Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Jump to bottom

Can I use SentenceTransformerTrainer to train BAAI/bge-m3? #2962

Open
S1yuan opened this issue Sep 26, 2024 · 2 comments
Open

Can I use SentenceTransformerTrainer to train BAAI/bge-m3? #2962

S1yuan opened this issue Sep 26, 2024 · 2 comments

Comments

@S1yuan
Copy link

S1yuan commented Sep 26, 2024

No description provided.

@tomaarsen
Copy link
Collaborator

Hello!

Yes, but only the Dense component, not the Sparse and Multivector ones.
When you load BAAI/bge-m3 (or a finetuned version) with Sentence Transformers, you are also only using the Dense component.

  • Tom Aarsen

@MohammedAlhajji
Copy link

yes, but my CUDA memory usage was lower when I used the FlagEmbedding Library. It's somewhat based on sentence-transformers so i'm not sure why but will debug and see

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Assignees
No one assigned
Labels
None yet
Projects
None yet
Milestone
No milestone
Development

No branches or pull requests
3 participants
@tomaarsen @S1yuan @MohammedAlhajji