Skip to content

Conversation

@a3213105
Copy link
Contributor

Sync with Torch vervion.
When seq_length is larger than max support seq length, we reduce seq_length to max support seq length.

@Duyi-Wang
Copy link
Contributor

Update config.ini in examples/model_config all at once if add new params

@a3213105 a3213105 merged commit 0d549e0 into intel:main Mar 22, 2024
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

2 participants