpg"},
|
| 401 |
+
{"type": "text", "text": "Describe this image."},
|
| 402 |
+
],
|
| 403 |
+
}
|
| 404 |
+
]
|
| 405 |
+
## Image URL
|
| 406 |
+
messages = [
|
| 407 |
+
{
|
| 408 |
+
"role": "user",
|
| 409 |
+
"content": [
|
| 410 |
+
{"type": "image", "image": "http://path/to/your/image.jpg"},
|
| 411 |
+
{"type": "text", "text": "Describe this image."},
|
| 412 |
+
],
|
| 413 |
+
}
|
| 414 |
+
]
|
| 415 |
+
## Base64 encoded image
|
| 416 |
+
messages = [
|
| 417 |
+
{
|
| 418 |
+
"role": "user",
|
| 419 |
+
"content": [
|
| 420 |
+
{"type": "image", "image": "data:image;base64,/9j/..."},
|
| 421 |
+
{"type": "text", "text": "Describe this image."},
|
| 422 |
+
],
|
| 423 |
+
}
|
| 424 |
+
]
|
| 425 |
+
```
|
| 426 |
+
#### Image Resolution for performance boost
|
| 427 |
+
|
| 428 |
+
The model supports a wide range of resolution inputs. By default, it uses the native resolution for input, but higher resolutions can enhance performance at the cost of more computation. Users can set the minimum and maximum number of pixels to achieve an optimal configuration for their needs, such as a token count range of 256-1280, to balance speed and memory usage.
|
| 429 |
+
|
| 430 |
+
```python
|
| 431 |
+
min_pixels = 256 * 28 * 28
|
| 432 |
+
max_pixels = 1280 * 28 * 28
|
| 433 |
+
processor = AutoProcessor.from_pretrained(
|
| 434 |
+
"Qwen/Qwen2.5-VL-7B-Instruct", min_pixels=min_pixels, max_pixels=max_pixels
|
| 435 |
+
)
|
| 436 |
+
```
|
| 437 |
+
|
| 438 |
+
Besides, We provide two methods for fine-grained control over the image size input to the model:
|
| 439 |
+
|
| 440 |
+
1. Define min_pixels and max_pixels: Images will be resized to maintain their aspect ratio within the range of min_pixels and max_pixels.
|
| 441 |
+
|
| 442 |
+
2. Specify exact dimensions: Directly set `resized_height` and `resized_width`. These values will be rounded to the nearest multiple of 28.
|
| 443 |
+
|
| 444 |
+
```python
|
| 445 |
+
# min_pixels and max_pixels
|
| 446 |
+
messages = [
|
| 447 |
+
{
|
| 448 |
+
"role": "user",
|
| 449 |
+
"content": [
|
| 450 |
+
{
|
| 451 |
+
"type": "image",
|
| 452 |
+
"image": "file:///path/to/your/image.jpg",
|
| 453 |
+
"resized_height": 280,
|
| 454 |
+
"resized_width": 420,
|
| 455 |
+
},
|
| 456 |
+
{"type": "text", "text": "Describe this image."},
|
| 457 |
+
],
|
| 458 |
+
}
|
| 459 |
+
]
|
| 460 |
+
# resized_height and resized_width
|
| 461 |
+
messages = [
|
| 462 |
+
{
|
| 463 |
+
"role": "user",
|
| 464 |
+
"content": [
|
| 465 |
+
{
|
| 466 |
+
"type": "image",
|
| 467 |
+
"image": "file:///path/to/your/image.jpg",
|
| 468 |
+
"min_pixels": 50176,
|
| 469 |
+
"max_pixels": 50176,
|
| 470 |
+
},
|
| 471 |
+
{"type": "text", "text": "Describe this image."},
|
| 472 |
+
],
|
| 473 |
+
}
|
| 474 |
+
]
|
| 475 |
+
```
|
| 476 |
+
|
| 477 |
+
### Processing Long Texts
|
| 478 |
+
|
| 479 |
+
The current `config.json` is set for context length up to 32,768 tokens.
|
| 480 |
+
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.
|
| 481 |
+
|
| 482 |
+
For supported frameworks, you could add the following to `config.json` to enable YaRN:
|
| 483 |
+
|
| 484 |
+
{
|
| 485 |
+
...,
|
| 486 |
+
"type": "yarn",
|
| 487 |
+
"mrope_section": [
|
| 488 |
+
16,
|
| 489 |
+
24,
|
| 490 |
+
24
|
| 491 |
+
],
|
| 492 |
+
"factor": 4,
|
| 493 |
+
"original_max_position_embeddings": 32768
|
| 494 |
+
}
|
| 495 |
+
|
| 496 |
+
However, it should be noted that this method has a significant impact on the performance of temporal and spatial localization tasks, and is therefore not recommended for use.
|
| 497 |
+
|
| 498 |
+
At the same time, for long video inputs, since MRoPE itself is more economical with ids, the max_position_embeddings can be directly modified to a larger value, such as 64k.
|
| 499 |
+
|
| 500 |
+
|
| 501 |
+
|
| 502 |
+
|
| 503 |
+
## Citation
|
| 504 |
+
|
| 505 |
+
If you find our work helpful, feel free to give us a cite.
|
| 506 |
+
|
| 507 |
+
```
|
| 508 |
+
@misc{qwen2.5-VL,
|
| 509 |
+
title = {Qwen2.5-VL},
|
| 510 |
+
url = {https://qwenlm.github.io/blog/qwen2.5-vl/},
|
| 511 |
+
author = {Qwen Team},
|
| 512 |
+
month = {January},
|
| 513 |
+
year = {2025}
|
| 514 |
+
}
|
| 515 |
+
|
| 516 |
+
@article{Qwen2VL,
|
| 517 |
+
title={Qwen2-VL: Enhancing Vision-Language Model's Perception of the World at Any Resolution},
|
| 518 |
+
author={Wang, Peng and Bai, Shuai and Tan, Sinan and Wang, Shijie and Fan, Zhihao and Bai, Jinze and Chen, Keqin and Liu, Xuejing and Wang, Jialin and Ge, Wenbin and Fan, Yang and Dang, Kai and Du, Mengfei and Ren, Xuancheng and Men, Rui and Liu, Dayiheng and Zhou, Chang and Zhou, Jingren and Lin, Junyang},
|
| 519 |
+
journal={arXiv preprint arXiv:2409.12191},
|
| 520 |
+
year={2024}
|
| 521 |
+
}
|
| 522 |
+
|
| 523 |
+
@article{Qwen-VL,
|
| 524 |
+
title={Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond},
|
| 525 |
+
author={Bai, Jinze and Bai, Shuai and Yang, Shusheng and Wang, Shijie and Tan, Sinan and Wang, Peng and Lin, Junyang and Zhou, Chang and Zhou, Jingren},
|
| 526 |
+
journal={arXiv preprint arXiv:2308.12966},
|
| 527 |
+
year={2023}
|
| 528 |
+
}
|
| 529 |
+
```
|
added_tokens.json
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</tool_call>": 151658,
|
| 3 |
+
"<tool_call>": 151657,
|
| 4 |
+
"<|box_end|>": 151649,
|
| 5 |
+
"<|box_start|>": 151648,
|
| 6 |
+
"<|endoftext|>": 151643,
|
| 7 |
+
"<|file_sep|>": 151664,
|
| 8 |
+
"<|fim_middle|>": 151660,
|
| 9 |
+
"<|fim_pad|>": 151662,
|
| 10 |
+
"<|fim_prefix|>": 151659,
|
| 11 |
+
"<|fim_suffix|>": 151661,
|
| 12 |
+
"<|im_end|>": 151645,
|
| 13 |
+
"<|im_start|>": 151644,
|
| 14 |
+
"<|image_pad|>": 151655,
|
| 15 |
+
"<|object_ref_end|>": 151647,
|
| 16 |
+
"<|object_ref_start|>": 151646,
|
| 17 |
+
"<|quad_end|>": 151651,
|
| 18 |
+
"<|quad_start|>": 151650,
|
| 19 |
+
"<|repo_name|>": 151663,
|
| 20 |
+
"<|video_pad|>": 151656,
|
| 21 |
+
"<|vision_end|>": 151653,
|
| 22 |
+
"<|vision_pad|>": 151654,
|
| 23 |
+
"<|vision_start|>": 151652
|
| 24 |
+
}
|
chat_template.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"chat_template": "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in messages %}{% if loop.first and message['role'] != 'system' %}<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n{% endif %}<|im_start|>{{ message['role'] }}\n{% if message['content'] is string %}{{ message['content'] }}<|im_end|>\n{% else %}{% for content in message['content'] %}{% if content['type'] == 'image' or 'image' in content or 'image_url' in content %}{% set image_count.value = image_count.value + 1 %}{% if add_vision_id %}Picture {{ image_count.value }}: {% endif %}<|vision_start|><|image_pad|><|vision_end|>{% elif content['type'] == 'video' or 'video' in content %}{% set video_count.value = video_count.value + 1 %}{% if add_vision_id %}Video {{ video_count.value }}: {% endif %}<|vision_start|><|video_pad|><|vision_end|>{% elif 'text' in content %}{{ content['text'] }}{% endif %}{% endfor %}<|im_end|>\n{% endif %}{% endfor %}{% if add_generation_prompt %}<|im_start|>assistant\n{% endif %}"
|
| 3 |
+
}
|
config.json
ADDED
|
@@ -0,0 +1,59 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"_name_or_path": "/root/.cache/huggingface/hub/models--Qwen--Qwen2.5-VL-7B-Instruct/snapshots/c6adf136ef57b4f6a6d7897c11bd3863bda237d7",
|
| 3 |
+
"architectures": [
|
| 4 |
+
"Qwen2_5_VLForConditionalGeneration"
|
| 5 |
+
],
|
| 6 |
+
"attention_dropout": 0.0,
|
| 7 |
+
"bos_token_id": 151643,
|
| 8 |
+
"eos_token_id": 151645,
|
| 9 |
+
"hidden_act": "silu",
|
| 10 |
+
"hidden_size": 3584,
|
| 11 |
+
"image_token_id": 151655,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
+
"intermediate_size": 18944,
|
| 14 |
+
"max_position_embeddings": 128000,
|
| 15 |
+
"max_window_layers": 28,
|
| 16 |
+
"model_type": "qwen2_5_vl",
|
| 17 |
+
"num_attention_heads": 28,
|
| 18 |
+
"num_hidden_layers": 28,
|
| 19 |
+
"num_key_value_heads": 4,
|
| 20 |
+
"quantization_config": {
|
| 21 |
+
"bits": 4,
|
| 22 |
+
"group_size": 128,
|
| 23 |
+
"modules_to_not_convert": [
|
| 24 |
+
"visual"
|
| 25 |
+
],
|
| 26 |
+
"quant_method": "awq",
|
| 27 |
+
"version": "gemm",
|
| 28 |
+
"zero_point": true
|
| 29 |
+
},
|
| 30 |
+
"rms_norm_eps": 1e-06,
|
| 31 |
+
"rope_scaling": {
|
| 32 |
+
"mrope_section": [
|
| 33 |
+
16,
|
| 34 |
+
24,
|
| 35 |
+
24
|
| 36 |
+
],
|
| 37 |
+
"rope_type": "default",
|
| 38 |
+
"type": "default"
|
| 39 |
+
},
|
| 40 |
+
"rope_theta": 1000000.0,
|
| 41 |
+
"sliding_window": 32768,
|
| 42 |
+
"tie_word_embeddings": false,
|
| 43 |
+
"torch_dtype": "bfloat16",
|
| 44 |
+
"transformers_version": "4.49.0.dev0",
|
| 45 |
+
"use_cache": true,
|
| 46 |
+
"use_sliding_window": false,
|
| 47 |
+
"video_token_id": 151656,
|
| 48 |
+
"vision_config": {
|
| 49 |
+
"hidden_size": 1280,
|
| 50 |
+
"in_chans": 3,
|
| 51 |
+
"model_type": "qwen2_5_vl",
|
| 52 |
+
"spatial_patch_size": 14,
|
| 53 |
+
"tokens_per_second": 2
|
| 54 |
+
},
|
| 55 |
+
"vision_end_token_id": 151653,
|
| 56 |
+
"vision_start_token_id": 151652,
|
| 57 |
+
"vision_token_id": 151654,
|
| 58 |
+
"vocab_size": 152064
|
| 59 |
+
}
|
generation_config.json
ADDED
|
@@ -0,0 +1,14 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token_id": 151643,
|
| 3 |
+
"do_sample": true,
|
| 4 |
+
"eos_token_id": [
|
| 5 |
+
151645,
|
| 6 |
+
151643
|
| 7 |
+
],
|
| 8 |
+
"pad_token_id": 151643,
|
| 9 |
+
"repetition_penalty": 1.05,
|
| 10 |
+
"temperature": 0.1,
|
| 11 |
+
"top_k": 1,
|
| 12 |
+
"top_p": 0.001,
|
| 13 |
+
"transformers_version": "4.49.0.dev0"
|
| 14 |
+
}
|
merges.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
model-00001-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a150a4a5932255e9493d012ef076178a38e42ae917a82d2dcccd1d67e33bfa3
|
| 3 |
+
size 4994852800
|
model-00002-of-00002.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:838a637a01105df9b31206973d461cc8868bf861089ee3e7cb5e5c8d9d63dfb9
|
| 3 |
+
size 1929119624
|
model.safetensors.index.json
ADDED
|
@@ -0,0 +1,1128 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"metadata": {
|
| 3 |
+
"total_size": 6923847680
|
| 4 |
+
},
|
| 5 |
+
"weight_map": {
|
| 6 |
+
"visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
|
| 7 |
+
"visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
|
| 8 |
+
"visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
|
| 9 |
+
"visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 10 |
+
"visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 11 |
+
"visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 12 |
+
"visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 13 |
+
"visual.blocks.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 14 |
+
"visual.blocks.0.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 15 |
+
"visual.blocks.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 16 |
+
"visual.blocks.0.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 17 |
+
"visual.blocks.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 18 |
+
"visual.blocks.0.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 19 |
+
"visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
|
| 20 |
+
"visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
|
| 21 |
+
"visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 22 |
+
"visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 23 |
+
"visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 24 |
+
"visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 25 |
+
"visual.blocks.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 26 |
+
"visual.blocks.1.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 27 |
+
"visual.blocks.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 28 |
+
"visual.blocks.1.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 29 |
+
"visual.blocks.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 30 |
+
"visual.blocks.1.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 31 |
+
"visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
|
| 32 |
+
"visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
|
| 33 |
+
"visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 34 |
+
"visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 35 |
+
"visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 36 |
+
"visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 37 |
+
"visual.blocks.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 38 |
+
"visual.blocks.2.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 39 |
+
"visual.blocks.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 40 |
+
"visual.blocks.2.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 41 |
+
"visual.blocks.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 42 |
+
"visual.blocks.2.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 43 |
+
"visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
|
| 44 |
+
"visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
|
| 45 |
+
"visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 46 |
+
"visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 47 |
+
"visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 48 |
+
"visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 49 |
+
"visual.blocks.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 50 |
+
"visual.blocks.3.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 51 |
+
"visual.blocks.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 52 |
+
"visual.blocks.3.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 53 |
+
"visual.blocks.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 54 |
+
"visual.blocks.3.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 55 |
+
"visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
|
| 56 |
+
"visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
|
| 57 |
+
"visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 58 |
+
"visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 59 |
+
"visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 60 |
+
"visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 61 |
+
"visual.blocks.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 62 |
+
"visual.blocks.4.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 63 |
+
"visual.blocks.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 64 |
+
"visual.blocks.4.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 65 |
+
"visual.blocks.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 66 |
+
"visual.blocks.4.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 67 |
+
"visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
|
| 68 |
+
"visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
|
| 69 |
+
"visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 70 |
+
"visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 71 |
+
"visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 72 |
+
"visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 73 |
+
"visual.blocks.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 74 |
+
"visual.blocks.5.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 75 |
+
"visual.blocks.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 76 |
+
"visual.blocks.5.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 77 |
+
"visual.blocks.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 78 |
+
"visual.blocks.5.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 79 |
+
"visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
|
| 80 |
+
"visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
|
| 81 |
+
"visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 82 |
+
"visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 83 |
+
"visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 84 |
+
"visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 85 |
+
"visual.blocks.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 86 |
+
"visual.blocks.6.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 87 |
+
"visual.blocks.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 88 |
+
"visual.blocks.6.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 89 |
+
"visual.blocks.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 90 |
+
"visual.blocks.6.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 91 |
+
"visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
|
| 92 |
+
"visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
|
| 93 |
+
"visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 94 |
+
"visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 95 |
+
"visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 96 |
+
"visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 97 |
+
"visual.blocks.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 98 |
+
"visual.blocks.7.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 99 |
+
"visual.blocks.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 100 |
+
"visual.blocks.7.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 101 |
+
"visual.blocks.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 102 |
+
"visual.blocks.7.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 103 |
+
"visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
|
| 104 |
+
"visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
|
| 105 |
+
"visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 106 |
+
"visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 107 |
+
"visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 108 |
+
"visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 109 |
+
"visual.blocks.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 110 |
+
"visual.blocks.8.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 111 |
+
"visual.blocks.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 112 |
+
"visual.blocks.8.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 113 |
+
"visual.blocks.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 114 |
+
"visual.blocks.8.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 115 |
+
"visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
|
| 116 |
+
"visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
|
| 117 |
+
"visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 118 |
+
"visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 119 |
+
"visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 120 |
+
"visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 121 |
+
"visual.blocks.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 122 |
+
"visual.blocks.9.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 123 |
+
"visual.blocks.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 124 |
+
"visual.blocks.9.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 125 |
+
"visual.blocks.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 126 |
+
"visual.blocks.9.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 127 |
+
"visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
|
| 128 |
+
"visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
|
| 129 |
+
"visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 130 |
+
"visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 131 |
+
"visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 132 |
+
"visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 133 |
+
"visual.blocks.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 134 |
+
"visual.blocks.10.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 135 |
+
"visual.blocks.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 136 |
+
"visual.blocks.10.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 137 |
+
"visual.blocks.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 138 |
+
"visual.blocks.10.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 139 |
+
"visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
|
| 140 |
+
"visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
|
| 141 |
+
"visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 142 |
+
"visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 143 |
+
"visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 144 |
+
"visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 145 |
+
"visual.blocks.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 146 |
+
"visual.blocks.11.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 147 |
+
"visual.blocks.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 148 |
+
"visual.blocks.11.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 149 |
+
"visual.blocks.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 150 |
+
"visual.blocks.11.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 151 |
+
"visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
|
| 152 |
+
"visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
|
| 153 |
+
"visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 154 |
+
"visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 155 |
+
"visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 156 |
+
"visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 157 |
+
"visual.blocks.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 158 |
+
"visual.blocks.12.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 159 |
+
"visual.blocks.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 160 |
+
"visual.blocks.12.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 161 |
+
"visual.blocks.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 162 |
+
"visual.blocks.12.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 163 |
+
"visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
|
| 164 |
+
"visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
|
| 165 |
+
"visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 166 |
+
"visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 167 |
+
"visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 168 |
+
"visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 169 |
+
"visual.blocks.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 170 |
+
"visual.blocks.13.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 171 |
+
"visual.blocks.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 172 |
+
"visual.blocks.13.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 173 |
+
"visual.blocks.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 174 |
+
"visual.blocks.13.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 175 |
+
"visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
|
| 176 |
+
"visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
|
| 177 |
+
"visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 178 |
+
"visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 179 |
+
"visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 180 |
+
"visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 181 |
+
"visual.blocks.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 182 |
+
"visual.blocks.14.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 183 |
+
"visual.blocks.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 184 |
+
"visual.blocks.14.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 185 |
+
"visual.blocks.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 186 |
+
"visual.blocks.14.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 187 |
+
"visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
|
| 188 |
+
"visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
|
| 189 |
+
"visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 190 |
+
"visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 191 |
+
"visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 192 |
+
"visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 193 |
+
"visual.blocks.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 194 |
+
"visual.blocks.15.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 195 |
+
"visual.blocks.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 196 |
+
"visual.blocks.15.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 197 |
+
"visual.blocks.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 198 |
+
"visual.blocks.15.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 199 |
+
"visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
|
| 200 |
+
"visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
|
| 201 |
+
"visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 202 |
+
"visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 203 |
+
"visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 204 |
+
"visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 205 |
+
"visual.blocks.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 206 |
+
"visual.blocks.16.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 207 |
+
"visual.blocks.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 208 |
+
"visual.blocks.16.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 209 |
+
"visual.blocks.16.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 210 |
+
"visual.blocks.16.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 211 |
+
"visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
|
| 212 |
+
"visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
|
| 213 |
+
"visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 214 |
+
"visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 215 |
+
"visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 216 |
+
"visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 217 |
+
"visual.blocks.17.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 218 |
+
"visual.blocks.17.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 219 |
+
"visual.blocks.17.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 220 |
+
"visual.blocks.17.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 221 |
+
"visual.blocks.17.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 222 |
+
"visual.blocks.17.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 223 |
+
"visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
|
| 224 |
+
"visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
|
| 225 |
+
"visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 226 |
+
"visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 227 |
+
"visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 228 |
+
"visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 229 |
+
