Official implementation of Half-Quadratic Quantization (HQQ)
Accessible large language models via k-bit quantization for PyTorch.
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
中文LLaMA&Alpaca大语言模型+本地CPU/GPU训练部署 (Chinese LLaMA & Alpaca LLMs)
Machine Learning Engineering Open Book