model_315779333_tiny_transformer_base.py
Model Overview
A base-scale implementation of the tiny transformer architecture, built for classification tasks.
Architecture
- Architecture: tiny transformer
- Scale: base
- Attention: dilated
- Fusion strategy: low rank
- Task head: classification
- Activation: gelu
- Normalization: batchnorm
- Initialization: orthogonal
Training
- Optimizer: lamb
- LR scheduler: step
Files
model_315779333_tiny_transformer_base.py — main artifact of this repository
License
See the license field above.
