from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base = "Qwen/Qwen2.5-7B-Instruct"
adapter = "<your-repo-id>"  # 例: katsukiono/Qwen2.5-7B-Instruct-pubmed-qlora-layer11-only-2048

tok = AutoTokenizer.from_pretrained(base, use_fast=True)
model = AutoModelForCausalLM.from_pretrained(
    base, device_map="auto", torch_dtype="auto", trust_remote_code=True
)
model = PeftModel.from_pretrained(model, adapter)
model.eval()