app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

def load_model():
    try:
        model_name = "internistai/base-7b-v0.2"
        tokenizer = AutoTokenizer.from_pretrained(model_name)
        model = AutoModelForCausalLM.from_pretrained(model_name)
        return model, tokenizer
    except Exception as e:
        print(f"Error loading model: {e}")
        return None, None

def chat(message, model, tokenizer):
    try:
        inputs = tokenizer(message, return_tensors="pt")
        outputs = model.generate(**inputs)
        response = tokenizer.decode(outputs[0], skip_special_tokens=True)
        return response
    except Exception as e:
        return f"Error generating response: {e}"

model, tokenizer = load_model()
if model is None or tokenizer is None:
    print("Failed to load model or tokenizer. Please check the configuration.")

iface = gr.Interface(fn=lambda message: chat(message, model, tokenizer), inputs="text", outputs="text")
iface.launch()