model_618940610_beit_xlarge.py
Model Overview
A xlarge-scale implementation of the beit architecture, built for matching tasks.
Architecture
- Architecture: beit
- Scale: xlarge
- Attention: sparse
- Fusion strategy: cross attention
- Task head: matching
- Activation: gelu
- Normalization: layernorm
- Initialization: xavier
Training
- Optimizer: rmsprop
- LR scheduler: linear warmup
Files
model_618940610_beit_xlarge.py — main artifact of this repository
License
See the license field above.
