Metadata-Version: 2.5
Name: blt-trainer
Version: 0.1.2
Summary: Pure functional 96-layer Byte Latent Transformer trainer with Muon and weighted streaming datamix
Requires-Python: >=3.10
Requires-Dist: datasets>=2.16.0
Requires-Dist: numpy>=1.24.0
Requires-Dist: torch>=2.2.0
