model_084674022_perceiver_small.py

Model Overview

A small-scale implementation of the perceiver architecture, built for retrieval tasks.

Architecture

• Architecture: perceiver
• Scale: small
• Attention: linear
• Fusion strategy: tensor fusion
• Task head: retrieval
• Activation: relu
• Normalization: layernorm
• Initialization: trunc normal

Training

• Optimizer: adamw
• LR scheduler: onecycle

Files

• model_084674022_perceiver_small.py — main artifact of this repository

License

See the license field above.