johnscottgit
/

bart-embedding

constant-warmup

Model card Files Files and versions

predict.py

Model Overview

A base-scale implementation of the perceiver architecture, built for classification tasks.

Architecture

Architecture: perceiver
Scale: base
Attention: standard
Fusion strategy: tucker
Task head: classification
Activation: relu
Normalization: scalenorm
Initialization: trunc normal

Training

Optimizer: adamw
LR scheduler: constant warmup

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