"visual.blocks.18.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 230 |
+
"visual.blocks.18.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 231 |
+
"visual.blocks.18.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 232 |
+
"visual.blocks.18.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 233 |
+
"visual.blocks.18.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 234 |
+
"visual.blocks.18.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 235 |
+
"visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
|
| 236 |
+
"visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
|
| 237 |
+
"visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 238 |
+
"visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 239 |
+
"visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 240 |
+
"visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 241 |
+
"visual.blocks.19.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 242 |
+
"visual.blocks.19.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 243 |
+
"visual.blocks.19.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 244 |
+
"visual.blocks.19.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 245 |
+
"visual.blocks.19.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 246 |
+
"visual.blocks.19.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 247 |
+
"visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
|
| 248 |
+
"visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
|
| 249 |
+
"visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 250 |
+
"visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 251 |
+
"visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 252 |
+
"visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 253 |
+
"visual.blocks.20.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 254 |
+
"visual.blocks.20.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 255 |
+
"visual.blocks.20.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 256 |
+
"visual.blocks.20.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 257 |
+
"visual.blocks.20.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 258 |
+
"visual.blocks.20.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 259 |
+
"visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
|
| 260 |
+
"visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
|
| 261 |
+
"visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 262 |
+
"visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 263 |
+
"visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 264 |
+
"visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 265 |
+
"visual.blocks.21.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 266 |
+
"visual.blocks.21.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 267 |
+
"visual.blocks.21.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 268 |
+
"visual.blocks.21.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 269 |
+
"visual.blocks.21.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 270 |
+
"visual.blocks.21.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 271 |
+
"visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
|
| 272 |
+
"visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
|
| 273 |
+
"visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 274 |
+
"visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 275 |
+
"visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 276 |
+
"visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 277 |
+
"visual.blocks.22.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 278 |
+
"visual.blocks.22.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 279 |
+
"visual.blocks.22.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 280 |
+
"visual.blocks.22.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 281 |
+
"visual.blocks.22.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 282 |
+
"visual.blocks.22.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 283 |
+
"visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
|
| 284 |
+
"visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
|
| 285 |
+
"visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 286 |
+
"visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 287 |
+
"visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 288 |
+
"visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 289 |
+
"visual.blocks.23.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 290 |
+
"visual.blocks.23.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 291 |
+
"visual.blocks.23.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 292 |
+
"visual.blocks.23.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 293 |
+
"visual.blocks.23.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 294 |
+
"visual.blocks.23.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 295 |
+
"visual.blocks.24.norm1.weight": "model-00001-of-00002.safetensors",
|
| 296 |
+
"visual.blocks.24.norm2.weight": "model-00001-of-00002.safetensors",
|
| 297 |
+
"visual.blocks.24.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 298 |
+
"visual.blocks.24.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 299 |
+
"visual.blocks.24.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 300 |
+
"visual.blocks.24.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 301 |
+
"visual.blocks.24.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 302 |
+
"visual.blocks.24.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 303 |
+
"visual.blocks.24.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 304 |
+
"visual.blocks.24.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 305 |
+
"visual.blocks.24.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 306 |
+
"visual.blocks.24.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 307 |
+
"visual.blocks.25.norm1.weight": "model-00001-of-00002.safetensors",
|
| 308 |
+
"visual.blocks.25.norm2.weight": "model-00001-of-00002.safetensors",
|
| 309 |
+
"visual.blocks.25.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 310 |
+
"visual.blocks.25.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 311 |
+
"visual.blocks.25.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 312 |
+
"visual.blocks.25.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 313 |
+
"visual.blocks.25.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 314 |
+
"visual.blocks.25.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 315 |
+
"visual.blocks.25.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 316 |
+
"visual.blocks.25.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 317 |
+
"visual.blocks.25.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 318 |
+
"visual.blocks.25.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 319 |
+
"visual.blocks.26.norm1.weight": "model-00001-of-00002.safetensors",
|
| 320 |
+
"visual.blocks.26.norm2.weight": "model-00001-of-00002.safetensors",
|
| 321 |
+
"visual.blocks.26.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 322 |
+
"visual.blocks.26.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 323 |
+
"visual.blocks.26.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 324 |
+
"visual.blocks.26.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 325 |
+
"visual.blocks.26.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 326 |
+
"visual.blocks.26.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 327 |
+
"visual.blocks.26.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 328 |
+
"visual.blocks.26.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 329 |
+
"visual.blocks.26.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 330 |
+
"visual.blocks.26.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 331 |
+
"visual.blocks.27.norm1.weight": "model-00001-of-00002.safetensors",
|
| 332 |
+
"visual.blocks.27.norm2.weight": "model-00001-of-00002.safetensors",
|
| 333 |
+
"visual.blocks.27.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 334 |
+
"visual.blocks.27.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 335 |
+
"visual.blocks.27.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 336 |
+
"visual.blocks.27.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 337 |
+
"visual.blocks.27.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 338 |
+
"visual.blocks.27.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 339 |
+
"visual.blocks.27.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 340 |
+
"visual.blocks.27.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 341 |
+
"visual.blocks.27.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 342 |
+
"visual.blocks.27.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 343 |
+
"visual.blocks.28.norm1.weight": "model-00001-of-00002.safetensors",
|
| 344 |
+
"visual.blocks.28.norm2.weight": "model-00001-of-00002.safetensors",
|
| 345 |
+
"visual.blocks.28.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 346 |
+
"visual.blocks.28.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 347 |
+
"visual.blocks.28.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 348 |
+
"visual.blocks.28.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 349 |
+
"visual.blocks.28.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 350 |
+
"visual.blocks.28.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 351 |
+
"visual.blocks.28.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 352 |
+
"visual.blocks.28.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 353 |
+
"visual.blocks.28.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 354 |
+
"visual.blocks.28.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 355 |
+
"visual.blocks.29.norm1.weight": "model-00001-of-00002.safetensors",
|
| 356 |
+
"visual.blocks.29.norm2.weight": "model-00001-of-00002.safetensors",
|
| 357 |
+
"visual.blocks.29.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 358 |
+
"visual.blocks.29.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 359 |
+
"visual.blocks.29.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 360 |
+
"visual.blocks.29.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 361 |
+
"visual.blocks.29.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 362 |
+
"visual.blocks.29.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 363 |
+
"visual.blocks.29.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 364 |
+
"visual.blocks.29.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 365 |
+
"visual.blocks.29.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 366 |
+
"visual.blocks.29.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 367 |
+
"visual.blocks.30.norm1.weight": "model-00001-of-00002.safetensors",
|
| 368 |
+
"visual.blocks.30.norm2.weight": "model-00001-of-00002.safetensors",
|
| 369 |
+
"visual.blocks.30.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 370 |
+
"visual.blocks.30.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 371 |
+
"visual.blocks.30.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 372 |
+
"visual.blocks.30.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 373 |
+
"visual.blocks.30.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 374 |
+
"visual.blocks.30.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 375 |
+
"visual.blocks.30.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 376 |
+
"visual.blocks.30.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 377 |
+
"visual.blocks.30.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 378 |
+
"visual.blocks.30.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 379 |
+
"visual.blocks.31.norm1.weight": "model-00001-of-00002.safetensors",
|
| 380 |
+
"visual.blocks.31.norm2.weight": "model-00001-of-00002.safetensors",
|
| 381 |
+
"visual.blocks.31.attn.qkv.weight": "model-00001-of-00002.safetensors",
|
| 382 |
+
"visual.blocks.31.attn.qkv.bias": "model-00001-of-00002.safetensors",
|
| 383 |
+
"visual.blocks.31.attn.proj.weight": "model-00001-of-00002.safetensors",
|
| 384 |
+
"visual.blocks.31.attn.proj.bias": "model-00001-of-00002.safetensors",
|
| 385 |
+
"visual.blocks.31.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
|
| 386 |
+
"visual.blocks.31.mlp.gate_proj.bias": "model-00001-of-00002.safetensors",
|
| 387 |
+
"visual.blocks.31.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
|
| 388 |
+
"visual.blocks.31.mlp.up_proj.bias": "model-00001-of-00002.safetensors",
|
| 389 |
+
"visual.blocks.31.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
|
| 390 |
+
"visual.blocks.31.mlp.down_proj.bias": "model-00001-of-00002.safetensors",
|
| 391 |
+
"visual.merger.ln_q.weight": "model-00001-of-00002.safetensors",
|
| 392 |
+
"visual.merger.mlp.0.weight": "model-00001-of-00002.safetensors",
|
| 393 |
+
"visual.merger.mlp.0.bias": "model-00001-of-00002.safetensors",
|
| 394 |
+
"visual.merger.mlp.2.weight": "model-00001-of-00002.safetensors",
|
| 395 |
+
"visual.merger.mlp.2.bias": "model-00001-of-00002.safetensors",
|
| 396 |
+
"model.embed_tokens.weight": "model-00001-of-00002.safetensors",
|
| 397 |
+
"model.layers.0.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 398 |
