support for qwen2.5_vl_3b
Open
Feature
- Dominant language
- Python
- Stars
- 133k
- Forks
- 15.7k
- Avg merge
- 1d 6h
- Merged PRs (30d)
- 155
Description
### Feature Idea
only support 7b
error while 3b
18:11:48.347 [Warning] [ComfyUI-0/STDERR] RuntimeError: Given normalized_shape=[3584], expected input with shape [*, 3584], but got input of size[1, 200, 2048]
### Existing Solutions
_No response_
### Other
_No response_
Contributor guide
Research direction
No files or tests are named. Reproduce the Qwen2.5-VL 3B loading error and compare its tensor shapes with the currently supported 7B path; done means the 3B model loads without the reported normalized_shape mismatch.
Written by the indexing model from the issue text.
Assessment
- Tech stack
- python, pytorch
- Domain
- machine-learning
- Issue type
- Feature
- Difficulty
- 4/5
- Estimated time
- 3-5 days
- Activity status
- Stale
- Clarity
- Needs clarification
- Newbie friendliness
- 35/100