model_465706439_swin_t_large.py

Model Overview

A large-scale implementation of the swin t architecture, built for retrieval tasks.

Architecture

• Architecture: swin t
• Scale: large
• Attention: sparse
• Fusion strategy: cross attention
• Task head: retrieval
• Activation: approx gelu
• Normalization: layernorm
• Initialization: xavier

Training

• Optimizer: lion
• LR scheduler: step

Files

• model_465706439_swin_t_large.py — main artifact of this repository

License

See the license field above.