+
"model.layers.0.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 399 |
+
"model.layers.0.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 400 |
+
"model.layers.0.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 401 |
+
"model.layers.0.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 402 |
+
"model.layers.0.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 403 |
+
"model.layers.0.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 404 |
+
"model.layers.0.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 405 |
+
"model.layers.0.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 406 |
+
"model.layers.0.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 407 |
+
"model.layers.0.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 408 |
+
"model.layers.0.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 409 |
+
"model.layers.0.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 410 |
+
"model.layers.0.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 411 |
+
"model.layers.0.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 412 |
+
"model.layers.0.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 413 |
+
"model.layers.0.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 414 |
+
"model.layers.0.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 415 |
+
"model.layers.0.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 416 |
+
"model.layers.0.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 417 |
+
"model.layers.0.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 418 |
+
"model.layers.0.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 419 |
+
"model.layers.0.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 420 |
+
"model.layers.0.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 421 |
+
"model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 422 |
+
"model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 423 |
+
"model.layers.1.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 424 |
+
"model.layers.1.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 425 |
+
"model.layers.1.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 426 |
+
"model.layers.1.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 427 |
+
"model.layers.1.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 428 |
+
"model.layers.1.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 429 |
+
"model.layers.1.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 430 |
+
"model.layers.1.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 431 |
+
"model.layers.1.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 432 |
+
"model.layers.1.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 433 |
+
"model.layers.1.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 434 |
+
"model.layers.1.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 435 |
+
"model.layers.1.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 436 |
+
"model.layers.1.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 437 |
+
"model.layers.1.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 438 |
+
"model.layers.1.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 439 |
+
"model.layers.1.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 440 |
+
"model.layers.1.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 441 |
+
"model.layers.1.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 442 |
+
"model.layers.1.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 443 |
+
"model.layers.1.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 444 |
+
"model.layers.1.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 445 |
+
"model.layers.1.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 446 |
+
"model.layers.1.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 447 |
+
"model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 448 |
+
"model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 449 |
+
"model.layers.2.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 450 |
+
"model.layers.2.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 451 |
+
"model.layers.2.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 452 |
+
"model.layers.2.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 453 |
+
"model.layers.2.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 454 |
+
"model.layers.2.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 455 |
+
"model.layers.2.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 456 |
+
"model.layers.2.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 457 |
+
"model.layers.2.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 458 |
+
"model.layers.2.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 459 |
+
"model.layers.2.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 460 |
+
"model.layers.2.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 461 |
+
"model.layers.2.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 462 |
+
"model.layers.2.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 463 |
+
"model.layers.2.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 464 |
+
"model.layers.2.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 465 |
+
"model.layers.2.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 466 |
+
"model.layers.2.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 467 |
+
"model.layers.2.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 468 |
+
"model.layers.2.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 469 |
+
"model.layers.2.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 470 |
+
"model.layers.2.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 471 |
+
"model.layers.2.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 472 |
+
"model.layers.2.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 473 |
+
"model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 474 |
+
"model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 475 |
+
"model.layers.3.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 476 |
+
"model.layers.3.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 477 |
+
"model.layers.3.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 478 |
+
"model.layers.3.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 479 |
+
"model.layers.3.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 480 |
+
"model.layers.3.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 481 |
+
"model.layers.3.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 482 |
+
"model.layers.3.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 483 |
+
"model.layers.3.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 484 |
+
"model.layers.3.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 485 |
+
"model.layers.3.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 486 |
+
"model.layers.3.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 487 |
+
"model.layers.3.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 488 |
+
"model.layers.3.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 489 |
+
"model.layers.3.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 490 |
+
"model.layers.3.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 491 |
+
"model.layers.3.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 492 |
+
"model.layers.3.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 493 |
+
"model.layers.3.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 494 |
+
"model.layers.3.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 495 |
+
"model.layers.3.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 496 |
+
"model.layers.3.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 497 |
+
"model.layers.3.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 498 |
+
"model.layers.3.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 499 |
+
"model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 500 |
+
"model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 501 |
+
"model.layers.4.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 502 |
+
"model.layers.4.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 503 |
+
"model.layers.4.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 504 |
+
"model.layers.4.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 505 |
+
"model.layers.4.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 506 |
+
"model.layers.4.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 507 |
+
"model.layers.4.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 508 |
+
"model.layers.4.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 509 |
+
"model.layers.4.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 510 |
+
"model.layers.4.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 511 |
+
"model.layers.4.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 512 |
+
"model.layers.4.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 513 |
+
"model.layers.4.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 514 |
+
"model.layers.4.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 515 |
+
"model.layers.4.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 516 |
+
"model.layers.4.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 517 |
+
"model.layers.4.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 518 |
+
"model.layers.4.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 519 |
+
"model.layers.4.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 520 |
+
"model.layers.4.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 521 |
+
"model.layers.4.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 522 |
+
"model.layers.4.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 523 |
+
"model.layers.4.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 524 |
+
"model.layers.4.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 525 |
+
"model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 526 |
+
"model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 527 |
+
"model.layers.5.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 528 |
+
"model.layers.5.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 529 |
+
"model.layers.5.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 530 |
+
"model.layers.5.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 531 |
+
"model.layers.5.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 532 |
+
"model.layers.5.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 533 |
+
"model.layers.5.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 534 |
+
"model.layers.5.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 535 |
+
"model.layers.5.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 536 |
+
"model.layers.5.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 537 |
+
"model.layers.5.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 538 |
+
"model.layers.5.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 539 |
+
"model.layers.5.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 540 |
+
"model.layers.5.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 541 |
+
"model.layers.5.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 542 |
+
"model.layers.5.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 543 |
+
"model.layers.5.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 544 |
+
"model.layers.5.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 545 |
+
"model.layers.5.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 546 |
+
"model.layers.5.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 547 |
+
"model.layers.5.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 548 |
+
"model.layers.5.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 549 |
+
"model.layers.5.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 550 |
+
"model.layers.5.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 551 |
+
"model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 552 |
+
"model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 553 |
+
"model.layers.6.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 554 |
+
"model.layers.6.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 555 |
+
"model.layers.6.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 556 |
+
"model.layers.6.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 557 |
+
"model.layers.6.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 558 |
+
"model.layers.6.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 559 |
+
"model.layers.6.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 560 |
+
"model.layers.6.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 561 |
+
"model.layers.6.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 562 |
+
"model.layers.6.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 563 |
+
"model.layers.6.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 564 |
+
"model.layers.6.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 565 |
+
"model.layers.6.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 566 |
+
"model.layers.6.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 567 |
+
"model.layers.6.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 568 |
+
