open_flamingo

An open-source framework for training large multimodal models.

MIT License

Downloads
1.5K
Stars
3.7K

Bot releases are visible (Hide)

open_flamingo - 2.0.1 Latest Release

Published by anas-awadalla about 1 year ago

What's Changed

New Contributors

Full Changelog: https://github.com/mlfoundations/open_flamingo/compare/2.0.0...2.0.1

open_flamingo - Second release

Published by i-gao over 1 year ago

Major codebase updates, along with five new models.

Changes:

  • Add gradient checkpointing, FullyShardedDataParallel
  • Remove color jitter when training
  • Fix cross-attention bug when calling generate()
  • Model releases
    • (CLIP ViT-L-14 / MPT-1B)
    • (CLIP ViT-L-14 / MPT-1B Dolly)
    • (CLIP ViT-L-14 / RedPajama-3B)
    • (CLIP ViT-L-14 / RedPajama-3B Instruct)
    • (CLIP ViT-L-14 / MPT-7B)
open_flamingo - Initial version w/ __init__ fix

Published by anas-awadalla over 1 year ago

Thanks to @chris-alexiuk for fixing!

open_flamingo - First release

Published by anas-awadalla over 1 year ago