| # 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 | |