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 |
|---|---|---|
| .. | ||
| convert_pregate.py 4.0 KB | ||
| convert_tokenizer.py 4.3 KB | ||
| repack_experts.py 14.7 KB | ||