model_033114196_vit_giant.py
Model Overview
A giant-scale implementation of the vit architecture, built for matching tasks.
Architecture
- Architecture: vit
- Scale: giant
- Attention: linear
- Fusion strategy: cross attention
- Task head: matching
- Activation: mish
- Normalization: layernorm
- Initialization: xavier uniform
Training
- Optimizer: rmsprop
- LR scheduler: exponential
Files
model_033114196_vit_giant.py — main artifact of this repository
License
See the license field above.
