app.py

import requests
import torch
from PIL import Image
from transformers import pipeline

pipe = pipeline("text-generation", model="meta-llama/Llama-3.2-1B")

# Load model directly
from transformers import AutoTokenizer, AutoModelForCausalLM

tokenizer = AutoTokenizer.from_pretrained("meta-llama/Llama-3.2-1B")
model = AutoModelForCausalLM.from_pretrained("meta-llama/Llama-3.2-1B")

# Load the processor
processor = AutoProcessor.from_pretrained(model_id)


# Define the function to generate text based on input prompt
def generate_text(prompt):
    if llm_pipeline is None:
        return "Error: Model not loaded."
    result = llm_pipeline(prompt, max_length=100, num_return_sequences=1)
    return result[0]['generated_text']

# Create the Gradio interface
interface = gr.Interface(
    fn=generate_text,
    inputs=gr.Textbox(lines=7, label="Input Prompt"),
    outputs="text",
    title="Large Language Model Text Generation",
    description="Enter a prompt to generate text using a large language model."
)

print("Launching the Gradio interface...")
# Launch the interface
interface.launch()