app.py

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

model_id = "key-life/codegen-alpaca-1b"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

def generate_code(prompt):
    formatted_prompt = f"### Instruction:\n{prompt}\n\n### Response:\n"
    inputs = tokenizer(formatted_prompt, return_tensors="pt").to(model.device)
    outputs = model.generate(**inputs, max_new_tokens=256)
    return tokenizer.decode(outputs[0], skip_special_tokens=True)

interface = gr.Interface(
    fn=generate_code,
    inputs=gr.Textbox(lines=5, label="Instruction"),
    outputs=gr.Code(label="Generated Code"),
    title="CodeGen Alpaca 1B",
    description="Give a coding instruction and get code as response from a fine-tuned StarCoderBase-1B model."
)

interface.launch()