app.py

import gradio as gr

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Meta-Llama-3-8B-Instruct")

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

# Create the Gradio interface
iface = gr.Interface(fn=generate, inputs="text", outputs="text", title="Medical Assistant", description="Ask me any medical question.")

# Launch the Gradio interface
iface.launch()