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

[WIP] support for more vlms #390

Open
wants to merge 4 commits into
base: main
Choose a base branch
from
Open

Conversation

n1ck-guo
Copy link
Contributor

@n1ck-guo n1ck-guo commented Dec 19, 2024

  • support for more vlms: solvlm, aria(wip), llama-3.2v-cot, deepseek-vl2
  • vl 70b+ on single card
  • new processor for all hf-model
  • modify get_multimodal_block_names (find language/vision/...)

Signed-off-by: n1ck-guo <[email protected]>
@n1ck-guo n1ck-guo requested review from WeiweiZhang1 and wenhuach21 and removed request for WeiweiZhang1 December 19, 2024 06:08
@@ -160,6 +160,9 @@ def __init__(
self.template, model=model, tokenizer=tokenizer, processor=processor, image_processor=image_processor)
dataset = self.template.default_dataset if dataset is None else dataset

if model.config.model_type == "deepseek_vl_v2":
Copy link
Contributor

Choose a reason for hiding this comment

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

the setting here is a little tricky. Could the quantizing-non-text-module still be supported?

Signed-off-by: n1ck-guo <[email protected]>
Signed-off-by: n1ck-guo <[email protected]>
@rubentorresbonet
Copy link

any chance to use auto rounder with Aria-UI or Aria?

@wenhuach21
Copy link
Contributor

any chance to use auto rounder with Aria-UI or Aria?
@n1ck-guo , could you take a look? If we have already supported it, we may publish the quantized model.
@rubentorresbonet We are approaching the Chinese New Year. So if the model needs extra support, I'm afraid this may be delayed until after the holiday.

@rubentorresbonet
Copy link

rubentorresbonet commented Jan 20, 2025

thanks for the answer. Surely Qwen2VLForConditionalGeneration is not the class to use for Aria-UI-base? Any example or saved model would be great. Thanks

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.

3 participants