model_039661283_cnn_transformer_nano.py
Model Overview
A nano-scale implementation of the cnn transformer architecture, built for contrastive tasks.
Architecture
- Architecture: cnn transformer
- Scale: nano
- Attention: sliding window
- Fusion strategy: concat mlp
- Task head: contrastive
- Activation: approx gelu
- Normalization: groupnorm
- Initialization: xavier
Training
- Optimizer: adam
- LR scheduler: polynomial
Files
model_039661283_cnn_transformer_nano.py — main artifact of this repository
License
See the license field above.