# Alpaca-eval alpaca-eval==0.6 # OlympiadBench antlr4-python3-runtime==4.11 cn2an # Dingo dingo-python==1.1.2 # Icl topk retriever faiss_gpu==1.7.2 # IFEval langdetect # TheoremQA latex2sympy2 # Lawbench, leval ltp # Math math-verify # Taco, apps Dataset pyext # Law Bench pypinyin # RULER wonderwords