Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.
Why do you think that https://github.com/AlpinDale/sparsegpt-for-LLaMA is a good alternative to LLaMA-8bit-LoRA
LLaMA-8bit-LoRA
Repository for Chat LLaMA - training a LoRA for the LLaMA (1 or 2) models on HuggingFace with 8-bit or 4-bit quantization. Research only.
Why do you think that https://github.com/AlpinDale/sparsegpt-for-LLaMA is a good alternative to LLaMA-8bit-LoRA