model_041637999_cnn_transformer_nano.py

Model Overview

A nano-scale implementation of the cnn transformer architecture, built for retrieval tasks.

Architecture

• Architecture: cnn transformer
• Scale: nano
• Attention: dilated
• Fusion strategy: bilinear
• Task head: retrieval
• Activation: relu
• Normalization: groupnorm
• Initialization: xavier uniform

Training

• Optimizer: lamb
• LR scheduler: polynomial

Files

• model_041637999_cnn_transformer_nano.py — main artifact of this repository

License

See the license field above.