model_735123571_mocov3_huge.py

Model Overview

A huge-scale implementation of the mocov3 architecture, built for classification tasks.

Architecture

• Architecture: mocov3
• Scale: huge
• Attention: sparse
• Fusion strategy: co attention
• Task head: classification
• Activation: gelu
• Normalization: instancenorm
• Initialization: orthogonal

Training

• Optimizer: lamb
• LR scheduler: cosine

Files

• model_735123571_mocov3_huge.py — main artifact of this repository

License

See the license field above.