model_366097590_mobilevit_huge.py

Model Overview

A huge-scale implementation of the mobilevit architecture, built for contrastive tasks.

Architecture

• Architecture: mobilevit
• Scale: huge
• Attention: grouped query
• Fusion strategy: tucker
• Task head: contrastive
• Activation: gelu
• Normalization: layernorm
• Initialization: trunc normal

Training

• Optimizer: rmsprop
• LR scheduler: constant warmup

Files

• model_366097590_mobilevit_huge.py — main artifact of this repository

License

See the license field above.