hqq-quantization：无需校准数据的快速量化方案

OA0

OA0 是一个探索 AI 的社区

现在注册

已注册用户请登录

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 deploying with vLLM or HuggingFace Transformers.

技能包地址：https://skillsmp.com/skills/davila7-claude-code-templates-cli-tool-components-skills-ai-research-optimization-hqq-skill-md

20 次点击 ∙ 0 人收藏

登录后收藏

0 条回复