model_272948624_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: cross attention
- Task head: multitask
- Activation: relu
- Normalization: layernorm
- Initialization: xavier
Training
- Optimizer: adafactor
- LR scheduler: polynomial
Files
model_272948624_coca_small.py — main artifact of this repository
License
See the license field above.