piwheels

lm-eval

A framework for evaluating language models

Installation

In a virtualenv (see these instructions if you need to create one):

pip3 install lm-eval

Dependencies

• rouge-score
• typing-extensions
• datasets
• tqdm
• scikit-learn
• evaluate
• numpy
• dill
• pytablewriter
• jinja2
• more-itertools
• sqlitedict
• word2number
• sacrebleu

Releases

Version	Released	Bookworm Python 3.11	Trixie Python 3.13	Files
0.5.0.dev1 pre-release	2026-05-11
lm_eval-0.5.0.dev1-py3-none-any.whl (8 MB)
0.4.13	2026-08-31
lm_eval-0.4.13-py3-none-any.whl (9 MB)
0.4.13.dev0 pre-release	2026-08-31
lm_eval-0.4.13.dev0-py3-none-any.whl (9 MB)
0.4.12	2026-05-11
lm_eval-0.4.12-py3-none-any.whl (8 MB)
0.4.11	2026-02-13
lm_eval-0.4.11-py3-none-any.whl (8 MB)
0.4.10	2026-01-27
lm_eval-0.4.10-py3-none-any.whl (8 MB)
0.4.9.2	2025-11-26
lm_eval-0.4.9.2-py3-none-any.whl (8 MB)
0.4.9.1	2025-08-04
lm_eval-0.4.9.1-py3-none-any.whl (7 MB)
0.4.9	2025-06-19
lm_eval-0.4.9-py3-none-any.whl (7 MB)
0.4.8	2025-03-05
lm_eval-0.4.8-py3-none-any.whl (4 MB)
0.4.7	2024-12-17
lm_eval-0.4.7-py3-none-any.whl (2 MB)
0.4.5	2024-10-08
lm_eval-0.4.5-py3-none-any.whl (2 MB)
0.4.4	2024-09-05
lm_eval-0.4.4-py3-none-any.whl (2 MB)
0.4.3	2024-07-01
lm_eval-0.4.3-py3-none-any.whl (2 MB)
0.4.2	2024-03-18
lm_eval-0.4.2-py3-none-any.whl (1 MB)
0.4.1	2024-01-31
lm_eval-0.4.1-py3-none-any.whl (1 MB)
0.4.0	2023-12-22
lm_eval-0.4.0-py3-none-any.whl (972 KB)
0.3.0	2022-12-08
lm_eval-0.3.0-py3-none-any.whl (174 KB)
0.2.0	2022-03-07
lm_eval-0.2.0-py3-none-any.whl (140 KB)
0.0.1	2021-09-02
lm_eval-0.0.1-py3-none-any.whl (100 KB)

Issues with this package?

• Search issues for this package
• Package or version missing? Open a new issue
• Something else? Open a new issue