afrideva / smol_llama-101M-GQA-python-GGUF

Are you ready to witness the incredible possibilities of code generation? 🚀. Brace yourself for an exceptional journey into the world of artificial intelligence and programming. Observe a script that will change the way you create and finalize code.

This script provides entry to a planet where machines can write code with remarkable precision and imagination.

"""
simple script for testing model(s) designed to generate/complete code

See details/args with the below. 
    python textgen_inference_code.py --help
"""
import logging
import random
import time
from pathlib import Path

import fire
import torch
from transformers import AutoModelForCausalLM, AutoTokenizer

logging.basicConfig(format="%(levelname)s - %(message)s", level=logging.INFO)


class Timer:
    """
    Basic timer utility.
    """

    def __enter__(self):

        self.start_time = time.perf_counter()
        return self

    def __exit__(self, exc_type, exc_value, traceback):

        self.end_time = time.perf_counter()
        self.elapsed_time = self.end_time - self.start_time
        logging.info(f"Elapsed time: {self.elapsed_time:.4f} seconds")


def load_model(model_name, use_fast=False):
    """ util for loading model and tokenizer"""
    logging.info(f"Loading model: {model_name}")
    tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=use_fast)
    model = AutoModelForCausalLM.from_pretrained(
        model_name, torch_dtype="auto", device_map="auto"
    )
    model = torch.compile(model)
    return tokenizer, model


def run_inference(prompt, model, tokenizer, max_new_tokens: int = 256):
    """
    run_inference

    Args:
        prompt (TYPE): Description
        model (TYPE): Description
        tokenizer (TYPE): Description
        max_new_tokens (int, optional): Description

    Returns:
        TYPE: Description
    """
    logging.info(f"Running inference with max_new_tokens={max_new_tokens} ...")
    with Timer() as timer:
        inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
        outputs = model.generate(
            **inputs,
            max_new_tokens=max_new_tokens,
            min_new_tokens=8,
            renormalize_logits=True,
            no_repeat_ngram_size=8,
            repetition_penalty=1.04,
            num_beams=4,
            early_stopping=True,
        )
    text = tokenizer.batch_decode(outputs, skip_special_tokens=True)[0]
    logging.info(f"Output text:\n\n{text}")
    return text


def main(
    model_name="BEE-spoke-data/smol_llama-101M-GQA-python",
    prompt:str=None,
    use_fast=False,
    n_tokens: int = 256,
):
    """Summary

    Args:
        model_name (str, optional): Description
        prompt (None, optional): specify the prompt directly (default: random choice from list)
        n_tokens (int, optional): max new tokens to generate
    """
    logging.info(f"Inference with:\t{model_name}, max_new_tokens:{n_tokens}")

    if prompt is None:
        prompt_list = [
            '''
            def print_primes(n: int):
               """
               Print all primes between 1 and n
               """''',
            "def quantum_analysis(",
            "def sanitize_filenames(target_dir:str, recursive:False, extension",
        ]
        prompt = random.SystemRandom().choice(prompt_list)

    logging.info(f"Using prompt:\t{prompt}")

    tokenizer, model = load_model(model_name, use_fast=use_fast)

    run_inference(prompt, model, tokenizer, n_tokens)


if __name__ == "__main__":
    fire.Fire(main)

Wowoweewa!! It can create some file cleaning utilities.