model.py

# from transformers import AutoTokenizer, AutoModelForCausalLM

# def load_model(model_name="meta-llama/Llama-3.1-8B"):
#     """
#     Load the Hugging Face Llama model and tokenizer.
#     """
#     tokenizer = AutoTokenizer.from_pretrained(model_name)
#     model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", torch_dtype="auto")
#     return tokenizer, model

# # Initialize model and tokenizer
# tokenizer, model = load_model()

from transformers import pipeline

# Replace with your Hugging Face API token
api_token = "your_huggingface_api_token"

# Load the model using the API
generator = pipeline(
    "text-generation",
    model="meta-llama/Llama-3.1-8B",
    use_auth_token=api_token
)