model_336150934_mobilevit_nano.py
Model Overview
A nano-scale implementation of the mobilevit architecture, built for retrieval tasks.
Architecture
- Architecture: mobilevit
- Scale: nano
- Attention: sparse
- Fusion strategy: low rank
- Task head: retrieval
- Activation: relu
- Normalization: rmsnorm
- Initialization: orthogonal
Training
- Optimizer: sgd
- LR scheduler: cosine
Files
model_336150934_mobilevit_nano.py — main artifact of this repository
License
See the license field above.
