model_223127011_albef_nano.py
Model Overview
A nano-scale implementation of the albef architecture, built for contrastive tasks.
Architecture
- Architecture: albef
- Scale: nano
- Attention: standard
- Fusion strategy: concat mlp
- Task head: contrastive
- Activation: swish
- Normalization: batchnorm
- Initialization: trunc normal
Training
- Optimizer: rmsprop
- LR scheduler: step
Files
model_223127011_albef_nano.py — main artifact of this repository
License
See the license field above.