app.py

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

# Load model and tokenizer (using CPU for broader accessibility)
model = AutoModelForCausalLM.from_pretrained("microsoft/phi-2", torch_dtype=torch.float32, device_map="cpu", trust_remote_code=True)
tokenizer = AutoTokenizer.from_pretrained("microsoft/phi-2", trust_remote_code=True)

def generate_text(prompt):
    inputs = tokenizer(prompt, return_tensors="pt", return_attention_mask=False)
    outputs = model.generate(**inputs, max_length=200)
    text = tokenizer.batch_decode(outputs)[0]
    return text

# Create Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=[gr.Textbox(lines=5, label="Enter your prompt")],
    outputs="text",
    title="PHI-2 Text Generator",
    description="Generate text using the PHI-2 generative language model",
)

# Launch the interface
iface.launch()