app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

model_name = "HuggingFaceTB/finemath-ablation-finemath-infimath-4plus"
# device = "cuda" if torch.cuda.is_available() else "cpu"
device = "cpu"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name).to(device)


def generate_text(prompt):
    inputs = tokenizer.encode(prompt, return_tensors="pt").to(device)
    outputs = model.generate(inputs, max_length=100, num_return_sequences=1)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)


interface = gr.Interface(
    fn=generate_text,
    inputs="text",
    outputs="text",
    title="MatheuX",
    description="MatheuX de LuXe on the FluX"
)


if __name__ == "__main__":
    interface.launch()