How to use dball/zephyr-tiny-sft-qlora-quantized-2 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("TinyLlama/TinyLlama-1.1B-Chat-v1.0") model = PeftModel.from_pretrained(base_model, "dball/zephyr-tiny-sft-qlora-quantized-2")