PEFT How to use chengyineng/bloom_cpu_prompt_tuning with PEFT:
from peft import PeftModel
from transformers import AutoModelForCausalLM
base_model = AutoModelForCausalLM.from_pretrained("bigscience/bloomz-560m")
model = PeftModel.from_pretrained(base_model, "chengyineng/bloom_cpu_prompt_tuning")