Downloads · 30 days
15
38% of all-time downloads
budgie-100m
Asilarkness/budgie-100m
budgie-100m is a machine learning model from Asilarkness. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as apache-2.0.
100M-param ablation checkpoint of budgie-1b (parrot-themed from-scratch reasoning LLM). Base pretrain, 12 layers x 768 dmodel, GQA 12Q/3KV, hybrid sliding-window+global attention, QK-norm, value-residual, partial RoPE…
All-time downloads
40
Public
Parameters
112M
448 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors448 MB · 99%
At a glance
- License
- apache-2.0
- Model type
- budgie
- Access
- Public
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026
- SHA
- a5d5b2cd
Model card
From the Hugging Face model README
budgie-100m
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.
- Type
- budgie
- License
- apache-2.0
- Created
- Jul 17, 2026
- Updated
- Jul 17, 2026