metadata
license: apache-2.0
tags:
- adam
- beit
- contrastive
- layernorm
- polynomial
- relu
- sliding-window
- small
- tucker
- xavier-uniform
model_606472619_beit_small.py
Model Overview
A small-scale implementation of the beit architecture, built for contrastive tasks.
Architecture
- Architecture: beit
- Scale: small
- Attention: sliding window
- Fusion strategy: tucker
- Task head: contrastive
- Activation: relu
- Normalization: layernorm
- Initialization: xavier uniform
Training
- Optimizer: adam
- LR scheduler: polynomial
Files
model_606472619_beit_small.py— main artifact of this repository
License
See the license field above.