model_273459090_coca_small.py

Model Overview

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

Architecture

• Architecture: coca
• Scale: small
• Attention: grouped query
• Fusion strategy: low rank
• Task head: multitask
• Activation: swish
• Normalization: batchnorm
• Initialization: kaiming

Training

• Optimizer: adamw
• LR scheduler: step

Files

• model_273459090_coca_small.py — main artifact of this repository

License

See the license field above.