The Fine-Tuning Index / PEFT & LoRA / #136
WangRongsheng/Aurora
by WangRongsheng · PEFT & LoRA · updated 2y ago
The official codes for "Aurora: Activating chinese chat capability for Mixtral-8x7B sparse Mixture-of-Experts through Instruction-Tuning"
27
momentum
260
stars
19
forks
#136
rank
chinesefine-tuninggptinstruction-tuninglanguage-modellarge-language-modelsllmloramixtralmixtral-8x7bmixtral-8x7b-instructqlora
View on GitHub →