Run 35B MoE models in ~2.5 GB of RAM. Weights stream from SSD; a trained router predicts loads a step ahead. Mac, iPhone, Android, Windows supported
Python
| Name | Last commit message | Last commit date |
|---|---|---|
| .. | ||
| __init__.py 867 B | ||
| heads.py 2.5 KB | ||
| install.py 8.2 KB | ||
| spec.py 2.8 KB | ||
| stager.py 12.7 KB | ||
| state.py 1.7 KB | ||