model_547648281_hybrid_xlarge.py
Model Overview
A xlarge-scale implementation of the hybrid architecture, built for multitask tasks.
Architecture
- Architecture: hybrid
- Scale: xlarge
- Attention: dilated
- Fusion strategy: co attention
- Task head: multitask
- Activation: gelu
- Normalization: groupnorm
- Initialization: kaiming normal
Training
- Optimizer: adafactor
- LR scheduler: constant warmup
Files
model_547648281_hybrid_xlarge.py— main artifact of this repository
License
See the license field above.
Inference Providers NEW
This model isn't deployed by any Inference Provider. 🙋 Ask for provider support