Skip to content

Conversation

@lim185
Copy link
Contributor

@lim185 lim185 commented Mar 2, 2026

Model training code revised. Also model designs were revised to avoid the gradient explosion problem in training the decoder portion.

@lim185 lim185 merged commit 0ebc6c2 into main Mar 2, 2026
1 check failed
@lim185 lim185 deleted the train-integration branch March 2, 2026 01:56
Sign in to join this conversation on GitHub.

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant