100M-param ablation checkpoint of budgie-1b (parrot-themed from-scratch reasoning LLM). Base pretrain, 12 layers x 768 d_model, GQA 12Q/3KV, hybrid sliding-window+global attention, QK-norm, value-residual, partial RoPE, tied embeddings. Trained 7629 steps on ~3B tokens (Muon + AdamW, WSD schedule).
Custom architecture — load with trust_remote_code=True or the vendored model.py/config.py.
Have the files? Submit a torrent.
Submit a torrent →Have the complete files and permission to share them? Replace the example folder path. The script checks the files, makes a torrent and submits its magnet and checksums. Keep your torrent client seeding. Get your community key from your settings, and read the script before running it.
curl -fsSL https://pirateface.co/package.sh | bash -s -- --repo Asilarkness/budgie-100m ./model-folder