sci-ml/lm-eval
A framework for evaluating language models (lm-evaluation-harness)
Screenshots
View
Download
BrowseRuntime Dependencies
lm-eval-0.4.12
>=sci-ml/datasets-2.16.0[python_single_target_python3_12
(-)
?
,python_single_target_python3_13
(-)
?
,python_single_target_python3_14
(-)
?
]
>=sci-ml/evaluate-0.4.0[python_single_target_python3_12
(-)
?
,python_single_target_python3_13
(-)
?
,python_single_target_python3_14
(-)
?
]
vllm?
( >=dev-python/vllm-0.18.0[python_single_target_python3_12
(-)
?
,python_single_target_python3_13
(-)
?
,python_single_target_python3_14
(-)
?
] )
python_single_target_python3_12?
( dev-python/dill[python_targets_python3_12
(-)
] dev-python/jinja2[python_targets_python3_12
(-)
] dev-python/more-itertools[python_targets_python3_12
(-)
] dev-python/numpy[python_targets_python3_12
(-)
] dev-python/pytablewriter[python_targets_python3_12
(-)
] dev-python/rouge-score[python_targets_python3_12
(-)
] dev-python/sacrebleu[python_targets_python3_12
(-)
] dev-python/scikit-learn[python_targets_python3_12
(-)
] dev-python/sqlitedict[python_targets_python3_12
(-)
] dev-python/tqdm[python_targets_python3_12
(-)
] dev-python/typing-extensions[python_targets_python3_12
(-)
] dev-python/word2number[python_targets_python3_12
(-)
] api?
( dev-python/aiohttp[python_targets_python3_12
(-)
] dev-python/requests[python_targets_python3_12
(-)
] dev-python/tenacity[python_targets_python3_12
(-)
] dev-python/tiktoken[python_targets_python3_12
(-)
] dev-python/tqdm[python_targets_python3_12
(-)
] )
ifeval?
( dev-python/langdetect[python_targets_python3_12
(-)
] dev-python/immutabledict[python_targets_python3_12
(-)
] >=dev-python/nltk-3.9.1[python_targets_python3_12
(-)
] )
math?
( =dev-python/antlr4-python3-runtime-4.11*[python_targets_python3_12
(-)
] >=dev-python/sympy-1.12[python_targets_python3_12
(-)
] ~dev-python/math-verify-0.9.0[python_targets_python3_12
(-)
] )
sentencepiece?
( >=sci-ml/sentencepiece-0.1.98[python_targets_python3_12
(-)
] )
statsmodels?
( dev-python/statsmodels[python_targets_python3_12
(-)
] )
)
python_single_target_python3_13?
( dev-python/dill[python_targets_python3_13
(-)
] dev-python/jinja2[python_targets_python3_13
(-)
] dev-python/more-itertools[python_targets_python3_13
(-)
] dev-python/numpy[python_targets_python3_13
(-)
] dev-python/pytablewriter[python_targets_python3_13
(-)
] dev-python/rouge-score[python_targets_python3_13
(-)
] dev-python/sacrebleu[python_targets_python3_13
(-)
] dev-python/scikit-learn[python_targets_python3_13
(-)
] dev-python/sqlitedict[python_targets_python3_13
(-)
] dev-python/tqdm[python_targets_python3_13
(-)
] dev-python/typing-extensions[python_targets_python3_13
(-)
] dev-python/word2number[python_targets_python3_13
(-)
] api?
( dev-python/aiohttp[python_targets_python3_13
(-)
] dev-python/requests[python_targets_python3_13
(-)
] dev-python/tenacity[python_targets_python3_13
(-)
] dev-python/tiktoken[python_targets_python3_13
(-)
] dev-python/tqdm[python_targets_python3_13
(-)
] )
ifeval?
( dev-python/langdetect[python_targets_python3_13
(-)
] dev-python/immutabledict[python_targets_python3_13
(-)
] >=dev-python/nltk-3.9.1[python_targets_python3_13
(-)
] )
math?
( =dev-python/antlr4-python3-runtime-4.11*[python_targets_python3_13
(-)
] >=dev-python/sympy-1.12[python_targets_python3_13
(-)
] ~dev-python/math-verify-0.9.0[python_targets_python3_13
(-)
] )
sentencepiece?
( >=sci-ml/sentencepiece-0.1.98[python_targets_python3_13
(-)
] )
statsmodels?
