How to use s-g-labs/linlu-lora-v0.2-qwen3.6-27b with PEFT:
from peft import PeftModel from transformers import AutoModelForCausalLM base_model = AutoModelForCausalLM.from_pretrained("./Qwen3.6-27B") model = PeftModel.from_pretrained(base_model, "s-g-labs/linlu-lora-v0.2-qwen3.6-27b")
s-g-labs commited on 