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

support qwen2 and siglip weight conversion script to enable training … #1221

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

Conversation

tao-githup
Copy link

…with llava-next and llava-onevision

@@ -60,8 +60,9 @@ def __init__(
self.img_h = img_h
self.img_w = img_w

assert self.img_h % self.patch_dim == 0
assert self.img_w % self.patch_dim == 0
if model_subtype == "siglip":
Copy link
Collaborator

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Why are we moving this assert so it's only used in the siglip case? We want it for the base clip case don't we?

Copy link
Author

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

We are moving this assert to be used only in the siglip case because the model used in siglip does not satisfy this assert, while the models used in several clip cases do satisfy it. By the way, do we have any specific reason for adding this assert before? If there is no other special reason, we can consider removing it.

Copy link

Marking as stale. No activity in 60 days.

@github-actions github-actions bot added the stale No activity in 60 days on issue or PR label Dec 17, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
stale No activity in 60 days on issue or PR
Projects
None yet
Development

Successfully merging this pull request may close these issues.

2 participants