app.py

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

# Load the model and tokenizer with trust_remote_code=True
model_name = "Flmc/DISC-MedLLM"
tokenizer = AutoTokenizer.from_pretrained(model_name, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)

# Function to generate responses
def generate_response(input_text):
    if not input_text.strip():
        return "Please enter some text to generate a response."
    
    inputs = tokenizer(input_text, return_tensors="pt")
    if torch.cuda.is_available():
        inputs = inputs.to("cuda")
        model.to("cuda")
    outputs = model.generate(**inputs, max_new_tokens=150)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

# Gradio interface
iface = gr.Interface(fn=generate_response, inputs="text", outputs="text", title="Flmc/DISC-MedLLM")

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