app.py

import gradio as gr
from transformers import AutoModelForCausalLM, AutoTokenizer

# Load LLaMA 3.2 model and tokenizer
model_name = "meta-llama/LLaMA-3.2"
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(model_name)

# Define the inference function
def generate_text(prompt, max_length=100, temperature=0.7):
    inputs = tokenizer(prompt, return_tensors="pt")
    output = model.generate(inputs['input_ids'], max_length=max_length, temperature=temperature)
    return tokenizer.decode(output[0], skip_special_tokens=True)

# Create the Gradio interface
iface = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.inputs.Textbox(label="Enter your prompt", placeholder="Start typing..."),
        gr.inputs.Slider(minimum=50, maximum=200, default=100, label="Max Length"),
        gr.inputs.Slider(minimum=0.1, maximum=1.0, default=0.7, label="Temperature"),
    ],
    outputs="text",
    title="LLaMA 3.2 Text Generator",
    description="Enter a prompt to generate text using the LLaMA 3.2 model.",
    theme="compact",
)

# Launch the Gradio app
iface.launch()