model_630250313_beit_giant.py
Model Overview
A giant-scale implementation of the beit architecture, built for classification tasks.
Architecture
- Architecture: beit
- Scale: giant
- Attention: multi query
- Fusion strategy: tucker
- Task head: classification
- Activation: gelu
- Normalization: scalenorm
- Initialization: trunc normal
Training
- Optimizer: rmsprop
- LR scheduler: cosine
Files
model_630250313_beit_giant.py — main artifact of this repository
License
See the license field above.
