model_234837678_albef_small.py

Model Overview

A small-scale implementation of the albef architecture, built for retrieval tasks.

Architecture

• Architecture: albef
• Scale: small
• Attention: sliding window
• Fusion strategy: gated fusion
• Task head: retrieval
• Activation: swish
• Normalization: groupnorm
• Initialization: kaiming normal

Training

• Optimizer: rmsprop
• LR scheduler: constant warmup

Files

• model_234837678_albef_small.py — main artifact of this repository

License

See the license field above.