Skip to content

Issues: QwenLM/Qwen2.5-VL

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

393 Open 175 Closed
393 Open 175 Closed
Author
Filter by author
Loading
Label
Filter by label
Loading
Use alt + click/return to exclude labels
or ⇧ + click/return for logical OR
Projects
Filter by project
Loading
Milestones
Filter by milestone
Loading
Assignee
Filter by who’s assigned
Sort
Sort by
Newest Oldest Most commented Least commented Recently updated Least recently updated Best match
Most reactions
👍 👎 😄 🎉 😕 ❤️ 🚀 👀

Issues list

How to distinguish different images in "Multi image inference"?
#745 opened Feb 8, 2025 by vefalun
如何在 VLLM 部署后使用 API 直接传递视频进行推理？
#742 opened Feb 8, 2025 by XyWzzZ
the context length of the model is too long。My scene doesn't need such a long context. How can I make it smaller, such as 4096
#741 opened Feb 8, 2025 by alanMachineLeraning
1
How to sovle warning:The context length of the model is too short to hold the multi-modal embeddings in the worst case
#738 opened Feb 8, 2025 by vefalun
1
Base model of Qwen/Qwen2.5-VL-7B-Instruct
#737 opened Feb 8, 2025 by weizhepei
3
image_inputs, video_inputs, video_kwargs = process_vision_info(messages, return_video_kwargs=True) cause stucking while loading some videos
#736 opened Feb 7, 2025 by LAW1223
1
There's an error when using flash_attention2
#735 opened Feb 7, 2025 by pentjosh
how to reduce the max_token when using vllm with the parameter "limit_mm_per_prompt" > 1 when initiating LLM( )
#734 opened Feb 7, 2025 by luosting
Grounding
#733 opened Feb 7, 2025 by SFTJBD
3
Prompt for GUI Agent
#732 opened Feb 7, 2025 by zhaopy10
2
cookbooks/mobile_agent.ipynb相同prompt和图片，不同结果
#729 opened Feb 6, 2025 by mangoyuan
1
The parameters about visual part and llm part
#727 opened Feb 6, 2025 by junwei0812
Prompt used for os environment benchmark?
#725 opened Feb 6, 2025 by cjfcsjt
5
[Bug]: TypeError: Qwen2_5_VLForConditionalGeneration.forward() got an unexpected keyword argument 'decoder_input_ids'
#744 opened Feb 5, 2025 by badhon1512
2
[Bug]: TypeError: Qwen2_5_VLForConditionalGeneration.forward() got an unexpected keyword argument 'decoder_input_ids'
#743 opened Feb 5, 2025 by badhon1512
2
[Bug]: TypeError: Qwen2_5_VLForConditionalGeneration.forward() got an unexpected keyword argument 'decoder_input_ids'
#739 opened Feb 5, 2025 by badhon1512
2
Qwen2_5_VLForConditionalGeneration
#723 opened Feb 5, 2025 by Wuhuddy
1
[Help Wanted]: Grounding Bias After Fine-Tuning on Qwen2.5-VL-7B
#721 opened Feb 4, 2025 by MuyaoLi-jimo
1 task done
5
Can I use vllm for qwenvl-2.5?
#720 opened Feb 4, 2025 by linchen111
1
is there any quantized models for Qwen2.5-VL
#719 opened Feb 4, 2025 by aabbccddwasd
7
Comparison of Text-Only Benchmark Performance with Qwen2.5-Instruct
#717 opened Feb 4, 2025 by y-rok
Issue with add_vision_ids=True argument
#716 opened Feb 4, 2025 by rajatguptakgp
How is image generation implemented in Qwen Chat? Is Qwen2.5 followed by a diffusion model or SD?
#740 opened Feb 4, 2025 by missTL
2
Reproduce results of LVBench
#715 opened Feb 3, 2025 by zgzxy001
4
DocVQA Evaluation Prompt
#714 opened Feb 3, 2025 by eladb3
1
ProTip! Type g i on any issue or pull request to go back to the issue listing page.