"model.layers.6.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 569 |
+
"model.layers.6.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 570 |
+
"model.layers.6.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 571 |
+
"model.layers.6.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 572 |
+
"model.layers.6.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 573 |
+
"model.layers.6.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 574 |
+
"model.layers.6.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 575 |
+
"model.layers.6.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 576 |
+
"model.layers.6.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 577 |
+
"model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 578 |
+
"model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 579 |
+
"model.layers.7.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 580 |
+
"model.layers.7.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 581 |
+
"model.layers.7.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 582 |
+
"model.layers.7.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 583 |
+
"model.layers.7.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 584 |
+
"model.layers.7.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 585 |
+
"model.layers.7.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 586 |
+
"model.layers.7.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 587 |
+
"model.layers.7.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 588 |
+
"model.layers.7.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 589 |
+
"model.layers.7.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 590 |
+
"model.layers.7.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 591 |
+
"model.layers.7.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 592 |
+
"model.layers.7.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 593 |
+
"model.layers.7.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 594 |
+
"model.layers.7.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 595 |
+
"model.layers.7.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 596 |
+
"model.layers.7.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 597 |
+
"model.layers.7.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 598 |
+
"model.layers.7.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 599 |
+
"model.layers.7.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 600 |
+
"model.layers.7.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 601 |
+
"model.layers.7.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 602 |
+
"model.layers.7.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 603 |
+
"model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 604 |
+
"model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 605 |
+
"model.layers.8.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 606 |
+
"model.layers.8.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 607 |
+
"model.layers.8.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 608 |
+
"model.layers.8.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 609 |
+
"model.layers.8.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 610 |
+
"model.layers.8.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 611 |
+
"model.layers.8.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 612 |
+
"model.layers.8.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 613 |
+
"model.layers.8.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 614 |
+
"model.layers.8.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 615 |
+
"model.layers.8.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 616 |
+
"model.layers.8.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 617 |
+
"model.layers.8.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 618 |
+
"model.layers.8.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 619 |
+
"model.layers.8.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 620 |
+
"model.layers.8.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 621 |
+
"model.layers.8.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 622 |
+
"model.layers.8.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 623 |
+
"model.layers.8.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 624 |
+
"model.layers.8.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 625 |
+
"model.layers.8.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 626 |
+
"model.layers.8.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 627 |
+
"model.layers.8.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 628 |
+
"model.layers.8.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 629 |
+
"model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 630 |
+
"model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 631 |
+
"model.layers.9.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 632 |
+
"model.layers.9.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 633 |
+
"model.layers.9.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 634 |
+
"model.layers.9.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 635 |
+
"model.layers.9.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 636 |
+
"model.layers.9.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 637 |
+
"model.layers.9.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 638 |
+
"model.layers.9.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 639 |
+
"model.layers.9.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 640 |
+
"model.layers.9.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 641 |
+
"model.layers.9.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 642 |
+
"model.layers.9.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 643 |
+
"model.layers.9.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 644 |
+
"model.layers.9.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 645 |
+
"model.layers.9.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 646 |
+
"model.layers.9.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 647 |
+
"model.layers.9.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 648 |
+
"model.layers.9.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 649 |
+
"model.layers.9.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 650 |
+
"model.layers.9.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 651 |
+
"model.layers.9.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 652 |
+
"model.layers.9.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 653 |
+
"model.layers.9.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 654 |
+
"model.layers.9.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 655 |
+
"model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 656 |
+
"model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 657 |
+
"model.layers.10.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 658 |
+
"model.layers.10.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 659 |
+
"model.layers.10.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 660 |
+
"model.layers.10.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 661 |
+
"model.layers.10.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 662 |
+
"model.layers.10.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 663 |
+
"model.layers.10.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 664 |
+
"model.layers.10.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 665 |
+
"model.layers.10.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 666 |
+
"model.layers.10.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 667 |
+
"model.layers.10.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 668 |
+
"model.layers.10.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 669 |
+
"model.layers.10.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 670 |
+
"model.layers.10.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 671 |
+
"model.layers.10.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 672 |
+
"model.layers.10.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 673 |
+
"model.layers.10.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 674 |
+
"model.layers.10.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 675 |
+
"model.layers.10.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 676 |
+
"model.layers.10.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 677 |
+
"model.layers.10.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 678 |
+
"model.layers.10.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 679 |
+
"model.layers.10.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 680 |
+
"model.layers.10.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 681 |
+
"model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 682 |
+
"model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 683 |
+
"model.layers.11.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 684 |
+
"model.layers.11.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 685 |
+
"model.layers.11.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 686 |
+
"model.layers.11.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 687 |
+
"model.layers.11.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 688 |
+
"model.layers.11.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 689 |
+
"model.layers.11.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 690 |
+
"model.layers.11.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 691 |
+
"model.layers.11.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 692 |
+
"model.layers.11.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 693 |
+
"model.layers.11.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 694 |
+
"model.layers.11.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 695 |
+
"model.layers.11.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 696 |
+
"model.layers.11.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 697 |
+
"model.layers.11.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 698 |
+
"model.layers.11.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 699 |
+
"model.layers.11.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 700 |
+
"model.layers.11.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 701 |
+
"model.layers.11.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 702 |
+
"model.layers.11.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 703 |
+
"model.layers.11.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 704 |
+
"model.layers.11.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 705 |
+
"model.layers.11.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 706 |
+
"model.layers.11.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 707 |
+
"model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 708 |
+
"model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 709 |
+
"model.layers.12.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 710 |
+
"model.layers.12.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 711 |
+
"model.layers.12.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 712 |
+
"model.layers.12.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 713 |
+
"model.layers.12.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 714 |
+
"model.layers.12.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 715 |
+
"model.layers.12.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 716 |
+
"model.layers.12.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 717 |
+
"model.layers.12.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 718 |
+
"model.layers.12.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 719 |
+
"model.layers.12.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 720 |
+
"model.layers.12.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 721 |
+
"model.layers.12.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 722 |
+
"model.layers.12.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 723 |
+
"model.layers.12.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 724 |
+
"model.layers.12.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 725 |
+
"model.layers.12.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 726 |
+
"model.layers.12.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 727 |
+
"model.layers.12.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 728 |
+
"model.layers.12.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 729 |
+
"model.layers.12.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 730 |
+
"model.layers.12.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 731 |
+
"model.layers.12.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 732 |
+
"model.layers.12.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 733 |
+
"model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 734 |
+
"model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 735 |
+
"model.layers.13.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 736 |
+
"model.layers.13.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 737 |
+
