model_715950174_mocov3_small.py

Model Overview

A small-scale implementation of the mocov3 architecture, built for multitask tasks.

Architecture

• Architecture: mocov3
• Scale: small
• Attention: linear
• Fusion strategy: cross attention
• Task head: multitask
• Activation: gelu
• Normalization: layernorm
• Initialization: trunc normal

Training

• Optimizer: adafactor
• LR scheduler: step

Files

• model_715950174_mocov3_small.py — main artifact of this repository

License

See the license field above.