Skip to content

Add Qwen2.5_VL Architecture Definition #579

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

Open
wants to merge 1 commit into
base: main
Choose a base branch
from

Conversation

qiuxy28
Copy link

@qiuxy28 qiuxy28 commented May 14, 2025

When merging Qwen2.5-VL models with mergekit, the system fails with:
RuntimeError:Tensor visual.merger.mlp.1.bias required but not present in model Qwen/Qwen2.5-VL-7B-Instruct
The error occurs because visual.merger.mlp.1 is an activation function without trainable parameters, but our architecture definition incorrectly expects weight/bias parameters.

Changes

  1. Add Qwen2.5_VL Architecture Definition

Testing

  • Successfully merged Qwen2.5-VL models using both linear and TIES methods
  • Benchmark results show expected performance on multimodal tasks

Copy link


Thank you for your submission, we really appreciate it. Like many open-source projects, we ask that you sign our Contributor License Agreement before we can accept your contribution. You can sign the CLA by just posting a Pull Request Comment same as the below format.


I have read the CLA Document and I hereby sign the CLA


You can retrigger this bot by commenting recheck in this Pull Request. Posted by the CLA Assistant Lite bot.

@qiuxy28
Copy link
Author

qiuxy28 commented May 14, 2025

I have read the CLA Document and I hereby sign the CLA

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

Successfully merging this pull request may close these issues.

2 participants