Fix max tokens in LLM2Vec Models

#96
Massive Text Embedding Benchmark org
No description provided.
Massive Text Embedding Benchmark org
edited Apr 20

Hi @Muennighoff ,

I think I misunderstood max tokens field on the MTEB leaderboard. Previously I put 512, which was the max length we used in MTEB eval. However, looking at other entries on the leaderboard, it seems to be the field to indicate the max length supported by the model. I have updated all LLM2Vec models accordingly. Please merge the changes at your convenience. Thank you!

vaibhavad changed pull request status to open
Massive Text Embedding Benchmark org

Looks good! Thanks for the fix.

tomaarsen changed pull request status to merged

Sign up or log in to comment