Skip to content

fix: apply text_projection for 600M model fine-tuning#188

Open
zhuxiaoxuhit wants to merge 1 commit intoQwenLM:mainfrom
zhuxiaoxuhit:fix-600m-finetuning-dimension-mismatch
Open

fix: apply text_projection for 600M model fine-tuning#188
zhuxiaoxuhit wants to merge 1 commit intoQwenLM:mainfrom
zhuxiaoxuhit:fix-600m-finetuning-dimension-mismatch

Conversation

@zhuxiaoxuhit
Copy link
Copy Markdown

Fix dimension mismatch by applying text_projection when text_hidden_size != hidden_size (for 600M model)

Fix dimension mismatch by applying text_projection when text_hidden_size != hidden_size
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.

1 participant