notebooks/llm-question-answering/app.py

import gradio as gr
from transformers import AutoTokenizer, TextIteratorStreamer

# Define the models and their configurations
model_name = "phi-2"  
model_configuration = {
    "toeknizer_kwargs": {'model_id': 'susnato/phi-2', 'prompt_template': 'Instruct:{instruction}\nOutput:'}  
}

# Load the tokenizer
tokenizer = AutoTokenizer.from_pretrained(model_name)
tokenizer_kwargs = model_configuration.get("toeknizer_kwargs", {})

# Define the Gradio interface
def main():
    with gr.Row():
        with gr.Column(scale=4):
            user_text = gr.Textbox(
                placeholder="Write an email about an alpaca that likes flan",
                label="User instruction",
            )
            model_output = gr.Textbox(label="Model response", interactive=False)
            performance = gr.Textbox(label="Performance", lines=1, interactive=False)
            with gr.Column(scale=1):
                button_clear = gr.Button(value="Clear")
                button_submit = gr.Button(value="Submit")

# Run the Gradio interface
iface = gr.Interface(fn=main, inputs=user_text, outputs=model_output, performance=performance, live=True)
iface.launch()