model_650683492_mae_large.py
Model Overview
A large-scale implementation of the mae architecture, built for generation tasks.
Architecture
- Architecture: mae
- Scale: large
- Attention: standard
- Fusion strategy: bilinear
- Task head: generation
- Activation: relu
- Normalization: layernorm
- Initialization: xavier uniform
Training
- Optimizer: adamw
- LR scheduler: polynomial
Files
model_650683492_mae_large.py — main artifact of this repository
License
See the license field above.