Skip to content

Latest commit

 

History

History
21 lines (14 loc) · 421 Bytes

EVAL.md

File metadata and controls

21 lines (14 loc) · 421 Bytes

Evaluation

Eval BISON

$ bash scripts/v1_5/eval/eval_bison.sh

Eval SVO Probes

$ bash scripts/v1_5/eval/eval_svo_probes.sh

Eval NLVR2

$ bash scripts/v1_5/eval/eval_nlvr2.sh

Eval EQBEN

$ bash scripts/v1_5/eval/eval_eqben.sh

Eval COLA

$ bash scripts/v1_5/eval/eval_cola.sh

Eval CaD QA

$ bash scripts/v1_5/eval/eval_cad_qa.sh

Code for LLM-assisted evaluation will be released soon.