PyPI page
Summary:
EvalFloor: is your LLM eval improvement real? Trying k prompt variants and keeping the best scores points on noise alone -- this computes how many, so you can tell a real gain from a lucky sample.
Latest version:
0.3.0
Optional dependencies:
datasets
|
torch
|
transformers
Downloads last day:
1
Downloads last week:
19
Downloads last month:
738
7-day smoothing