model_725409417_mocov3_large.py

Model Overview

A large-scale implementation of the mocov3 architecture, built for matching tasks.

Architecture

• Architecture: mocov3
• Scale: large
• Attention: linear
• Fusion strategy: gated fusion
• Task head: matching
• Activation: gelu
• Normalization: groupnorm
• Initialization: trunc normal

Training

• Optimizer: adafactor
• LR scheduler: constant warmup

Files

• model_725409417_mocov3_large.py — main artifact of this repository

License

See the license field above.