model_731647480_mocov3_xlarge.py

Model Overview

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

Architecture

• Architecture: mocov3
• Scale: xlarge
• Attention: sliding window
• Fusion strategy: co attention
• Task head: classification
• Activation: gelu tanh
• Normalization: rmsnorm
• Initialization: kaiming

Training

• Optimizer: adafactor
• LR scheduler: polynomial

Files

• model_731647480_mocov3_xlarge.py — main artifact of this repository

License

See the license field above.