make_prompt.py

# Usecase

def make_prompt(input_text: str, system_prompt="", max_length=512) -> str:
    """
    Generates text using a large language model, given a prompt and a device.
    Args:
        input_text (str): The input text for prompting.
        system_prompt (str): The system prompt (not used in the function).
        max_length (int): The maximum length of the generated text.

    Returns:
        A string containing the generated text.
    """
    prompt = f"<s>[INST]{input_text}[/INST]"

    tokenized_input = tokenizer(prompt, return_tensors="pt", add_special_tokens=False)

    model_inputs = tokenized_input.to(device)

    output = model.generate(
        **model_inputs,
        max_length=max_length,
        use_cache=True,
        early_stopping=True,
        bos_token_id=model.config.bos_token_id,
        eos_token_id=model.config.eos_token_id,
        pad_token_id=model.config.eos_token_id,
        temperature=0.1,
        do_sample=True
    )

    # Randomly select one of the generated outputs
    response = random.choice(tokenizer.batch_decode(output))

    # Wrap the response text to a width of 90 characters
    wrapped_response = text_wrapper(response)
    print(wrapped_response)

# The code assumes that 'tokenizer' and 'model' are defined 
# and available before calling this function.