load_example.py

"""Minimal load example for modrill/MN9-SHORT-515K."""
from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

BASE = "Qwen/Qwen3-4B-Base"
ADAPTER = "modrill/MN9-SHORT-515K"


def load(device_map="auto"):
    tok = AutoTokenizer.from_pretrained(BASE, trust_remote_code=True)
    model = AutoModelForCausalLM.from_pretrained(
        BASE, torch_dtype="auto", device_map=device_map, trust_remote_code=True
    )
    model = PeftModel.from_pretrained(model, ADAPTER)
    model.eval()
    return tok, model


if __name__ == "__main__":
    tok, model = load()
    print("loaded", type(model).__name__, "params", sum(p.numel() for p in model.parameters()))