model_588331833_deit_huge.py
Model Overview
A huge-scale implementation of the deit architecture, built for contrastive tasks.
Architecture
- Architecture: deit
- Scale: huge
- Attention: multi query
- Fusion strategy: concat mlp
- Task head: contrastive
- Activation: mish
- Normalization: groupnorm
- Initialization: xavier
Training
- Optimizer: adafactor
- LR scheduler: constant warmup
Files
model_588331833_deit_huge.py— main artifact of this repository
License
See the license field above.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support