model_581937358_deit_xlarge.py

Model Overview

A xlarge-scale implementation of the deit architecture, built for matching tasks.

Architecture

• Architecture: deit
• Scale: xlarge
• Attention: sparse
• Fusion strategy: concat mlp
• Task head: matching
• Activation: approx gelu
• Normalization: batchnorm
• Initialization: kaiming

Training

• Optimizer: adafactor
• LR scheduler: step

Files

• model_581937358_deit_xlarge.py — main artifact of this repository

License

See the license field above.