unitxt

unitxt copied to clipboard

yoavkatz

Closes: https://github.com/IBM/unitxt/issues/1517

elronbandel

Add new processors and update type hints for response assessment tasks

1

elronbandel

yoavkatz

bnayahu

Safety benchmark comprised of AttaQ, ProvoQ, AirBench, and AILuminate, all with Granite Guardian as judge.

bnayahu

yoavkatz

dafnapension

New metric definitions for llama-3-3-70b as judge in Arena Hard benchmark * Added metric definitions for llama-3-3-70b as judge in Arena Hard benchmark supporting: * WML Inference Engine * Generic...

kmazrolina

Rag metric update again

1

Repeating #1945 here again. To the letter. It seems to me that github could not digest the late addition of `.github/actions/install-internal-pip/action.yml` so repeated here, when that action is already in.

dafnapension