model_013078813_vit_small.py

Model Overview

A small-scale implementation of the vit architecture, built for matching tasks.

Architecture

• Architecture: vit
• Scale: small
• Attention: grouped query
• Fusion strategy: tucker
• Task head: matching
• Activation: relu
• Normalization: layernorm
• Initialization: orthogonal

Training

• Optimizer: adam
• LR scheduler: onecycle

Files

• model_013078813_vit_small.py — main artifact of this repository

License

See the license field above.