app.py

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

MODEL_ID = "AlexKitipov/phi-2"

tokenizer = AutoTokenizer.from_pretrained(MODEL_ID, trust_remote_code=True)
model = AutoModelForCausalLM.from_pretrained(
    MODEL_ID,
    torch_dtype="auto",
    trust_remote_code=True,
    device_map="cpu"
)

def chat(prompt):
    inputs = tokenizer(prompt, return_tensors="pt")
    outputs = model.generate(
        **inputs,
        max_new_tokens=256,
        temperature=0.7,
        top_p=0.9
    )
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

demo = gr.Interface(
    fn=chat,
    inputs=gr.Textbox(
        lines=18,
        label="Prompt",
        placeholder="Type your message here..."
    ),
    outputs=gr.Textbox(
        lines=18,
        label="Response",
        placeholder="The model's response will appear here..."
    ),
    title="Phi‑2 App — by AlexKitipov",
    description="Interactive Phi‑2 demo with larger side‑by‑side text areas.",
)

demo.launch()