Rauf Yagfarov comments

Repositories
Issues
Comments

Results 13 comments of


                                            Rauf Yagfarov

Video Grounding on a sequence of frame images

Apparently due to [this](https://github.com/QwenLM/Qwen2.5-VL/issues/716) add_vision_id is ignored

Issue with add_vision_ids=True argument

I added vision ids just by replacing the chat template: ```python processor.chat_template = chat_template_old chat_template_new = "{% set image_count = namespace(value=0) %}{% set video_count = namespace(value=0) %}{% for message in...

Training on custom long range dataset

How to set 'depth' properly ?