app.py

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

model_name = "microsoft/phi-2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name, torch_dtype=torch.float32)

def chat(user_input):
    inputs = tokenizer(user_input, return_tensors="pt")
    outputs = model.generate(**inputs, max_length=200, pad_token_id=tokenizer.eos_token_id)
    response = tokenizer.decode(outputs[0], skip_special_tokens=True)
    return response

iface = gr.Interface(fn=chat, inputs="text", outputs="text", title="Free AI Chatbot")
iface.launch()