How to use ping98k/open-llama-7b-openthought-mid-lora with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("./open_llama_7b_v2_4bit") model = PeftModel.from_pretrained(base_model, "ping98k/open-llama-7b-openthought-mid-lora")
