app.py

import spaces
import gradio as gr
import torch
import transformers
from transformers import AutoModelForCausalLM, AutoTokenizer
import os

title = """# Welcome to 🌟Tonic's✨StarCoder
✨StarCoder StarCoder2-15B model is a 15B parameter model trained on 600+ programming languages from The Stack v2, with opt-out requests excluded. The model uses Grouped Query Attention, a context window of 16,384 tokens with a sliding window attention of 4,096 tokens, and was trained using the Fill-in-the-Middle objective on 4+ trillion tokens. The model was trained with NVIDIA NeMo™ Framework using the NVIDIA Eos Supercomputer built with NVIDIA DGX H100 systems. You can build with this endpoint using✨StarCoder available here : [bigcode/starcoder2-15b](https://huggingface.co/bigcode/starcoder2-15b). You can also use ✨StarCoder by cloning this space. Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/starcoder2?duplicate=true"><img src="https://img.shields.io/badge/-Duplicate%20Space-blue?labelColor=white&style=flat&logo=data:image/png;base64,iVBORw0KGgoAAAANSUhEUgAAABAAAAAQCAYAAAAf8/9hAAAAAXNSR0IArs4c6QAAAP5JREFUOE+lk7FqAkEURY+ltunEgFXS2sZGIbXfEPdLlnxJyDdYB62sbbUKpLbVNhyYFzbrrA74YJlh9r079973psed0cvUD4A+4HoCjsA85X0Dfn/RBLBgBDxnQPfAEJgBY+A9gALA4tcbamSzS4xq4FOQAJgCDwV2CPKV8tZAJcAjMMkUe1vX+U+SMhfAJEHasQIWmXNN3abzDwHUrgcRGmYcgKe0bxrblHEB4E/pndMazNpSZGcsZdBlYJcEL9Afo75molJyM2FxmPgmgPqlWNLGfwZGG6UiyEvLzHYDmoPkDDiNm9JR9uboiONcBXrpY1qmgs21x1QwyZcpvxt9NS09PlsPAAAAAElFTkSuQmCC&logoWidth=14" alt="Duplicate Space"></a></h3> 
Join us : 🌟TeamTonic🌟 is always making cool demos! Join our active builder's 🛠️community 👻 [![Join us on Discord](https://img.shields.io/discord/1109943800132010065?label=Discord&logo=discord&style=flat-square)](https://discord.gg/GWpVpekp) On 🤗Huggingface:[MultiTransformer](https://huggingface.co/MultiTransformer) Math 🔍 [introspector](https://huggingface.co/introspector) On 🌐Github: [Tonic-AI](https://github.com/tonic-ai) & contribute to🌟 [SciTonic](https://github.com/Tonic-AI/scitonic)🤗Big thanks to Yuvi Sharma and all the folks at huggingface for the community grant 🤗
"""

default_system_prompt = """SYSTEM: You are an AI that code. Answer with code."""

model_path = "bigcode/starcoder2-15b"


hf_token = os.getenv("HF_TOKEN")
if not hf_token:
    raise ValueError("Hugging Face token not found. Please set the HF_TOKEN environment variable.")

model = AutoModelForCausalLM.from_pretrained(
    model_path,
    torch_dtype=torch.bfloat16,
    device_map="auto",
#   trust_remote_code=True,
    token=hf_token,
)

tokenizer = AutoTokenizer.from_pretrained(model_path, trust_remote_code=True)

# import gradio as gr
# from transformers import AutoTokenizer, AutoModelForCausalLM, BitsAndBytesConfig

# checkpoint = "bigcode/starcoder2-15b"
# quantization_config = BitsAndBytesConfig(load_in_8bit=True)
# tokenizer = AutoTokenizer.from_pretrained(checkpoint)
# model = AutoModelForCausalLM.from_pretrained(checkpoint, quantization_config=quantization_config).to("cuda")
@spaces.GPU
def generate_text(prompt, temperature, max_length):
    inputs = tokenizer.encode(prompt, return_tensors="pt").to("cuda")
    outputs = model.generate(inputs, max_length=max_length, top_p=0.9, temperature=temperature)
    return tokenizer.decode(outputs[0])

def gradio_app():
    with gr.Blocks() as demo:
        gr.Markdown(title)
        output = gr.Code(label="Generated Code", lines=40)
        with gr.Row():
            generate_btn = gr.Button("Generate")
        with gr.Row():
            temperature = gr.Slider(minimum=0.1, maximum=1.0, step=0.1, value=0.5, label="Temperature")
            max_length = gr.Slider(minimum=100, maximum=1024, step=10, value=100, label="Generate Length")
        with gr.Row():
            prompt = gr.Textbox(label="Enter your code prompt", placeholder="def print_hello_world():")

        generate_btn.click(
            fn=generate_text,
            inputs=[prompt, temperature, max_length],
            outputs=output
        )

    demo.launch()