89 lines
3.8 KiB
Markdown
89 lines
3.8 KiB
Markdown
---
|
||
license: apache-2.0
|
||
language:
|
||
- zh
|
||
- en
|
||
pipeline_tag: image-text-to-text
|
||
tags:
|
||
- multimodal
|
||
library_name: transformers
|
||
base_model:
|
||
- Qwen/Qwen2.5-VL-7B-Instruct
|
||
---
|
||
|
||
# Qwen2.5-VL-7B-Instruct-GPTQ-Int4
|
||
|
||
This is an **UNOFFICIAL** GPTQ-Int4 quantized version of the `Qwen2.5-VL-7B-Instruct` model using `gptqmodel` library.
|
||
|
||
The model is compatible with the latest `transformers` library (which can run non-quantized Qwen2.5-VL models).
|
||
|
||
### Performance
|
||
|
||
| Model | Size (Disk) | ChartQA (test) | OCRBench |
|
||
| ------------------------------------------------------------ | :---------: | :------------: | :------: |
|
||
| [Qwen2.5-VL-3B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct) | 7.1 GB | 83.48 | 791 |
|
||
| [Qwen2.5-VL-3B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-3B-Instruct-AWQ) | 3.2 GB | 82.52 | 786 |
|
||
| **Qwen2.5-VL-3B-Instruct-GPTQ-Int4** | 3.2 GB | 82.56 | 784 |
|
||
| [Qwen2.5-VL-7B-Instruct](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct) | 16.0 GB | 83.2 | 846 |
|
||
| [Qwen2.5-VL-7B-Instruct-AWQ](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct-AWQ) | 6.5 GB | 79.68 | 837 |
|
||
| **Qwen2.5-VL-7B-Instruct-GPTQ-Int4** | 6.5 GB | 81.48 | 845 |
|
||
|
||
|
||
#### Note
|
||
|
||
- Evaluations are performed using [lmms-eval](https://github.com/EvolvingLMMs-Lab/lmms-eval) with default setting.
|
||
- GPTQ models are computationally more effective (fewer VRAM usage, faster inference speed) than AWQ series in these evaluations.
|
||
|
||
### Quick Tour
|
||
|
||
Install the required libraries:
|
||
```
|
||
pip install git+https://github.com/huggingface/transformers accelerate qwen-vl-utils
|
||
pip install gptqmodel tokenicer # optional
|
||
```
|
||
|
||
Sample code:
|
||
```python
|
||
from transformers import Qwen2_5_VLForConditionalGeneration, AutoTokenizer, AutoProcessor
|
||
from qwen_vl_utils import process_vision_info
|
||
|
||
model = Qwen2_5_VLForConditionalGeneration.from_pretrained(
|
||
"hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4",
|
||
attn_implementation="flash_attention_2",
|
||
device_map="auto"
|
||
)
|
||
processor = AutoProcessor.from_pretrained("hfl/Qwen2.5-VL-7B-Instruct-GPTQ-Int4")
|
||
|
||
messages = [{
|
||
"role": "user",
|
||
"content": [
|
||
{"type": "image", "image": "https://raw.githubusercontent.com/ymcui/Chinese-LLaMA-Alpaca-3/refs/heads/main/pics/banner.png"},
|
||
{"type": "text", "text": "请你描述一下这张图片。"},
|
||
],
|
||
}]
|
||
|
||
text = processor.apply_chat_template(messages, tokenize=False, add_generation_prompt=True)
|
||
image_inputs, video_inputs = process_vision_info(messages)
|
||
inputs = processor(
|
||
text=[text], images=image_inputs, videos=video_inputs,
|
||
padding=True, return_tensors="pt",
|
||
).to("cuda")
|
||
|
||
generated_ids = model.generate(**inputs, max_new_tokens=512)
|
||
generated_ids_trimmed = [out_ids[len(in_ids) :] for in_ids, out_ids in zip(inputs.input_ids, generated_ids)]
|
||
output_text = processor.batch_decode(generated_ids_trimmed, skip_special_tokens=True, clean_up_tokenization_spaces=False)
|
||
print(output_text)
|
||
```
|
||
|
||
Results:
|
||
```
|
||
['这张图片展示了一个标志或图标，包含以下内容：\n\n1. 左侧有一个圆形的图标，里面有一幅插画，描绘了两只羊驼（Alpaca），背景中有树木和一座亭子。\n2. 中间部分用中文写着“中文LLaMA & Alpaca大模型”，意思是“Chinese LLaMA & Alpaca Large Language Models”。\n3. 右侧有一个黑色的数字“3”，旁边有一些电路板的图案。\n\n整体来看，这个标志可能与中文的大型语言模型（LLaMA和Alpaca）有关，可能是一个项目、平台或产品的名称。']
|
||
```
|
||
|
||
### Disclaimer
|
||
- **This is NOT an official model by Qwen. Use at your own risk.**
|
||
- For detailed usage, please check [Qwen2.5-VL's page](https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct).
|
||
|
||
|
||
|