( dev-python/statsmodels[python_targets_python3_13
(-)
] )
)
python_single_target_python3_14?
( dev-python/dill[python_targets_python3_14
(-)
] dev-python/jinja2[python_targets_python3_14
(-)
] dev-python/more-itertools[python_targets_python3_14
(-)
] dev-python/numpy[python_targets_python3_14
(-)
] dev-python/pytablewriter[python_targets_python3_14
(-)
] dev-python/rouge-score[python_targets_python3_14
(-)
] dev-python/sacrebleu[python_targets_python3_14
(-)
] dev-python/scikit-learn[python_targets_python3_14
(-)
] dev-python/sqlitedict[python_targets_python3_14
(-)
] dev-python/tqdm[python_targets_python3_14
(-)
] dev-python/typing-extensions[python_targets_python3_14
(-)
] dev-python/word2number[python_targets_python3_14
(-)
] api?
( dev-python/aiohttp[python_targets_python3_14
(-)
] dev-python/requests[python_targets_python3_14
(-)
] dev-python/tenacity[python_targets_python3_14
(-)
] dev-python/tiktoken[python_targets_python3_14
(-)
] dev-python/tqdm[python_targets_python3_14
(-)
] )
ifeval?
( dev-python/langdetect[python_targets_python3_14
(-)
] dev-python/immutabledict[python_targets_python3_14
(-)
] >=dev-python/nltk-3.9.1[python_targets_python3_14
(-)
] )
math?
( =dev-python/antlr4-python3-runtime-4.11*[python_targets_python3_14
(-)
] >=dev-python/sympy-1.12[python_targets_python3_14
(-)
] ~dev-python/math-verify-0.9.0[python_targets_python3_14
(-)
] )
sentencepiece?
( >=sci-ml/sentencepiece-0.1.98[python_targets_python3_14
(-)
] )
statsmodels?
( dev-python/statsmodels[python_targets_python3_14
(-)
] )
)
python_single_target_python3_12?
( dev-lang/python:3.12 )
python_single_target_python3_13?
( dev-lang/python:3.13 )
python_single_target_python3_14?
( dev-lang/python:3.14 )
lm-eval-0.4.11
>=sci-ml/datasets-2.16.0[python_single_target_python3_12
(-)
?
,python_single_target_python3_13
(-)
?
,python_single_target_python3_14
(-)
?
]
>=sci-ml/evaluate-0.4.0[python_single_target_python3_12
(-)
?
,python_single_target_python3_13
(-)
?
,python_single_target_python3_14
(-)
?
]
vllm?
( >=dev-python/vllm-0.4.2[python_single_target_python3_12
(-)
?
,python_single_target_python3_13
(-)
?
,python_single_target_python3_14
(-)
?
] )
python_single_target_python3_12?
( dev-python/dill[python_targets_python3_12
(-)
] dev-python/jinja2[python_targets_python3_12
(-)
] dev-python/jsonlines[python_targets_python3_12
(-)
] dev-python/more-itertools[python_targets_python3_12
(-)
] dev-python/numpy[python_targets_python3_12
(-)
] dev-python/pytablewriter[python_targets_python3_12
(-)
] dev-python/rouge-score[python_targets_python3_12
(-)
] dev-python/sacrebleu[python_targets_python3_12
(-)
] dev-python/sqlitedict[python_targets_python3_12
(-)
] dev-python/typing-extensions[python_targets_python3_12
(-)
] dev-python/word2number[python_targets_python3_12
(-)
] dev-python/zstandard[python_targets_python3_12
(-)
] dev-python/scikit-learn[python_targets_python3_12
(-)
] api?
( dev-python/aiohttp[python_targets_python3_12
(-)
] dev-python/requests[python_targets_python3_12
(-)
] dev-python/tenacity[python_targets_python3_12
(-)
] dev-python/tiktoken[python_targets_python3_12
(-)
] dev-python/tqdm[python_targets_python3_12
(-)
] )
ifeval?
( dev-python/langdetect[python_targets_python3_12
(-)
] dev-python/immutabledict[python_targets_python3_12
(-)
] >=dev-python/nltk-3.9.1[python_targets_python3_12
(-)
] )
math?
( =dev-python/antlr4-python3-runtime-4.11*[python_targets_python3_12
(-)
] >=dev-python/sympy-1.12[python_targets_python3_12
(-)
] ~dev-python/math-verify-0.9.0[python_targets_python3_12
(-)
] )
sentencepiece?
