Sub category scores on mtbench
#1
by
RASMUS
- opened
Could you release the results in subcategories for mtbench (Writing, reasoning etch.)
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