"model.layers.13.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 738 |
+
"model.layers.13.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 739 |
+
"model.layers.13.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 740 |
+
"model.layers.13.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 741 |
+
"model.layers.13.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 742 |
+
"model.layers.13.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 743 |
+
"model.layers.13.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 744 |
+
"model.layers.13.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 745 |
+
"model.layers.13.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 746 |
+
"model.layers.13.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 747 |
+
"model.layers.13.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 748 |
+
"model.layers.13.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 749 |
+
"model.layers.13.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 750 |
+
"model.layers.13.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 751 |
+
"model.layers.13.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 752 |
+
"model.layers.13.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 753 |
+
"model.layers.13.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 754 |
+
"model.layers.13.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 755 |
+
"model.layers.13.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 756 |
+
"model.layers.13.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 757 |
+
"model.layers.13.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 758 |
+
"model.layers.13.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 759 |
+
"model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 760 |
+
"model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 761 |
+
"model.layers.14.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 762 |
+
"model.layers.14.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 763 |
+
"model.layers.14.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 764 |
+
"model.layers.14.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 765 |
+
"model.layers.14.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 766 |
+
"model.layers.14.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 767 |
+
"model.layers.14.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 768 |
+
"model.layers.14.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 769 |
+
"model.layers.14.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 770 |
+
"model.layers.14.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 771 |
+
"model.layers.14.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 772 |
+
"model.layers.14.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 773 |
+
"model.layers.14.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 774 |
+
"model.layers.14.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 775 |
+
"model.layers.14.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 776 |
+
"model.layers.14.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 777 |
+
"model.layers.14.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 778 |
+
"model.layers.14.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 779 |
+
"model.layers.14.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 780 |
+
"model.layers.14.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 781 |
+
"model.layers.14.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 782 |
+
"model.layers.14.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 783 |
+
"model.layers.14.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 784 |
+
"model.layers.14.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 785 |
+
"model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 786 |
+
"model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 787 |
+
"model.layers.15.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 788 |
+
"model.layers.15.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 789 |
+
"model.layers.15.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 790 |
+
"model.layers.15.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 791 |
+
"model.layers.15.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 792 |
+
"model.layers.15.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 793 |
+
"model.layers.15.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 794 |
+
"model.layers.15.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 795 |
+
"model.layers.15.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 796 |
+
"model.layers.15.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 797 |
+
"model.layers.15.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 798 |
+
"model.layers.15.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 799 |
+
"model.layers.15.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 800 |
+
"model.layers.15.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 801 |
+
"model.layers.15.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 802 |
+
"model.layers.15.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 803 |
+
"model.layers.15.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 804 |
+
"model.layers.15.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 805 |
+
"model.layers.15.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 806 |
+
"model.layers.15.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 807 |
+
"model.layers.15.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 808 |
+
"model.layers.15.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 809 |
+
"model.layers.15.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 810 |
+
"model.layers.15.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 811 |
+
"model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 812 |
+
"model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 813 |
+
"model.layers.16.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 814 |
+
"model.layers.16.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 815 |
+
"model.layers.16.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 816 |
+
"model.layers.16.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 817 |
+
"model.layers.16.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 818 |
+
"model.layers.16.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 819 |
+
"model.layers.16.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 820 |
+
"model.layers.16.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 821 |
+
"model.layers.16.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 822 |
+
"model.layers.16.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 823 |
+
"model.layers.16.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 824 |
+
"model.layers.16.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 825 |
+
"model.layers.16.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 826 |
+
"model.layers.16.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 827 |
+
"model.layers.16.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 828 |
+
"model.layers.16.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 829 |
+
"model.layers.16.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 830 |
+
"model.layers.16.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 831 |
+
"model.layers.16.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 832 |
+
"model.layers.16.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 833 |
+
"model.layers.16.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 834 |
+
"model.layers.16.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 835 |
+
"model.layers.16.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 836 |
+
"model.layers.16.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 837 |
+
"model.layers.16.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 838 |
+
"model.layers.16.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 839 |
+
"model.layers.17.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 840 |
+
"model.layers.17.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 841 |
+
"model.layers.17.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 842 |
+
"model.layers.17.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 843 |
+
"model.layers.17.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 844 |
+
"model.layers.17.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 845 |
+
"model.layers.17.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 846 |
+
"model.layers.17.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 847 |
+
"model.layers.17.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 848 |
+
"model.layers.17.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 849 |
+
"model.layers.17.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 850 |
+
"model.layers.17.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 851 |
+
"model.layers.17.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 852 |
+
"model.layers.17.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 853 |
+
"model.layers.17.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 854 |
+
"model.layers.17.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 855 |
+
"model.layers.17.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 856 |
+
"model.layers.17.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 857 |
+
"model.layers.17.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 858 |
+
"model.layers.17.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 859 |
+
"model.layers.17.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 860 |
+
"model.layers.17.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 861 |
+
"model.layers.17.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 862 |
+
"model.layers.17.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 863 |
+
"model.layers.17.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 864 |
+
"model.layers.17.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 865 |
+
"model.layers.18.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 866 |
+
"model.layers.18.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 867 |
+
"model.layers.18.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 868 |
+
"model.layers.18.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 869 |
+
"model.layers.18.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 870 |
+
"model.layers.18.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 871 |
+
"model.layers.18.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 872 |
+
"model.layers.18.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 873 |
+
"model.layers.18.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 874 |
+
"model.layers.18.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 875 |
+
"model.layers.18.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 876 |
+
"model.layers.18.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 877 |
+
"model.layers.18.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 878 |
+
"model.layers.18.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 879 |
+
"model.layers.18.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 880 |
+
"model.layers.18.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 881 |
+
"model.layers.18.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 882 |
+
"model.layers.18.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 883 |
+
"model.layers.18.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 884 |
+
"model.layers.18.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 885 |
+
"model.layers.18.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 886 |
+
"model.layers.18.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 887 |
+
"model.layers.18.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 888 |
+
"model.layers.18.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 889 |
+
"model.layers.18.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 890 |
+
"model.layers.18.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 891 |
+
"model.layers.19.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 892 |
+
"model.layers.19.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 893 |
+
"model.layers.19.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 894 |
+
"model.layers.19.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 895 |
+
"model.layers.19.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 896 |
+
"model.layers.19.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 897 |
+
"model.layers.19.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 898 |
+
"model.layers.19.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 899 |
+
"model.layers.19.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 900 |
+
"model.layers.19.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 901 |
+
"model.layers.19.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 902 |
+
"model.layers.19.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 903 |
+
"model.layers.19.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 904 |
+
"model.layers.19.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 905 |
