major-scale/anim-binary-counting

A World Model That Learned Perfect Binary Arithmetic

DreamerV3 world model trained on a 4-bit binary counting environment (500K steps). The model learned to simulate carry cascades autonomously — 100% completion rate under full observation ablation.

Paper: GitHub

Files

File	Description	Size
latest.pt	Full DreamerV3 checkpoint (PyTorch)	136 MB
exported/dreamer_weights.bin	Extracted weight matrices for numpy RSSM	23 MB
exported/dreamer_manifest.json	Weight name mapping	4 KB
battery.npz	Pre-collected hidden states from 15 episodes	25 MB
metrics.jsonl	Training metrics log	79 KB

Usage

The analysis scripts use the exported weights (no PyTorch required):

git clone https://github.com/major-scale/anim-binary-counting
cd anim-binary-counting

# Download exported weights
mkdir -p checkpoints/exported
wget https://huggingface.co/major-scale/anim-binary-counting/resolve/main/exported/dreamer_weights.bin -O checkpoints/exported/dreamer_weights.bin
wget https://huggingface.co/major-scale/anim-binary-counting/resolve/main/exported/dreamer_manifest.json -O checkpoints/exported/dreamer_manifest.json
wget https://huggingface.co/major-scale/anim-binary-counting/resolve/main/battery.npz -O data/battery.npz

# Run analysis
pip install -r code/requirements.txt
python code/analysis/verify_dual_mode.py

Training

Trained with DreamerV3-torch on a single GPU (~4 hours). See code/training/ in the GitHub repo for configs and launcher.

License

MIT