app.py

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

# Load model and tokenizer
model_name = "meta-llama/Llama-3.2-3b-base"  # Use the actual model path
tokenizer = AutoTokenizer.from_pretrained(model_name)
model = AutoModelForCausalLM.from_pretrained(
    model_name,
    torch_dtype=torch.bfloat16,
    device_map="auto"
)

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

# Create Gradio interface
demo = gr.Interface(
    fn=generate_text,
    inputs=[
        gr.Textbox(lines=5, placeholder="Enter your prompt here..."),
        gr.Slider(minimum=1, maximum=500, value=100, label="Max Length"),
        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, label="Temperature")
    ],
    outputs=gr.Textbox(),
    title="Llama 3.2 3B API",
    description="Generate text using Meta's Llama 3.2 3B model"
)

# Add API functionality
demo.queue()
demo.launch()