The Fine-Tuning Index / RLHF & Preference / #28

ModelCloud/GPTQModel

by ModelCloud · RLHF & Preference · updated today

LLM model quantization (compression) toolkit with HW acceleration support for Nvidia, AMD, Intel GPU and Intel/AMD/Apple CPU via HF, vLLM, and SGLang.

67
momentum
1,177
stars
187
forks
#28
rank
gptqoptimumpeftquantizationsglangtransformersvllm
View on GitHub →