app.py

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

model_id = "microsoft/phi-2"
tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id)

pipe = pipeline("text-generation", model=model, tokenizer=tokenizer)

def chat(msg):
    out = pipe(msg, max_new_tokens=150)[0]['generated_text']
    return out

gr.Interface(fn=chat, inputs="text", outputs="text").launch()