model_627493963_beit_giant.py
Model Overview
A giant-scale implementation of the beit architecture, built for classification tasks.
Architecture
- Architecture: beit
- Scale: giant
- Attention: standard
- Fusion strategy: tensor fusion
- Task head: classification
- Activation: gelu
- Normalization: groupnorm
- Initialization: kaiming normal
Training
- Optimizer: sgd
- LR scheduler: constant warmup
Files
model_627493963_beit_giant.py — main artifact of this repository
License
See the license field above.