Add support for Molmo-D-7B Model #1542
Closed
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
Any updates on this? |
|
@jlia0 I'm working on this slowly since I'm juggling a couple things. It will take me probably a week. |
|
/ready |
merrymercy
requested changes
Oct 11, 2024
| def test_molmo_d(self): | ||
| for text, images in CONVS: | ||
| for model_path, torch_dtype, tolerance in MODELS: | ||
| self.assert_srt_vision_backbone_and_hf_vision_backbone_close( |
There was a problem hiding this comment.
Do you have an end-to-end test for the whole model?
Can you add a new test here https://github.com/sgl-project/sglang/blob/main/test/srt/test_vision_openai_server.py?
zhyncs
requested review from
Ying1123,
zhyncs,
hnyls2002,
ispobock and
ByronHsu
as code owners
|
Closed due to inactivity. Feel free to reopen if you have new progress. |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
Support for https://huggingface.co/allenai/Molmo-7B-D-0924
It's been awhile since I've supported a model, so I figured it would be good practice. It seems to be a CLIP-Vit encoder with some embedding pooling and then a Qwen LLM backbone. I'm trying to figure out the vision backbone first and then I think the frozen parts will come together by importing from Qwen2.py file.