How to use ZeroUniqueness/qlora-llama-2-13b-code with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("/workspace/webui/models/TheBloke_Llama-2-13B-fp16") model = PeftModel.from_pretrained(base_model, "ZeroUniqueness/qlora-llama-2-13b-code")