Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

update docs qwen2-vl #1869

Merged
merged 2 commits into from
Aug 30, 2024
Merged

update docs qwen2-vl #1869

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
3ec975c
update docs
Jintao-Huang Aug 30, 2024
b5d37b8
update
Jintao-Huang Aug 30, 2024
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
13 changes: 13 additions & 0 deletions docs/source/Multi-Modal/qwen2-vl最佳实践.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -153,6 +153,19 @@ history: [['<img>http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/road

## 微调

### 图像OCR微调
我们使用 latex-ocr-print 数据集进行微调，该数据集的任务是进行Latex OCR。您可以在 modelscope 上找到该数据集: [https://modelscope.cn/datasets/AI-ModelScope/LaTeX_OCR](https://modelscope.cn/datasets/AI-ModelScope/LaTeX_OCR)

```bash
# 单卡A10/3090可运行
# GPU Memory: 20GB
SIZE_FACTOR=8 MAX_PIXELS=602112 CUDA_VISIBLE_DEVICES=0 swift sft \
--model_type qwen2-vl-7b-instruct \
--model_id_or_path qwen/Qwen2-VL-7B-Instruct \
--sft_type lora \
--dataset latex-ocr-print#20000
```

### 图像描述微调

我们使用 coco-en-mini 数据集进行微调，该数据集的任务是对图片内容进行描述。您可以在 modelscope 上找到该数据集: [https://modelscope.cn/datasets/modelscope/coco_2014_caption](https://modelscope.cn/datasets/modelscope/coco_2014_caption)
Expand Down
13 changes: 13 additions & 0 deletions docs/source_en/Multi-Modal/qwen2-vl-best-practice.md
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -139,6 +139,19 @@ history: [['<img>http://modelscope-open.oss-cn-hangzhou.aliyuncs.com/images/road

## Fine-tuning

### Image OCR fine-tuning
We fine-tune using latex-ocr-printdataset, which aims to describe the content of images. You can find this dataset on ModelScope: [https://modelscope.cn/datasets/AI-ModelScope/LaTeX_OCR](https://modelscope.cn/datasets/AI-ModelScope/LaTeX_OCR)

```bash
# Single-card A10/3090 can run
# GPU Memory: 20GB
SIZE_FACTOR=8 MAX_PIXELS=602112 CUDA_VISIBLE_DEVICES=0 swift sft \
--model_type qwen2-vl-7b-instruct \
--model_id_or_path qwen/Qwen2-VL-7B-Instruct \
--sft_type lora \
--dataset latex-ocr-print#20000
```

### Image Description Fine-tuning

We fine-tune using the coco-en-mini dataset, which aims to describe the content of images. You can find this dataset on ModelScope: [https://modelscope.cn/datasets/modelscope/coco_2014_caption](https://modelscope.cn/datasets/modelscope/coco_2014_caption)
Expand Down
Loading