model_287927282_coca_xlarge.py

Model Overview

A xlarge-scale implementation of the coca architecture, built for matching tasks.

Architecture

• Architecture: coca
• Scale: xlarge
• Attention: dilated
• Fusion strategy: low rank
• Task head: matching
• Activation: mish
• Normalization: batchnorm
• Initialization: trunc normal

Training

• Optimizer: adafactor
• LR scheduler: onecycle

Files

• model_287927282_coca_xlarge.py — main artifact of this repository

License

See the license field above.