PyPI page
Home page
Author:
None
Summary:
Rigorous LLM evaluation: bootstrap CIs, significance testing, and automated statistical auditing
Latest version:
0.1.0
Required dependencies:
jinja2
|
numpy
|
rich
|
scikit-learn
|
scipy
|
typer
Optional dependencies:
anthropic
|
datasets
|
evalkit-research
|
fastapi
|
httpx
|
jupyter
|
krippendorff
|
mypy
|
nltk
|
openai
|
pandas
|
pydantic
|
pytest
|
pytest-cov
|
rouge-score
|
ruff
|
sentence-transformers
|
uvicorn
Downloads last day:
2
Downloads last week:
12
Downloads last month:
50