Embedding Draw Challenge

Embedding Draw Challenge

A Gradio draw challenge from google built around the EmbeddingGemma 2 model. The card gives no rules, so the page itself shows how to play.

Made by google on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Embedding Draw Challenge is a Gradio demo from the google account that builds a drawing challenge around EmbeddingGemma 2. The Space names the model google/embeddinggemma-2 and a dataset called gg-hf-em/embeddinggemma-2-eap-extras. The card is a single line, so it says nothing about the rules or how a round is scored.

Who it suits: People who want to try an embedding model through a game instead of reading about it. Developers can also read the short app file to see how a challenge page is built.

Industry | Who uses it | How they use it | Example
Education | Students of machine learning | Learn what an embedding model does by playing | Open the page and take the challenge
Research | ML practitioners | Try EmbeddingGemma 2 on their own inputs | Play a round and note how it responds
Software | Developers | Study a small Gradio game around a model | Read app.py in a local copy

If you need written rules or documentation, you can skip it, because the card gives none.

Where to use it: The demo runs in these places:

• A web browser: open the Space page on Hugging Face and play there.
• Windows, macOS or Linux: run a copy on your own computer with Python 3.12.

Use case | Who | What they get back
Play the challenge | Anyone | Whatever the Gradio page shows after each round
Try the model | ML practitioners | A hands-on feel for EmbeddingGemma 2
Run it locally | Developers | The same Gradio app on their own computer

How to set it up: You need a few things first:

• Python 3.12
• The huggingface_hub package, which the first command installs
• The packages listed in requirements.txt

The steps download the Space, install Gradio at the version the Space uses, add the other packages and start the app.

1. Install the Hugging Face package.
2. Download the Space into a folder called embedding-draw-challenge.
3. Move into that folder.
4. Install Gradio 6.28.0.
5. Install the packages from requirements.txt.
6. Start the app.

pip install -U huggingface_hub
hf download google/embedding-draw-challenge --repo-type space --local-dir embedding-draw-challenge
cd embedding-draw-challenge
pip install gradio==6.28.0
pip install -r requirements.txt
python app.py

How to use it: Open the Space page on Hugging Face, or start the local copy with the last command above. Gradio serves a web page where you take the challenge. The card does not list the controls.

python app.py

Tool | What it does
hf download | Copies the Space's files into a folder on your computer
python app.py | Starts the challenge on your own computer

Example: You open the Space and start the challenge. Because the card says nothing about the rules, you follow the prompts the page gives and read how the model responds.

For newcomers and experts: If you are new to this, open the Space page and play one round. You do not need to install anything for that. An embedding model turns inputs into numbers that can be compared, and the game is a way to feel that.

If you know the field, the Space names google/embeddinggemma-2 and one extra dataset. The repository is three files by the card's own list, app.py, requirements.txt and the README, and the hosted Space runs on the zero-a10g hardware tier.

You open the Space or run python app.py
A Gradio page starts the challenge
EmbeddingGemma 2 works on your input
The page shows the result

Good to know: The card says almost nothing, so check the page for the rules before relying on it.

• License: apache-2, as the Space lists it.
• Cost to run: none named. The hosted Space runs on the zero-a10g hardware at Hugging Face.
• Data it reaches: what you give the challenge, plus the model and dataset it names. A local copy downloads the Space's files from Hugging Face.
• Not for: none stated in the card.

On Hugging Face, 13 November 2026

• Likes: 30
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/google/embedding-draw-challenge
• Files: https://huggingface.co/spaces/google/embedding-draw-challenge/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.