bwang0911 changed pull request status to open
Jina AI org
This comment has been hidden
Jina AI org

I think we can just move this function call after truncation instead of modifying truncate_embeddings
https://huggingface.co/jinaai/xlm-roberta-flash-implementation/blob/12700ba4972d9e900313a85ae855f5a76fb9500e/modeling_xlm_roberta.py#L592

Ready to merge
This branch is ready to get merged automatically.

Sign up or log in to comment