model_263966039_coca_nano.py

Model Overview

A nano-scale implementation of the coca architecture, built for classification tasks.

Architecture

• Architecture: coca
• Scale: nano
• Attention: grouped query
• Fusion strategy: bilinear
• Task head: classification
• Activation: mish
• Normalization: rmsnorm
• Initialization: orthogonal

Training

• Optimizer: sgd
• LR scheduler: linear warmup

Files

• model_263966039_coca_nano.py — main artifact of this repository

License

See the license field above.