model_076084019_perceiver_nano.py
Model Overview
A nano-scale implementation of the perceiver architecture, built for contrastive tasks.
Architecture
- Architecture: perceiver
- Scale: nano
- Attention: flash
- Fusion strategy: cross attention
- Task head: contrastive
- Activation: gelu
- Normalization: groupnorm
- Initialization: trunc normal
Training
- Optimizer: adam
- LR scheduler: polynomial
Files
model_076084019_perceiver_nano.py — main artifact of this repository
License
See the license field above.