+
"model.layers.19.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 906 |
+
"model.layers.19.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 907 |
+
"model.layers.19.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 908 |
+
"model.layers.19.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 909 |
+
"model.layers.19.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 910 |
+
"model.layers.19.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 911 |
+
"model.layers.19.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 912 |
+
"model.layers.19.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 913 |
+
"model.layers.19.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 914 |
+
"model.layers.19.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 915 |
+
"model.layers.19.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 916 |
+
"model.layers.19.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 917 |
+
"model.layers.20.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 918 |
+
"model.layers.20.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 919 |
+
"model.layers.20.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 920 |
+
"model.layers.20.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 921 |
+
"model.layers.20.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 922 |
+
"model.layers.20.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 923 |
+
"model.layers.20.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 924 |
+
"model.layers.20.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 925 |
+
"model.layers.20.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 926 |
+
"model.layers.20.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 927 |
+
"model.layers.20.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 928 |
+
"model.layers.20.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 929 |
+
"model.layers.20.self_attn.o_proj.qweight": "model-00001-of-00002.safetensors",
|
| 930 |
+
"model.layers.20.self_attn.o_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 931 |
+
"model.layers.20.self_attn.o_proj.scales": "model-00001-of-00002.safetensors",
|
| 932 |
+
"model.layers.20.mlp.gate_proj.qweight": "model-00001-of-00002.safetensors",
|
| 933 |
+
"model.layers.20.mlp.gate_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 934 |
+
"model.layers.20.mlp.gate_proj.scales": "model-00001-of-00002.safetensors",
|
| 935 |
+
"model.layers.20.mlp.up_proj.qweight": "model-00001-of-00002.safetensors",
|
| 936 |
+
"model.layers.20.mlp.up_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 937 |
+
"model.layers.20.mlp.up_proj.scales": "model-00001-of-00002.safetensors",
|
| 938 |
+
"model.layers.20.mlp.down_proj.qweight": "model-00001-of-00002.safetensors",
|
| 939 |
+
"model.layers.20.mlp.down_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 940 |
+
"model.layers.20.mlp.down_proj.scales": "model-00001-of-00002.safetensors",
|
| 941 |
+
"model.layers.20.input_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 942 |
+
"model.layers.20.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
|
| 943 |
+
"model.layers.21.self_attn.q_proj.qweight": "model-00001-of-00002.safetensors",
|
| 944 |
+
"model.layers.21.self_attn.q_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 945 |
+
"model.layers.21.self_attn.q_proj.scales": "model-00001-of-00002.safetensors",
|
| 946 |
+
"model.layers.21.self_attn.q_proj.bias": "model-00001-of-00002.safetensors",
|
| 947 |
+
"model.layers.21.self_attn.k_proj.qweight": "model-00001-of-00002.safetensors",
|
| 948 |
+
"model.layers.21.self_attn.k_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 949 |
+
"model.layers.21.self_attn.k_proj.scales": "model-00001-of-00002.safetensors",
|
| 950 |
+
"model.layers.21.self_attn.k_proj.bias": "model-00001-of-00002.safetensors",
|
| 951 |
+
"model.layers.21.self_attn.v_proj.qweight": "model-00001-of-00002.safetensors",
|
| 952 |
+
"model.layers.21.self_attn.v_proj.qzeros": "model-00001-of-00002.safetensors",
|
| 953 |
+
"model.layers.21.self_attn.v_proj.scales": "model-00001-of-00002.safetensors",
|
| 954 |
+
"model.layers.21.self_attn.v_proj.bias": "model-00001-of-00002.safetensors",
|
| 955 |
+
"model.layers.21.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 956 |
+
"model.layers.21.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 957 |
+
"model.layers.21.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 958 |
+
"model.layers.21.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 959 |
+
"model.layers.21.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 960 |
+
"model.layers.21.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 961 |
+
"model.layers.21.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 962 |
+
"model.layers.21.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 963 |
+
"model.layers.21.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 964 |
+
"model.layers.21.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 965 |
+
"model.layers.21.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 966 |
+
"model.layers.21.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 967 |
+
"model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 968 |
+
"model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 969 |
+
"model.layers.22.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 970 |
+
"model.layers.22.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 971 |
+
"model.layers.22.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 972 |
+
"model.layers.22.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 973 |
+
"model.layers.22.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 974 |
+
"model.layers.22.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 975 |
+
"model.layers.22.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 976 |
+
"model.layers.22.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 977 |
+
"model.layers.22.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 978 |
+
"model.layers.22.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 979 |
+
"model.layers.22.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 980 |
+
"model.layers.22.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 981 |
+
"model.layers.22.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 982 |
+
"model.layers.22.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 983 |
+
"model.layers.22.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 984 |
+
"model.layers.22.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 985 |
+
"model.layers.22.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 986 |
+
"model.layers.22.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 987 |
+
"model.layers.22.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 988 |
+
"model.layers.22.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 989 |
+
"model.layers.22.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 990 |
+
"model.layers.22.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 991 |
+
"model.layers.22.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 992 |
+
"model.layers.22.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 993 |
+
"model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 994 |
+
"model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 995 |
+
"model.layers.23.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 996 |
+
"model.layers.23.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 997 |
+
"model.layers.23.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 998 |
+
"model.layers.23.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 999 |
+
"model.layers.23.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1000 |
+
"model.layers.23.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1001 |
+
"model.layers.23.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1002 |
+
"model.layers.23.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1003 |
+
"model.layers.23.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1004 |
+
"model.layers.23.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1005 |
+
"model.layers.23.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1006 |
+
"model.layers.23.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1007 |
+
"model.layers.23.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1008 |
+
"model.layers.23.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1009 |
+
"model.layers.23.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1010 |
+
"model.layers.23.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1011 |
+
"model.layers.23.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1012 |
+
"model.layers.23.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1013 |
+
"model.layers.23.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1014 |
+
"model.layers.23.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1015 |
+
"model.layers.23.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1016 |
+
"model.layers.23.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1017 |
+
"model.layers.23.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1018 |
+
"model.layers.23.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1019 |
+
"model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1020 |
+
"model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1021 |
+
"model.layers.24.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1022 |
+
"model.layers.24.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1023 |
+
"model.layers.24.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1024 |
+
"model.layers.24.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1025 |
+
"model.layers.24.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1026 |
+
"model.layers.24.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1027 |
+
"model.layers.24.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1028 |
+
"model.layers.24.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1029 |
+
"model.layers.24.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1030 |
+
"model.layers.24.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1031 |
+
"model.layers.24.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1032 |
+
"model.layers.24.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1033 |
+
"model.layers.24.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1034 |
+
"model.layers.24.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1035 |
+
"model.layers.24.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1036 |
+
"model.layers.24.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1037 |
+
"model.layers.24.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1038 |
+
"model.layers.24.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1039 |
+
"model.layers.24.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1040 |
+
"model.layers.24.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1041 |
+
"model.layers.24.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1042 |
+
"model.layers.24.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1043 |
+
"model.layers.24.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1044 |
+
"model.layers.24.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1045 |
+
"model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1046 |
+
"model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1047 |
+
"model.layers.25.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1048 |
+
"model.layers.25.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1049 |
+
"model.layers.25.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1050 |
+
"model.layers.25.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1051 |
+
"model.layers.25.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1052 |
+
"model.layers.25.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1053 |
+
"model.layers.25.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1054 |
+
"model.layers.25.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1055 |
+
"model.layers.25.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1056 |
+
"model.layers.25.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1057 |
+
"model.layers.25.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1058 |
+
"model.layers.25.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1059 |
+
"model.layers.25.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1060 |
+
"model.layers.25.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1061 |
+
"model.layers.25.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1062 |
+
"model.layers.25.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1063 |
+
"model.layers.25.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1064 |
+
"model.layers.25.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1065 |
+
"model.layers.25.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1066 |
+
"model.layers.25.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1067 |
+
"model.layers.25.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1068 |
+
"model.layers.25.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1069 |
