import gradio as gr
from transformers import AutoTokenizer, AutoModelForCausalLM

model_name = "your-username/my-wizardmath-finetuned"

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto")

def generate_response(prompt):
    inputs = tokenizer(prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

gr.Interface(fn=generate_response,
             inputs="text",
             outputs="text",
             title="WizardMath Fine-Tuned",
             description="Ask WizardMath anything!"
            ).launch()