SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Qwen2-VL: clean-up and add more tests (#33354)

Browse Source 
* clean-up on qwen2-vl and add generation tests

* add video tests

* Update tests/models/qwen2_vl/test_processing_qwen2_vl.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* fix and add better tests

* Update src/transformers/models/qwen2_vl/image_processing_qwen2_vl.py

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* update docs and address comments

* Update docs/source/en/model_doc/qwen2_vl.md

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* Update docs/source/en/model_doc/qwen2_vl.md

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>

* update

* remove size at all

---------

Co-authored-by: amyeroberts <22614925+amyeroberts@users.noreply.github.com>
This commit is contained in:
Raushan Turganbay
2024-09-12 18:24:04 +02:00
committed by GitHub
parent 8f8af0fb38
commit 2f611d30d9
6 changed files with 297 additions and 106 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/source/en/model_doc/qwen2_vl.md
View File

@@ -229,8 +229,6 @@ processor = AutoProcessor.from_pretrained("Qwen/Qwen2-VL-7B-Instruct", min_pixel
```
#### Multiple Image Inputs
By default, images and video content are directly included in the conversation. When handling multiple images, it's helpful to add labels to the images and videos for better reference. Users can control this behavior with the following settings: