hqq-quantization
from Orchestra-Research/AI-research-SKILLs
Half-Quadratic Quantization for LLMs without calibration data. Use when quantizing models to 4/3/2-bit precision without needing calibration datasets, for fast quantization workflows, or when deployin
v1.0.0MIT
446
Lines
1,218
Words
18
Code Blocks
Languages
bashpython
10-optimization/hqq/SKILL.md