home/categories/computational-chemistry/orchestra-research-ai-research-skills-10-optimization-hqq-skill-md
computational-chemistryresearch

hqq-quantization

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.

Orchestra-Research
maintainer
Orchestra-Research
Обновлено 11/25/2025
Звёзды
6563
Форки
515
quick start

Installation and usage

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.

Установка
$ install --globalskills.sh
Использование

После установки вы можете использовать этот skill, выполнив следующую команду в терминале:

skills use hqq-quantization