metadata
license: mit
tags:
- contrastive
- cosine
- efficientformer
- gated-fusion
- giant
- instancenorm
- novograd
- standard
- swish
- xavier
model_404349722_efficientformer_giant.py
Model Overview
A giant-scale implementation of the efficientformer architecture, built for contrastive tasks.
Architecture
- Architecture: efficientformer
- Scale: giant
- Attention: standard
- Fusion strategy: gated fusion
- Task head: contrastive
- Activation: swish
- Normalization: instancenorm
- Initialization: xavier
Training
- Optimizer: novograd
- LR scheduler: cosine
Files
model_404349722_efficientformer_giant.py— main artifact of this repository
License
See the license field above.