app.py

from transformers import AutoModelForCausalLM, AutoTokenizer
import gradio as gr

# Load the model and tokenizer
model_name = "meta-llama/Llama-3.1-8B-Instruct"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

def predict(input_text):
    # Tokenize input and generate text
    inputs = tokenizer(input_text, return_tensors="pt")
    outputs = model.generate(**inputs)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

# Create a Gradio interface
interface = gr.Interface(
    fn=predict,
    inputs=gr.Textbox(label="Input Text"),
    outputs=gr.Textbox(label="Generated Output"),
    title="Phi-4 Model",
    description="Generate text using the microsoft/phi-4 model."
)

# Launch the interface
interface.launch()