|
--- |
|
license: mit |
|
library_name: transformers |
|
pipeline_tag: image-text-to-text |
|
--- |
|
|
|
# Skywork-R1V-38B-AWQ |
|
|
|
<div align="center"> |
|
<img src="skywork-logo.png" alt="Introduction Image" width="500" height="400"> |
|
</div> |
|
|
|
## 📖 [Technical Report](https://github.com/SkyworkAI/Skywork-R1V/blob/main/Skywork_R1V.pdf) | 💻 [GitHub](https://github.com/SkyworkAI/Skywork-R1V) | 🌐 [Wisemodel](https://wisemodel.cn/models/Skywork/Skywork-R1V) |
|
|
|
<div align="center"> |
|
|
|
[](https://github.com/SkyworkAI/Skywork-R1V/stargazers) [](https://github.com/SkyworkAI/Skywork-R1V/fork) |
|
|
|
</div> |
|
|
|
|
|
## Evaluation |
|
|
|
<div align="center"> |
|
<b>Comparison with Larger-Scale Open-Source and Closed-Source Models</b> |
|
</div> |
|
|
|
<table align="center"> |
|
<thead> |
|
<tr> |
|
<th></th> |
|
<th align="center"><strong>Benchmark</strong></th> |
|
<th align="center"><strong>LLM</strong></th> |
|
<th align="center" colspan="5"><strong>VLM</strong></th> |
|
</tr> |
|
<tr> |
|
<th></th> |
|
<th></th> |
|
<th align="center"><strong>QwQ-32B-Preview</strong></th> |
|
<th align="center"><strong>InternVL-2.5-38B</strong></th> |
|
<th align="center"><strong>VILA 1.5-40B</strong></th> |
|
<th align="center"><strong>InternVL2-40B</strong></th> |
|
<th align="center"><strong>Skywork-R1V-38B</strong></th> |
|
<th align="center"><strong>Skywork-R1V-AWQ</strong></th> |
|
</tr> |
|
</thead> |
|
<tbody> |
|
<tr> |
|
<td rowspan="3">Reasoning</td> |
|
<td>MATH-500</td> |
|
<td align="center">90.6</td> |
|
<td align="center">-</td> |
|
<td align="center">-</td> |
|
<td align="center">-</td> |
|
<td align="center"><strong>94.0</strong></td> |
|
<td align="center">86.0</td> |
|
</tr> |
|
<tr> |
|
<td>AIME 2024</td> |
|
<td align="center">50.0</td> |
|
<td align="center">-</td> |
|
<td align="center">-</td> |
|
<td align="center">-</td> |
|
<td align="center"><strong>72.0</strong></td> |
|
<td align="center">61.0</td> |
|
</tr> |
|
<tr> |
|
<td>GPQA</td> |
|
<td align="center">54.5</td> |
|
<td align="center">-</td> |
|
<td align="center">-</td> |
|
<td align="center">-</td> |
|
<td align="center"><strong>61.6</strong></td> |
|
<td align="center">56.5</td> |
|
</tr> |
|
<tr> |
|
<td rowspan="2">Vision</td> |
|
<td>MathVista(mini)</td> |
|
<td align="center">-</td> |
|
<td align="center">71.9</td> |
|
<td align="center">49.5</td> |
|
<td align="center">63.7</td> |
|
<td align="center">67.5</td> |
|
<td align="center">59.9</td> |
|
</tr> |
|
<tr> |
|
<td>MMMU(Val)</td> |
|
<td align="center">-</td> |
|
<td align="center">63.9</td> |
|
<td align="center">55.1</td> |
|
<td align="center">55.2</td> |
|
<td align="center"><strong>69.0</strong></td> |
|
<td align="center">60.1</td> |
|
</tr> |
|
</tbody> |
|
</table> |
|
|
|
## Usage |
|
You can use the quantized model with different inference frameworks: |
|
### Using VLLM |
|
|
|
#### Python API |
|
|
|
```python |
|
import os |
|
from vllm import LLM, SamplingParams |
|
from vllm.entrypoints.chat_utils import load_chat_template |
|
|
|
model_name = "Skywork/Skywork-R1V-38B-AWQ" # or local path |
|
llm = LLM(model_name, |
|
dtype='float16', |
|
quantization="awq", |
|
gpu_memory_utilization=0.85, |
|
max_model_len=4096, |
|
trust_remote_code=True, |
|
) |
|
|
|
# Add your inference code here |
|
``` |
|
|
|
#### OpenAI-compatible API Server |
|
|
|
```bash |
|
MODEL_ID="Skywork/Skywork-R1V-38B-AWQ" # or local path |
|
|
|
|
|
CUDA_VISIBLE_DEVICES=0 \ |
|
python -m vllm.entrypoints.openai.api_server \ |
|
--model $MODEL_ID \ |
|
--dtype float16 \ |
|
--quantization awq \ |
|
--port 23334 \ |
|
--max-model-len 12000 \ |
|
--gpu-memory-utilization 0.9 \ |
|
--trust-remote-code |
|
