model_652268093_mae_large.py
Model Overview
A large-scale implementation of the mae architecture, built for contrastive tasks.
Architecture
- Architecture: mae
- Scale: large
- Attention: flash
- Fusion strategy: gated fusion
- Task head: contrastive
- Activation: relu
- Normalization: layernorm
- Initialization: xavier uniform
Training
- Optimizer: adafactor
- LR scheduler: linear warmup
Files
model_652268093_mae_large.py — main artifact of this repository
License
See the license field above.
