lm-eval

PyPI page
Home page
Author: EleutherAI
License: MIT
Summary: A framework for evaluating language models
Latest version: 0.4.13
Required dependencies: datasets | dill | evaluate | jinja2 | more-itertools | numpy | pytablewriter | rouge-score | sacrebleu | scikit-learn | sqlitedict | tqdm | typing-extensions | word2number
Optional dependencies: accelerate | aiohttp | antlr4-python3-runtime | auto-gptq | emoji | fugashi | fuzzywuzzy | gptqmodel | ibm-watsonx-ai | immutabledict | jieba | jsonlines | kstar-planner | langdetect | lark | librosa | litellm | lm-eval | math-verify | nagisa | neologdn | nltk | numpy | onnxruntime | onnxruntime-genai | optimum | optimum-habana | optimum-intel | pandas | pddl | peft | pillow | pycountry | pymorphy2 | pytest | pytest-cov | pytest-xdist | python-dotenv | requests | rouge | rouge-score | scipy | sentencepiece | soundfile | sparsify | statsmodels | sympy | tarski | tenacity | tiktoken | torch | tqdm | trackio | transformers | unitxt | vllm | wandb | wonderwords | zeno-client | zstandard

Downloads last day: 47,223
Downloads last week: 307,309
Downloads last month: 1,032,386
7-day smoothing