``` |
|
|
|
### Using LMDeploy |
|
|
|
```python |
|
import os |
|
from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig |
|
from lmdeploy.vl import load_image |
|
|
|
model_path = "Skywork/Skywork-R1V-38B-AWQ" # or local path |
|
|
|
engine_config = TurbomindEngineConfig(cache_max_entry_count=0.75) |
|
chat_template_config = ChatTemplateConfig(model_name=model_path) |
|
pipe = pipeline(model_path, |
|
backend_config=engine_config, |
|
chat_template_config=chat_template_config, |
|
) |
|
|
|
# Example: Multimodal inference |
|
image = load_image('table.jpg') |
|
response = pipe(('Describe this image?', image)) |
|
print(response.text) |
|
``` |
|
|
|
## Hardware Requirements |
|
|
|
The AWQ quantization reduces the memory footprint compared to the original FP16 model. We recommend: |
|
|
|
- At least one GPU with 30GB+ VRAM for inference |
|
- For optimal performance with longer contexts, 40GB+ VRAM is recommended |
|
|
|
## Citation |
|
|
|
If you use this model in your research, please cite: |
|
|
|
```bibtex |
|
@article{skywork2025r1v, |
|
title = {Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought}, |
|
author = {Yi Peng, Chris, Xiaokun Wang, Yichen Wei, Jiangbo Pei, Weijie Qiu, Ai Jian, Yunzhuo Hao, Jiachun Pan, Tianyidan Xie, Li Ge, Rongxian Zhuang, Xuchen Song, Yang Liu, Yahui Zhou}, |
|
year = {2025}, |
|
journal = {https://github.com/SkyworkAI/Skywork-R1V/blob/main/report/Skywork_R1V.pdf}, |
|
url = {https://huggingface.co/Skywork/Skywork-R1V-38B} |
|
} |
|
``` |
|
|
|
# Skywork-R1V-38B-AWQ (中文说明) |
|
|
|
|
|
## 使用方法 |
|
您可以使用不同的推理框架来使用这个量化模型： |
|
|
|
### 使用 VLLM |
|
|
|
#### Python API |
|
|
|
```python |
|
import os |
|
from vllm import LLM, SamplingParams |
|
from vllm.entrypoints.chat_utils import load_chat_template |
|
|
|
model_name = "Skywork/Skywork-R1V-38B-AWQ" # 或本地路径 |
|
llm = LLM(model_name, |
|
dtype='float16', |
|
quantization="awq", |
|
gpu_memory_utilization=0.85, |
|
max_model_len=4096, |
|
trust_remote_code=True, |
|
) |
|
|
|
# 在此添加您的推理代码 |
|
``` |
|
|
|
#### OpenAI 兼容的 API 服务器 |
|
|
|
```bash |
|
MODEL_ID="Skywork/Skywork-R1V-38B-AWQ" # 或本地路径 |
|
|
|
CUDA_VISIBLE_DEVICES=0 \ |
|
python -m vllm.entrypoints.openai.api_server \ |
|
--model $MODEL_ID \ |
|
--dtype float16 \ |
|
--quantization awq \ |
|
--port 23334 \ |
|
--max-model-len 12000 \ |
|
--gpu-memory-utilization 0.9 \ |
|
--trust-remote-code |
|
``` |
|
|
|
### 使用 LMDeploy |
|
|
|
```python |
|
import os |
|
from lmdeploy import pipeline, TurbomindEngineConfig, ChatTemplateConfig |
|
from lmdeploy.vl import load_image |
|
|
|
model_path = "Skywork/Skywork-R1V-38B-AWQ" # 或本地路径 |
|
|
|
engine_config = TurbomindEngineConfig(cache_max_entry_count=0.75) |
|
chat_template_config = ChatTemplateConfig(model_name=model_path) |
|
pipe = pipeline(model_path, |
|
backend_config=engine_config, |
|
chat_template_config=chat_template_config, |
|
) |
|
|
|
# 示例：多模态推理 |
|
image = load_image('table.jpg') |
|
response = pipe(('描述这个图片？', image)) |
|
print(response.text) |
|
``` |
|
|
|
## 硬件要求 |
|
|
|
与原始 FP16 模型相比，AWQ 量化减少了内存占用。我们建议： |
|
|
|
- 至少一块 30GB+ 显存的 GPU 用于推理 |
|
- 对于更长上下文的最佳性能，建议使用 40GB+ 显存 |
|
|
|
## 引用 |
|
|
|
如果您在研究中使用此模型，请引用： |
|
|
|
```bibtex |
|
@misc{peng2025skyworkr1vpioneeringmultimodal, |
|
title={Skywork R1V: Pioneering Multimodal Reasoning with Chain-of-Thought}, |
|
author={Yi Peng and Chris and Xiaokun Wang and Yichen Wei and Jiangbo Pei and Weijie Qiu and Ai Jian and Yunzhuo Hao and Jiachun Pan and Tianyidan Xie and Li Ge and Rongxian Zhuang and Xuchen Song and Yang Liu and Yahui Zhou}, |
|
year={2025}, |
|
eprint={2504.05599}, |
|
archivePrefix={arXiv}, |
|
primaryClass={cs.CV}, |
|
url={https://arxiv.org/abs/2504.05599}, |
|
} |
|
``` |
