model_253914481_albef_huge.py

Model Overview

A huge-scale implementation of the albef architecture, built for generation tasks.

Architecture

• Architecture: albef
• Scale: huge
• Attention: multi query
• Fusion strategy: concat mlp
• Task head: generation
• Activation: mish
• Normalization: scalenorm
• Initialization: orthogonal

Training

• Optimizer: adam
• LR scheduler: step

Files

• model_253914481_albef_huge.py — main artifact of this repository

License

See the license field above.