model_097403367_perceiver_large.py

Model Overview

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

Architecture

• Architecture: perceiver
• Scale: large
• Attention: dilated
• Fusion strategy: tensor fusion
• Task head: classification
• Activation: mish
• Normalization: scalenorm
• Initialization: trunc normal

Training

• Optimizer: novograd
• LR scheduler: constant warmup

Files

• model_097403367_perceiver_large.py — main artifact of this repository

License

See the license field above.