PyPI page
Home page
Author:
None
License:
MIT
Summary:
Train and serve pairwise LLM judges (A/B/tie) with budget-aware multi-turn packing and position-bias correction
Latest version:
0.1.1
Required dependencies:
numpy
|
pandas
|
pyyaml
Optional dependencies:
accelerate
|
datasets
|
peft
|
pytest
|
scikit-learn
|
torch
|
transformers
Downloads last day:
0
Downloads last week:
6
Downloads last month:
65