INT4 LoRA great-tuning vs QLoRA: A user inquired about the variations concerning INT4 LoRA great-tuning and QLoRA in terms of accuracy and speed. One more member explained that QLoRA with HQQ requires frozen quantized weights, will not use tinnygemm, and makes use of dequantizing together with torch.matmulTweet from Robert Graham (@ErrataRob): nVid