model_283034612_coca_large.py

Model Overview

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

Architecture

• Architecture: coca
• Scale: large
• Attention: dilated
• Fusion strategy: gated fusion
• Task head: multitask
• Activation: gelu
• Normalization: scalenorm
• Initialization: trunc normal

Training

• Optimizer: adafactor
• LR scheduler: cosine

Files

• model_283034612_coca_large.py — main artifact of this repository

License

See the license field above.