metadata
license: mit
tags:
- adam
- approx-gelu
- classification
- linear-warmup
- poolformer
- scalenorm
- standard
- tensor-fusion
- xavier-uniform
- xlarge
model_432419520_poolformer_xlarge.py
Model Overview
A xlarge-scale implementation of the poolformer architecture, built for classification tasks.
Architecture
- Architecture: poolformer
- Scale: xlarge
- Attention: standard
- Fusion strategy: tensor fusion
- Task head: classification
- Activation: approx gelu
- Normalization: scalenorm
- Initialization: xavier uniform
Training
- Optimizer: adam
- LR scheduler: linear warmup
Files
model_432419520_poolformer_xlarge.py— main artifact of this repository
License
See the license field above.