sofiantsw
/

mistral-recsys66

Model card Files Files and versions

predict.py

Model Overview

A huge-scale implementation of the dino architecture, built for classification tasks.

Architecture

Architecture: dino
Scale: huge
Attention: sliding window
Fusion strategy: low rank
Task head: classification
Activation: gelu tanh
Normalization: batchnorm
Initialization: trunc normal

Training

Optimizer: lamb
LR scheduler: exponential

Files

predict.py — main artifact of this repository

License

See the license field above.

Downloads last month: -; Downloads are not tracked for this model. How to track

Inference Providers NEW

This model isn't deployed by any Inference Provider. 🙋 Ask for provider support