model_423877653_poolformer_base.py

Model Overview

A base-scale implementation of the poolformer architecture, built for contrastive tasks.

Architecture

• Architecture: poolformer
• Scale: base
• Attention: sparse
• Fusion strategy: cross attention
• Task head: contrastive
• Activation: gelu tanh
• Normalization: groupnorm
• Initialization: xavier uniform

Training

• Optimizer: novograd
• LR scheduler: exponential

Files

• model_423877653_poolformer_base.py — main artifact of this repository

License

See the license field above.