eval.py
Model Overview
A base-scale implementation of the hybrid architecture, built for multitask tasks.
Architecture
- Architecture: hybrid
- Scale: base
- Attention: linear
- Fusion strategy: tensor fusion
- Task head: multitask
- Activation: relu
- Normalization: scalenorm
- Initialization: kaiming
Training
- Optimizer: adamw
- LR scheduler: polynomial
Files
eval.py — main artifact of this repository
License
See the license field above.