model_357099823_mobilevit_large.py

Model Overview

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

Architecture

• Architecture: mobilevit
• Scale: large
• Attention: dilated
• Fusion strategy: cross attention
• Task head: contrastive
• Activation: gelu
• Normalization: layernorm
• Initialization: kaiming normal

Training

• Optimizer: adafactor
• LR scheduler: exponential

Files

• model_357099823_mobilevit_large.py — main artifact of this repository

License

See the license field above.