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.

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

vllm grpo trainer不支持qwen2.5VL #133

Open
tcy6 opened this issue Feb 24, 2025 · 0 comments
Open

vllm grpo trainer不支持qwen2.5VL #133

tcy6 opened this issue Feb 24, 2025 · 0 comments

Comments

@tcy6
Copy link

tcy6 commented Feb 24, 2025

vllm 0.7.2支持qwen2VL模型,也能跑通训练代码,但是不支持qwen2.5VL模型,尝试更新vllm至0.7.3后,出现以下问题。

raise ValueError(
[rank0]: ValueError: Attempted to assign 308 + 104 + 104 + 104 + 104 + 104 + 104 = 932 multimodal tokens to 1159 placeholders

这个问题在vllm 0.7.2的时候,是通过在初始化vllm LLM时传入以下参数解决。

mm_processor_kwargs = {
  "max_pixels": max_pixels,
  "min_pixels": min_pixels,
}

但是在vllm 0.7.3时,这种方式失效了。
希望能够解决一下这个问题,十分感谢!
@TobiasLee 能麻烦大佬帮忙看看嘛~

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant