2024-08-22 14:48:45 +08:00
|
|
|
# Alpaca-eval
|
2024-06-06 11:48:07 +08:00
|
|
|
alpaca-eval==0.6
|
2025-01-24 10:00:01 +08:00
|
|
|
# OlympiadBench
|
|
|
|
|
antlr4-python3-runtime==4.11
|
2024-08-22 14:48:45 +08:00
|
|
|
cn2an
|
2024-11-08 14:38:43 +08:00
|
|
|
# Dingo
|
|
|
|
|
dingo-python==1.1.2
|
2024-08-22 14:48:45 +08:00
|
|
|
# Icl topk retriever
|
2023-11-06 21:57:32 +08:00
|
|
|
faiss_gpu==1.7.2
|
2024-08-22 14:48:45 +08:00
|
|
|
# Humaneval, Humaneval X
|
|
|
|
|
-e git+https://github.com/open-compass/human-eval.git#egg=human-eval
|
|
|
|
|
# IFEval
|
|
|
|
|
langdetect
|
|
|
|
|
# TheoremQA
|
2025-03-13 20:52:50 +08:00
|
|
|
latex2sympy2==1.9.1
|
2024-08-22 14:48:45 +08:00
|
|
|
# Lawbench, leval
|
|
|
|
|
ltp
|
2025-02-20 19:32:12 +08:00
|
|
|
# Math
|
|
|
|
|
math-verify
|
2024-08-22 14:48:45 +08:00
|
|
|
# Taco, apps Dataset
|
|
|
|
|
pyext
|
|
|
|
|
# Law Bench
|
|
|
|
|
pypinyin
|
|
|
|
|
# RULER
|
2024-08-20 11:40:11 +08:00
|
|
|
wonderwords
|