( >=sci-ml/sentencepiece-0.1.98[python_targets_python3_12
(-)
] )
statsmodels?
( dev-python/statsmodels[python_targets_python3_12
(-)
] )
)
python_single_target_python3_13?
( dev-python/dill[python_targets_python3_13
(-)
] dev-python/jinja2[python_targets_python3_13
(-)
] dev-python/jsonlines[python_targets_python3_13
(-)
] dev-python/more-itertools[python_targets_python3_13
(-)
] dev-python/numpy[python_targets_python3_13
(-)
] dev-python/pytablewriter[python_targets_python3_13
(-)
] dev-python/rouge-score[python_targets_python3_13
(-)
] dev-python/sacrebleu[python_targets_python3_13
(-)
] dev-python/sqlitedict[python_targets_python3_13
(-)
] dev-python/typing-extensions[python_targets_python3_13
(-)
] dev-python/word2number[python_targets_python3_13
(-)
] dev-python/zstandard[python_targets_python3_13
(-)
] dev-python/scikit-learn[python_targets_python3_13
(-)
] api?
( dev-python/aiohttp[python_targets_python3_13
(-)
] dev-python/requests[python_targets_python3_13
(-)
] dev-python/tenacity[python_targets_python3_13
(-)
] dev-python/tiktoken[python_targets_python3_13
(-)
] dev-python/tqdm[python_targets_python3_13
(-)
] )
ifeval?
( dev-python/langdetect[python_targets_python3_13
(-)
] dev-python/immutabledict[python_targets_python3_13
(-)
] >=dev-python/nltk-3.9.1[python_targets_python3_13
(-)
] )
math?
( =dev-python/antlr4-python3-runtime-4.11*[python_targets_python3_13
(-)
] >=dev-python/sympy-1.12[python_targets_python3_13
(-)
] ~dev-python/math-verify-0.9.0[python_targets_python3_13
(-)
] )
sentencepiece?
( >=sci-ml/sentencepiece-0.1.98[python_targets_python3_13
(-)
] )
statsmodels?
( dev-python/statsmodels[python_targets_python3_13
(-)
] )
)
python_single_target_python3_14?
( dev-python/dill[python_targets_python3_14
(-)
] dev-python/jinja2[python_targets_python3_14
(-)
] dev-python/jsonlines[python_targets_python3_14
(-)
] dev-python/more-itertools[python_targets_python3_14
(-)
] dev-python/numpy[python_targets_python3_14
(-)
] dev-python/pytablewriter[python_targets_python3_14
(-)
] dev-python/rouge-score[python_targets_python3_14
(-)
] dev-python/sacrebleu[python_targets_python3_14
(-)
] dev-python/sqlitedict[python_targets_python3_14
(-)
] dev-python/typing-extensions[python_targets_python3_14
(-)
] dev-python/word2number[python_targets_python3_14
(-)
] dev-python/zstandard[python_targets_python3_14
(-)
] dev-python/scikit-learn[python_targets_python3_14
(-)
] api?
( dev-python/aiohttp[python_targets_python3_14
(-)
] dev-python/requests[python_targets_python3_14
(-)
] dev-python/tenacity[python_targets_python3_14
(-)
] dev-python/tiktoken[python_targets_python3_14
(-)
] dev-python/tqdm[python_targets_python3_14
(-)
] )
ifeval?
( dev-python/langdetect[python_targets_python3_14
(-)
] dev-python/immutabledict[python_targets_python3_14
(-)
] >=dev-python/nltk-3.9.1[python_targets_python3_14
(-)
] )
math?
( =dev-python/antlr4-python3-runtime-4.11*[python_targets_python3_14
(-)
] >=dev-python/sympy-1.12[python_targets_python3_14
(-)
] ~dev-python/math-verify-0.9.0[python_targets_python3_14
(-)
] )
sentencepiece?
( >=sci-ml/sentencepiece-0.1.98[python_targets_python3_14
(-)
] )
statsmodels?
( dev-python/statsmodels[python_targets_python3_14
(-)
] )
)
python_single_target_python3_12?
( dev-lang/python:3.12 )
python_single_target_python3_13?
( dev-lang/python:3.13 )
python_single_target_python3_14?
( dev-lang/python:3.14 )