model_loader.py

from transformers import AutoModelForCausalLM, AutoTokenizer, pipeline

def load_model(model_name="your-username/sentinel"):
    """
    Load Sentinel model and tokenizer.
    """
    print(f"Loading {model_name}...")
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(
        model_name,
        device_map="auto",   # Uses GPU if available
        trust_remote_code=True
    )
    generator = pipeline("text-generation", model=model, tokenizer=tokenizer)
    return generator