QLoRA: Efficient Finetuning of Quantized LLMs
Home Page:https://arxiv.org/abs/2305.14314
Geek Repo:Geek Repo
Github PK Tool:Github PK Tool
sidracha opened this issue 10 months ago · comments
My fine tuning was interrupted on a 4-bit quantized model. How can I merge the weights of a checkpoint with the base model to use for inference? I couldn't find a way to do it anywhere else