import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

model_path = 'Mxode/NanoLM-1B-Instruct-v2'

model = AutoModelForCausalLM.from_pretrained(model_path).to('cuda:0', torch.bfloat16)
tokenizer = AutoTokenizer.from_pretrained(model_path)


def get_response(prompt: str, **kwargs):
    generation_args = dict(
        max_new_tokens = kwargs.pop("max_new_tokens", 512),
        do_sample = kwargs.pop("do_sample", True),
        temperature = kwargs.pop("temperature", 0.7),
        top_p = kwargs.pop("top_p", 0.8),
        top_k = kwargs.pop("top_k", 40),
        **kwargs
    )

    messages = [
        {"role": "system", "content": "You are a helpful assistant."},
        {"role": "user", "content": prompt}
    ]
    text = tokenizer.apply_chat_template(
        messages,
        tokenize=False,
        add_generation_prompt=True
    )
    model_inputs = tokenizer([text], return_tensors="pt").to(model.device)

    generated_ids = model.generate(model_inputs.input_ids, **generation_args)
    generated_ids = [
        output_ids[len(input_ids):] for input_ids, output_ids in zip(model_inputs.input_ids, generated_ids)
    ]

    response = tokenizer.batch_decode(generated_ids, skip_special_tokens=True)[0]
    return response


prompt = "Calculate (99 - 1) * (3 + 4)"
print(get_response(prompt, do_sample=False))

"""
To calculate \((99 - 1) * (3 + 4)\), follow the order of operations, also known as PEMDAS (Parentheses, Exponents, Multiplication and Division, and Addition and Subtraction).

First, solve the expressions inside the parentheses:

1. \(99 - 1 = 98\)
2. \(3 + 4 = 7\)

Now, multiply the results:

\(98 * 7 = 686\)

So, \((99 - 1) * (3 + 4) = 686\).
"""