app.py

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

title = """# 🙋🏻‍♂️Welcome to🌟Tonic's🔮🪄DeepSeek📉Math
You can build with this endpoint using 🔮🪄DeepSeek📉Math. The demo is still a work in progress and we're looking forward to build downstream tasks that showcase outstanding mathematical reasoning. Have any ideas ? join us below !
You can also use 🔮🪄DeepSeek📉Math by cloning this space. 🧬🔬🔍 Simply click here: <a style="display:inline-block" href="https://huggingface.co/spaces/Tonic/Math?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: [TeamTonic](https://huggingface.co/TeamTonic) & [MultiTransformer](https://huggingface.co/MultiTransformer) Math with [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 🤗
"""

model_name = "deepseek-ai/deepseek-math-7b-instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.bfloat16, device_map="auto")
model.generation_config = GenerationConfig.from_pretrained(model_name)
model.generation_config.pad_token_id = model.generation_config.eos_token_id

@spaces.GPU
def solve_math_problem(question, max_tokens):
    prompt = f"User: {question}\nPlease reason step by step, and put your final answer within \\boxed{{}}.\nAssistant:"
    input_ids = tokenizer(prompt, return_tensors="pt").input_ids.to(model.device)
    outputs = model.generate(input_ids, max_length=max_tokens + input_ids.shape[1], pad_token_id=model.generation_config.pad_token_id)
    result = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return result

def main():
    with gr.Blocks() as demo:
        gr.Markdown(title)
        with gr.Row():
            question = gr.Textbox(lines=5, label="Enter your math problem")
            max_tokens = gr.Slider(minimum=150, maximum=1200, default=250, label="Max Tokens")
        submit_button = gr.Button("Solve")
        output = gr.Textbox(label="🔮🪄DeepSeek📉Math")

        submit_button.click(fn=solve_math_problem, inputs=[question, max_tokens], outputs=output)

    demo.launch()

if __name__ == "__main__":
    main()