model_669947708_dino_nano.py

Model Overview

A nano-scale implementation of the dino architecture, built for multitask tasks.

Architecture

• Architecture: dino
• Scale: nano
• Attention: linear
• Fusion strategy: tensor fusion
• Task head: multitask
• Activation: approx gelu
• Normalization: scalenorm
• Initialization: xavier

Training

• Optimizer: rmsprop
• LR scheduler: exponential

Files

• model_669947708_dino_nano.py — main artifact of this repository

License

See the license field above.