Is there a way to get PEFT to work with inference endpoints?
Ideally, we should be able to support multiple PEFT models with a common inference endpoint for the base model.
Is there a way to get PEFT to work with inference endpoints?
Ideally, we should be able to support multiple PEFT models with a common inference endpoint for the base model.
any updates here?
You could configure a custom handler that allows you to specify code to load the model and its adapters Create custom Inference Handler