Fixes for issues in generating pre-training data by converting images into discrete tokens

AILab-CVC / SEED

Official implementation of SEED-LLaMA (ICLR 2024).

https://ailab-cvc.github.io/seed

Other

515 stars 30 forks source link

Open shubhamgarg21 opened 3 months ago

shubhamgarg21 commented 3 months ago

Step 3 of Multimodal LLM Pre-training was failing.

Fix for same is in this PR