model_247714362_albef_xlarge.py

Model Overview

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

Architecture

• Architecture: albef
• Scale: xlarge
• Attention: sparse
• Fusion strategy: bilinear
• Task head: matching
• Activation: gelu
• Normalization: layernorm
• Initialization: xavier

Training

• Optimizer: novograd
• LR scheduler: cosine

Files

• model_247714362_albef_xlarge.py — main artifact of this repository

License

See the license field above.