Vision multimodal #369
Draft
Vision multimodal #369
Conversation
This file contains hidden or 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
tscholak
reviewed
Oct 4, 2025
| hint=FieldHint.architecture, | ||
| ) | ||
| # TODO: ====== Appropriate name?? ====== | ||
| decoder: BlockSequenceConfig = Field( |
| peft=self._peft, | ||
| ) | ||
| # TODO: ====== Appropriate name?? ====== | ||
| self.decoder = self._config.decoder.get_layer( |
| peft=self._peft, | ||
| ) | ||
| # TODO: ====== Hidden dim ====== | ||
| self.adapter = self._config.adapter.get_layer( |
There was a problem hiding this comment.
I don't think we want to make the adapter part of the encoder, because adapter tensor shapes depend on decoder. And we also want to mix and match existing pre trained encoders and decoders...
There was a problem hiding this comment.
It's the same with every module basically, their shapes all need to match. I'm organizing the modules so thy manage their internal hidden shapes, but input and output shapes are managed by the parent modules (hidden_dim argument), so in that case it makes sense to keep the adapter here.
The todo refers to the MLP assuming matching input and output dimensions, that's an easy fix but I haven't gotten to it yet.
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Outdated suggestions cannot be applied.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.
✨ Description
An attempt at integrating multimodal vision models to main. Still a lot of work to do...