How to use homerquan/mn-context-engine-lora-v1 with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("google/gemma-4-E4B") model = PeftModel.from_pretrained(base_model, "homerquan/mn-context-engine-lora-v1")
