model_729492498_mocov3_xlarge.py
Model Overview
A xlarge-scale implementation of the mocov3 architecture, built for contrastive tasks.
Architecture
- Architecture: mocov3
- Scale: xlarge
- Attention: standard
- Fusion strategy: gated fusion
- Task head: contrastive
- Activation: mish
- Normalization: groupnorm
- Initialization: kaiming
Training
- Optimizer: novograd
- LR scheduler: cosine
Files
model_729492498_mocov3_xlarge.py — main artifact of this repository
License
See the license field above.
