---
title: AI vs Human Code Classifier
emoji: 🤖
colorFrom: purple
colorTo: blue
sdk: docker
python_version: "3.11.9"
suggested_hardware: cpu-basic
startup_duration_timeout: 60m
preload_from_hub:
  - microsoft/unixcoder-base
models:
  - microsoft/unixcoder-base
short_description: AI vs human code classifier
tags:
  - code-classification
  - explainability
  - xgboost
---

# AI vs Human Code Classifier

Gradio demo for [Hugging Face Spaces](https://huggingface.co/docs/hub/spaces-overview) using the same inference stack as the Reflex app (`reflex_ui`).

## Deploy on Hugging Face

1. Create a [new Space](https://huggingface.co/new-space), pick **Gradio**, then push this repository (or connect GitHub and set the repository).
2. In **Settings → Hardware**, keep **CPU Basic** (free: 16 GB RAM) unless you need a GPU.
3. Open the **App** tab. The first run may take a while while weights load.

Public URL shape: `https://huggingface.co/spaces/<your-username>/<space-name>` (and the `.hf.space` embed URL from the Space menu).

## Local Gradio (optional)

```bash
pip install -r requirements.txt
python app.py
```

## Local Reflex UI

See `reflex_ui/README.md` for the full Reflex front end.