model_725155645_mocov3_large.py

Model Overview

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

Architecture

• Architecture: mocov3
• Scale: large
• Attention: standard
• Fusion strategy: low rank
• Task head: retrieval
• Activation: gelu
• Normalization: rmsnorm
• Initialization: xavier

Training

• Optimizer: rmsprop
• LR scheduler: polynomial

Files

• model_725155645_mocov3_large.py — main artifact of this repository

License

See the license field above.