app.py

import gradio as gr
from transformers import pipeline, AutoTokenizer, AutoModelForCausalLM
import torch

model_dir = "./"  # your model folder
tokenizer = AutoTokenizer.from_pretrained(model_dir)
model = AutoModelForCausalLM.from_pretrained(model_dir)

generator = pipeline("text-generation", model=model, tokenizer=tokenizer, device=0 if torch.cuda.is_available() else -1)

def generate_answer(prompt):
    output = generator(prompt, max_length=100, do_sample=True, top_p=0.95, temperature=0.7)
    return output[0]['generated_text']

gr.Interface(fn=generate_answer, inputs="text", outputs="text", title="Medical Chatbot").launch()