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

model_name = "microsoft/phi-2"  # Very fast & high quality

tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

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

def chat(user_input, history=[]):
    result = pipe(user_input, max_new_tokens=100, do_sample=True, temperature=0.8)
    response = result[0]["generated_text"]
    history.append((user_input, response))
    return history, history

gr.ChatInterface(
    fn=chat,
    title="⚡ Mobe 2.0 – Super Fast AI",
    description="Using Microsoft Phi-2, blazing fast!",
    theme="soft"
).launch()