X-InstructBLIP Code #599
Merged
X-InstructBLIP Code #599
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
…ypos/cleaned up some comments
maulikmadhavi
pushed a commit
to maulikmadhavi/LAVIS
that referenced
this pull request
May 19, 2024
X-InstructBLIP Code
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Outdated suggestions cannot be applied.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.
Adds multimodal capabilities to LAVIS (audio + 3D processors and encoders). Includes ULIP code (https://github.com/salesforce/ULIP) for 3D encoding and BEATs (https://github.com/microsoft/unilm/tree/master/beats) for audio encoding. Includes model code for X-InstructBLIP an extension of InstructBLIP to multiple modalities.
Finally, a collection of dataset support is added, including: [Audio]: AudioCaps, Clotho, AudioSet, WavCaps, ESC50, [3D] Objaverse, ModelNet [Video] MusicAVQA, VALOR, VATEX, WebVideo, VLEP, VIOLIN.
In addition, separate instruction tuning datasets are introduced with their own configs + an instruction text processor that randomly samples instruction templates for a variety of modalities and tasks.