model_727550322_mocov3_large.py

Model Overview

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

Architecture

• Architecture: mocov3
• Scale: large
• Attention: multi query
• Fusion strategy: cross attention
• Task head: retrieval
• Activation: gelu
• Normalization: batchnorm
• Initialization: trunc normal

Training

• Optimizer: adamw
• LR scheduler: step

Files

• model_727550322_mocov3_large.py — main artifact of this repository

License

See the license field above.