PyPI page
Summary:
Lightweight evaluation framework that unifies inference through a single VLLM sampler and runs IF-EVAL, IFBench, WritingBench, HealthBench, Arena-Hard, and AlpacaEval end-to-end.
Latest version:
0.1.0
Required dependencies:
emoji
|
immutabledict
|
langdetect
|
matplotlib
|
nltk
|
numpy
|
openai
|
pandas
|
setuptools
|
syllapy
|
tqdm
Downloads last day:
6
Downloads last week:
13
Downloads last month:
28
7-day smoothing