PyPI page
Home page
Author:
Sahil Kadadekar
Summary:
Quantize an LLM and check it still refuses what it should — a GPU-aware quantization CLI that measures the safety drift of the quantization it just performed.
Latest version:
0.26.0
Required dependencies:
accelerate
|
datasets
|
httpx
|
huggingface-hub
|
llmcompressor
|
psutil
|
torch
|
transformers
Optional dependencies:
gguf
|
gptqmodel
|
httpx
|
inspect-ai
|
pytest
|
ruff
|
scipy
Downloads last day:
92
Downloads last week:
1,249
Downloads last month:
2,468
7-day smoothing