# Alpaca-eval
alpaca-eval==0.6
# OlympiadBench
antlr4-python3-runtime==4.11
cn2an
# Dingo
dingo-python==1.5.0
# Icl topk retriever
faiss_gpu==1.7.2
# Humaneval, Humaneval X
-e git+https://github.com/open-compass/human-eval.git#egg=human-eval
# IFEval
langdetect
# Lawbench, leval
ltp
# Math
math-verify[antlr4_11_0]
# Taco, apps Dataset
pyext
# Law Bench
pypinyin
# Smolinstruct
rdkit
# RULER
wonderwords