+
"model.layers.25.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1070 |
+
"model.layers.25.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1071 |
+
"model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1072 |
+
"model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1073 |
+
"model.layers.26.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1074 |
+
"model.layers.26.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1075 |
+
"model.layers.26.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1076 |
+
"model.layers.26.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1077 |
+
"model.layers.26.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1078 |
+
"model.layers.26.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1079 |
+
"model.layers.26.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1080 |
+
"model.layers.26.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1081 |
+
"model.layers.26.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1082 |
+
"model.layers.26.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1083 |
+
"model.layers.26.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1084 |
+
"model.layers.26.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1085 |
+
"model.layers.26.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1086 |
+
"model.layers.26.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1087 |
+
"model.layers.26.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1088 |
+
"model.layers.26.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1089 |
+
"model.layers.26.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1090 |
+
"model.layers.26.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1091 |
+
"model.layers.26.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1092 |
+
"model.layers.26.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1093 |
+
"model.layers.26.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1094 |
+
"model.layers.26.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1095 |
+
"model.layers.26.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1096 |
+
"model.layers.26.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1097 |
+
"model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1098 |
+
"model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1099 |
+
"model.layers.27.self_attn.q_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1100 |
+
"model.layers.27.self_attn.q_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1101 |
+
"model.layers.27.self_attn.q_proj.scales": "model-00002-of-00002.safetensors",
|
| 1102 |
+
"model.layers.27.self_attn.q_proj.bias": "model-00002-of-00002.safetensors",
|
| 1103 |
+
"model.layers.27.self_attn.k_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1104 |
+
"model.layers.27.self_attn.k_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1105 |
+
"model.layers.27.self_attn.k_proj.scales": "model-00002-of-00002.safetensors",
|
| 1106 |
+
"model.layers.27.self_attn.k_proj.bias": "model-00002-of-00002.safetensors",
|
| 1107 |
+
"model.layers.27.self_attn.v_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1108 |
+
"model.layers.27.self_attn.v_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1109 |
+
"model.layers.27.self_attn.v_proj.scales": "model-00002-of-00002.safetensors",
|
| 1110 |
+
"model.layers.27.self_attn.v_proj.bias": "model-00002-of-00002.safetensors",
|
| 1111 |
+
"model.layers.27.self_attn.o_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1112 |
+
"model.layers.27.self_attn.o_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1113 |
+
"model.layers.27.self_attn.o_proj.scales": "model-00002-of-00002.safetensors",
|
| 1114 |
+
"model.layers.27.mlp.gate_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1115 |
+
"model.layers.27.mlp.gate_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1116 |
+
"model.layers.27.mlp.gate_proj.scales": "model-00002-of-00002.safetensors",
|
| 1117 |
+
"model.layers.27.mlp.up_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1118 |
+
"model.layers.27.mlp.up_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1119 |
+
"model.layers.27.mlp.up_proj.scales": "model-00002-of-00002.safetensors",
|
| 1120 |
+
"model.layers.27.mlp.down_proj.qweight": "model-00002-of-00002.safetensors",
|
| 1121 |
+
"model.layers.27.mlp.down_proj.qzeros": "model-00002-of-00002.safetensors",
|
| 1122 |
+
"model.layers.27.mlp.down_proj.scales": "model-00002-of-00002.safetensors",
|
| 1123 |
+
"model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1124 |
+
"model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
|
| 1125 |
+
"model.norm.weight": "model-00002-of-00002.safetensors",
|
| 1126 |
+
"lm_head.weight": "model-00002-of-00002.safetensors"
|
| 1127 |
+
}
|
| 1128 |
+
}
|
preprocessor_config.json
ADDED
|
@@ -0,0 +1,29 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"do_convert_rgb": true,
|
| 3 |
+
"do_normalize": true,
|
| 4 |
+
"do_rescale": true,
|
| 5 |
+
"do_resize": true,
|
| 6 |
+
"image_mean": [
|
| 7 |
+
0.48145466,
|
| 8 |
+
0.4578275,
|
| 9 |
+
0.40821073
|
| 10 |
+
],
|
| 11 |
+
"image_processor_type": "Qwen2_5_VLImageProcessor",
|
| 12 |
+
"image_std": [
|
| 13 |
+
0.26862954,
|
| 14 |
+
0.26130258,
|
| 15 |
+
0.27577711
|
| 16 |
+
],
|
| 17 |
+
"max_pixels": 12845056,
|
| 18 |
+
"merge_size": 2,
|
| 19 |
+
"min_pixels": 3136,
|
| 20 |
+
"patch_size": 14,
|
| 21 |
+
"processor_class": "Qwen2_5_VLProcessor",
|
| 22 |
+
"resample": 3,
|
| 23 |
+
"rescale_factor": 0.00392156862745098,
|
| 24 |
+
"size": {
|
| 25 |
+
"longest_edge": 12845056,
|
| 26 |
+
"shortest_edge": 3136
|
| 27 |
+
},
|
| 28 |
+
"temporal_patch_size": 2
|
| 29 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"<|im_start|>",
|
| 4 |
+
"<|im_end|>",
|
| 5 |
+
"<|object_ref_start|>",
|
| 6 |
+
"<|object_ref_end|>",
|
| 7 |
+
"<|box_start|>",
|
| 8 |
+
"<|box_end|>",
|
| 9 |
+
"<|quad_start|>",
|
| 10 |
+
"<|quad_end|>",
|
| 11 |
+
"<|vision_start|>",
|
| 12 |
+
"<|vision_end|>",
|
| 13 |
+
"<|vision_pad|>",
|
| 14 |
+
"<|image_pad|>",
|
| 15 |
+
"<|video_pad|>"
|
| 16 |
+
],
|
| 17 |
+
"eos_token": {
|
| 18 |
+
"content": "<|im_end|>",
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"normalized": false,
|
| 21 |
+
"rstrip": false,
|
| 22 |
+
"single_word": false
|
| 23 |
+
},
|
| 24 |
+
"pad_token": {
|
| 25 |
+
"content": "<|endoftext|>",
|
| 26 |
+
"lstrip": false,
|
| 27 |
+
"normalized": false,
|
| 28 |
+
"rstrip": false,
|
| 29 |
+
"single_word": false
|
| 30 |
+
}
|
| 31 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c5ae00e602b8860cbd784ba82a8aa14e8feecec692e7076590d014d7b7fdafa
|
| 3 |
+
size 11421896
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,208 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_bos_token": false,
|
| 3 |
+
"add_prefix_space": false,
|
| 4 |
+
"added_tokens_decoder": {
|
| 5 |
+
"151643": {
|
| 6 |
+
"content": "<|endoftext|>",
|
| 7 |
+
"lstrip": false,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false,
|
| 11 |
+
"special": true
|
| 12 |
+
},
|
| 13 |
+
"151644": {
|
| 14 |
+
"content": "<|im_start|>",
|
| 15 |
+
"lstrip": false,
|
| 16 |
+
"normalized": false,
|
| 17 |
+
"rstrip": false,
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"special": true
|
| 20 |
+
},
|
| 21 |
+
"151645": {
|
| 22 |
+
"content": "<|im_end|>",
|
| 23 |
+
"lstrip": false,
|
| 24 |
+
"normalized": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"single_word": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
"151646": {
|
| 30 |
+
"content": "<|object_ref_start|>",
|
| 31 |
+
"lstrip": false,
|
| 32 |
+
"normalized": false,
|
| 33 |
+
"rstrip": false,
|
| 34 |
+
"single_word": false,
|
| 35 |
+
"special": true
|
| 36 |
+
},
|
| 37 |
+
"151647": {
|
| 38 |
+
"content": "<|object_ref_end|>",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": false,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false,
|
| 43 |
+
"special": true
|
| 44 |
+
},
|
| 45 |
+
"151648": {
|
| 46 |
+
"content": "<|box_start|>",
|
| 47 |
+
"lstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"rstrip": false,
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"special": true
|
| 52 |
+
},
|
| 53 |
+
"151649": {
|
| 54 |
+
"content": "<|box_end|>",
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"normalized": false,
|
| 57 |
+
"rstrip": false,
|
| 58 |
+
"single_word": false,
|
| 59 |
+
"special": true
|
| 60 |
+
},
|
| 61 |
+
"151650": {
|
| 62 |
+
"content": "<|quad_start|>",
|
| 63 |
+
"lstrip": false,
|
| 64 |
+
"normalized": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"single_word": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
"151651": {
|
| 70 |
+
"content": "<|quad_end|>",
|
| 71 |
+
"lstrip": false,
|
| 72 |
+
"normalized": false,
|
| 73 |
+
"rstrip": false,
|
| 74 |
+
"single_word": false,
|
| 75 |
+
"special": true
|
| 76 |
+
},
|
| 77 |
+
"151652": {
|
| 78 |
+
"content": "<|vision_start|>",
|
| 79 |
+
"lstrip": false,
|
| 80 |
+
"normalized": false,
|
| 81 |
+
"rstrip": false,
|
| 82 |
+
"single_word": false,
|
| 83 |
+
"special": true
|
| 84 |
+
},
|
| 85 |
+
"151653": {
|
| 86 |
+
"content": "<|vision_end|>",
|
| 87 |
+
"lstrip": false,
|
| 88 |
+
"normalized": false,
|
| 89 |
+
"rstrip": false,
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"special": true
|
| 92 |
+
},
|
| 93 |
+
"151654": {
|
| 94 |
+
"content": "<|vision_pad|>",
|
| 95 |
+
"lstrip": false,
|
| 96 |
+
"normalized": false,
|
| 97 |
+
"rstrip": false,
|
| 98 |
+
"single_word": false,
|
| 99 |
+
"special": true
|
| 100 |
+
},
|
| 101 |
+
"151655": {
|
| 102 |
+
"content": "<|image_pad|>",
|
| 103 |
+
"lstrip": false,
|
| 104 |
+
"normalized": false,
|
| 105 |
+
"rstrip": false,
|
| 106 |
+
"single_word": false,
|
| 107 |
+
"special": true
|
| 108 |
+
},
|
| 109 |
+
"151656": {
|
| 110 |
+
"content": "<|video_pad|>",
|
| 111 |
+
"lstrip": false,
|
| 112 |
+
"normalized": false,
|
| 113 |
+
"rstrip": false,
|
| 114 |
+
"single_word": false,
|
| 115 |
+
"special": true
|
| 116 |
+
},
|
| 117 |
+
"151657": {
|
| 118 |
+
"content": "<tool_call>",
|
| 119 |
+
"lstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"rstrip": false,
|
| 122 |
+
"single_word": false,
|
| 123 |
+
"special": false
|
| 124 |
+
},
|
| 125 |
+
"151658": {
|
| 126 |
+
"content": "</tool_call>",
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"normalized": false,
|
| 129 |
+
"rstrip": false,
|
| 130 |
+
"single_word": false,
|
| 131 |
+
"special": false
|
| 132 |
+
},
|
| 133 |
+
"151659": {
|
| 134 |
+
"content": "<|fim_prefix|>",
|
| 135 |
+
"lstrip": false,
|
| 136 |
+
"normalized": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"single_word": false,
|
| 139 |
+
"special": false
|
| 140 |
+
},
|
| 141 |
+
"151660": {
|
| 142 |
+
"content": "<|fim_middle|>",
|
| 143 |
+
"lstrip": false,
|
| 144 |
+
"normalized": false,
|
| 145 |
+
"rstrip": false,
|
| 146 |
+
"single_word": false,
|
| 147 |
+
"special": false
|
| 148 |
+
},
|
| 149 |
+
"151661": {
|
| 150 |
+
"content": "<|fim_suffix|>",
|
| 151 |
+
"lstrip": false,
|
| 152 |
+
"normalized": false,
|
| 153 |
+
"rstrip": false,
|
| 154 |
+
"single_word": false,
|
| 155 |
+
"special": false
|
| 156 |
+
},
|
| 157 |
+
"151662": {
|
| 158 |
+
"content": "<|fim_pad|>",
|
| 159 |
+
"lstrip": false,
|
| 160 |
+
"normalized": false,
|
| 161 |
+
"rstrip": false,
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"special": false
|
| 164 |
+
},
|
| 165 |
+
"151663": {
|
| 166 |
+
"content": "<|repo_name|>",
|
| 167 |
+
"lstrip": false,
|
| 168 |
+
"normalized": false,
|
| 169 |
+
"rstrip": false,
|
| 170 |
+
"single_word": false,
|
| 171 |
+
"special": false
|
| 172 |
+
},
|
| 173 |
+
"151664": {
|
| 174 |
+
"content": "<|file_sep|>",
|
| 175 |
+
"lstrip": false,
|
| 176 |
+
"normalized": false,
|
| 177 |
+
"rstrip": false,
|
| 178 |
+
"single_word": false,
|
| 179 |
+
"special": false
|
| 180 |
+
}
|
| 181 |
+
},
|
| 182 |
+
"additional_special_tokens": [
|
| 183 |
+
"<|im_start|>",
|
| 184 |
+
"<|im_end|>",
|
| 185 |
+
"<|object_ref_start|>",
|
| 186 |
+
"<|object_ref_end|>",
|
| 187 |
+
"<|box_start|>",
|
| 188 |
+
"<|box_end|>",
|
| 189 |
+
"<|quad_start|>",
|
| 190 |
+
"<|quad_end|>",
|
| 191 |
+
"<|vision_start|>",
|
| 192 |
+
"<|vision_end|>",
|
| 193 |
+
"<|vision_pad|>",
|
| 194 |
+
"<|image_pad|>",
|
| 195 |
+
"<|video_pad|>"
|
| 196 |
+
],
|
| 197 |
+
"bos_token": null,
|
| 198 |
+
"chat_template": "{%- if tools %}\n {{- '<|im_start|>system\\n' }}\n {%- if messages[0]['role'] == 'system' %}\n {{- messages[0]['content'] }}\n {%- else %}\n {{- '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 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",
|
| 199 |
+
"clean_up_tokenization_spaces": false,
|
| 200 |
+
"eos_token": "<|im_end|>",
|
| 201 |
+
"errors": "replace",
|
| 202 |
+
"extra_special_tokens": {},
|
| 203 |
+
"model_max_length": 131072,
|
| 204 |
+
"pad_token": "<|endoftext|>",
|
| 205 |
+
"split_special_tokens": false,
|
| 206 |
+
"tokenizer_class": "Qwen2Tokenizer",
|
| 207 |
+
"unk_token": null
|
| 208 |
+
}
|
vocab.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|