Open RonanKMcGovern opened 3 days ago
I agree that the information is a bit sparse. Could you expand on what exactly you would like to see? What is the workaround for that you mentioned, do you mean quantization methods that don't support merging? What type of performance do you have in mind?
System Info
NA
Who can help?
@BenjaminBossan could you add a note to the docs to explain the default behaviour, and also any work arounds (e.g. loading a base model and dequantizing and loading the adapter and then merging) for best performance? Thanks
https://huggingface.co/docs/peft/main/en/package_reference/lora#peft.LoraModel.merge_and_unload
Information
Tasks
examples
folderReproduction
NA
Expected behavior
NA