PyPI page
Home page
Author:
Federico Sciuca
License:
MIT
Summary:
Probe-then-quantize for LLMs: measure a model's fragility curve, plan bit/tier placement by the tiered decode law, and emit ready-to-run llama.cpp recipes.
Latest version:
1.37.0
Required dependencies:
gguf
|
requests
Downloads last day:
31
Downloads last week:
140
Downloads last month:
490
7-day smoothing