app.py

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

device = "cuda" if torch.cuda.is_available() else "cpu"
model_path = "ibm-granite/granite-3b-code-base"
tokenizer = AutoTokenizer.from_pretrained(model_path)
model = AutoModelForCausalLM.from_pretrained(model_path, device_map=device)
model.eval()

def generate_code(input_text):
    input_tokens = tokenizer(input_text, return_tensors="pt")
    for i in input_tokens:
        input_tokens[i] = input_tokens[i].to(device)
    output = model.generate(**input_tokens, max_new_tokens=200)
    output_text = tokenizer.batch_decode(output, skip_special_tokens=True)[0]
    return output_text

# Gradio Interface
iface = gr.Interface(
    fn=generate_code, 
    inputs=gr.inputs.Textbox(lines=2, placeholder="Enter code snippet here..."), 
    outputs="text"
)

iface.launch()