model_052830750_cnn_transformer_base.py
Model Overview
A base-scale implementation of the cnn transformer architecture, built for multitask tasks.
Architecture
- Architecture: cnn transformer
- Scale: base
- Attention: sparse
- Fusion strategy: low rank
- Task head: multitask
- Activation: mish
- Normalization: batchnorm
- Initialization: xavier uniform
Training
- Optimizer: sgd
- LR scheduler: cosine
Files
model_052830750_cnn_transformer_base.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