model_063024864_cnn_transformer_xlarge.py

Model Overview

A xlarge-scale implementation of the cnn transformer architecture, built for contrastive tasks.

Architecture

• Architecture: cnn transformer
• Scale: xlarge
• Attention: sliding window
• Fusion strategy: tucker
• Task head: contrastive
• Activation: swish
• Normalization: layernorm
• Initialization: kaiming

Training

• Optimizer: adamw
• LR scheduler: cosine

Files

• model_063024864_cnn_transformer_xlarge.py — main artifact of this repository

License

See the license field above.