Skip to content

Releases: octo-models/octo

v1.5

24 May 00:28
5eaa5c6
Compare
Choose a tag to compare

What's Changed

  • Improved cross-attention between visual and language tokens by repeating language tokens at every timestep in the context window.
  • Augmented the language instructions in the data with rephrasings from GPT-3.5.
  • Bug fixes:
    • Turned off dropout in the diffusion head due to incompatibility with layer norm.
    • Fixed an off-by-one error with the attention mask.
    • Fixed an issue where different image augmentations did not get fresh random seeds.

v0.1.0

18 Dec 16:56
37951e4
Compare
Choose a tag to compare

Creating this to document the initial release version of Octo (12/14/23).