Sub category scores on mtbench

#1
by RASMUS - opened

Could you release the results in subcategories for mtbench (Writing, reasoning etch.)

LumiOpen org

We have updated the model card with the per-category MTBench scores. The overall average has changed slightly from 5.93 to 6.16 for English and from 5.9 to 5.73 for Finnish. The new scores are from our latest finetuning run after we filtered out some samples from the dataset.

laineyyy changed discussion status to closed
Your need to confirm your account before you can post a new comment.

Sign up or log in to comment