model_058341607_cnn_transformer_large.py

Model Overview

A large-scale implementation of the cnn transformer architecture, built for multitask tasks.

Architecture

• Architecture: cnn transformer
• Scale: large
• Attention: sliding window
• Fusion strategy: gated fusion
• Task head: multitask
• Activation: relu
• Normalization: instancenorm
• Initialization: xavier

Training

• Optimizer: lion
• LR scheduler: step

Files

• model_058341607_cnn_transformer_large.py — main artifact of this repository

License

See the license field above.