app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

def load_model():
    # model_name = "internistai/base-7b-v0.2"
    model_name = "distilgpt2"
    tokenizer = AutoTokenizer.from_pretrained(model_name)
    model = AutoModelForCausalLM.from_pretrained(model_name)
    return model, tokenizer

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

model, tokenizer = load_model()

# Gradio interface to handle text input
iface = gr.Interface(
    fn=lambda message: chat(message, model, tokenizer),
    inputs="text",
    outputs="text"
)

# Expose an API endpoint
iface.launch(server_name="0.0.0.0", server_port=7860, enable_queue=True)