app.py

import os

import gradio as gr
from transformers import pipeline
HF_TOKEN = os.environ.get("llama3", None)

# Initialize the text generation pipeline
pipe = pipeline("text-generation", model="meta-llama/Meta-Llama-3.1-405B")

# Define the function to generate text
def generate_text(prompt):
    result = pipe(prompt, max_length=50, num_return_sequences=1)
    return result[0]['generated_text']

# Create a Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter your prompt here..."),
    outputs="text",
    title="Meta-Llama Text Generation",
    description="Generate text using the Meta-Llama 3.1 405B model."
)

# Launch the interface
iface.launch()