demo

title	BrickGPT-Demo
emoji	🧱
colorFrom	green
colorTo	yellow
license	mit
short_description	Generate stable toy brick structures from text prompts.
app_file	app.py
sdk	gradio
sdk_version	5.49.1
python_version	3.10.13
models	AvaLovelace/BrickGPT
pinned	true
thumbnail	https://cdn-uploads.huggingface.co/production/uploads/672403d5f328a3e6638331ee/H66Srg95-N--44lg9-4dX.png

BrickGPT Demo

This subdirectory contains the code for the official BrickGPT Gradio demo.

Prerequisites

• Llama-3.2-1B-Instruct: BrickGPT is fine-tuned from meta-llama/Llama-3.2-1B-Instruct, a gated model. Request access to the model here. Then generate a Hugging Face user access token and set your access token as an environment variable: export HF_TOKEN=<your_token>. The model will be automatically downloaded upon running the code.
• Gurobi: Running stability analysis requires a Gurobi licence to use Gurobi. Academics may request a free licence from the Gurobi website here. Place the Gurobi licence file in your home directory or another recommended location.
• ImportLDraw: Rendering brick visualizations requires ImportLDraw, provided as a Git submodule. Follow these instructions to install ImportLDraw:
  • Download Git LFS, then run git lfs install.
  • Install Git submodules with git submodule update --init.
  • Download the LDraw parts library and extract it in your home directory: (cd ~ && wget https://library.ldraw.org/library/updates/complete.zip && unzip complete.zip).
    • If you wish to put the LDraw parts library in a different directory, set the environment variable LDRAW_LIBRARY_PATH to the path of the ldraw directory: export LDRAW_LIBRARY_PATH=path/to/ldraw.
  • Download this background exr file and place it in the ImportLDraw/loadldraw subdirectory.

Usage

Install the Python project manager uv. Then run the demo with:

uv run gradio app.py