Support idefics multimodal #7
Open
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
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Outdated suggestions cannot be applied.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.
This is similar to the Llama implementation in #4, but extended to multimodal HF models.
Idefics2 by HuggingFace supports multiple-image inputs. Its API output format is quite similar to ChatGPT's output format. I initially tried it with 50 frames, which is what GPT4-V was using, but that gave OOM, so I lowered the num_frames to 10.
Other multimodal models on HF should be quite similar to implement, though I think for things like Llava, multi-image input may not be supported off the shelf.