metadata
license: bsd-3-clause
tags:
- contrastive
- cross-attention
- exponential
- gelu
- kaiming
- layernorm
- perceiver
- sgd
- sparse
- tiny
model_080148785_perceiver_tiny.py
Model Overview
A tiny-scale implementation of the perceiver architecture, built for contrastive tasks.
Architecture
- Architecture: perceiver
- Scale: tiny
- Attention: sparse
- Fusion strategy: cross attention
- Task head: contrastive
- Activation: gelu
- Normalization: layernorm
- Initialization: kaiming
Training
- Optimizer: sgd
- LR scheduler: exponential
Files
model_080148785_perceiver_tiny.py— main artifact of this repository
License
See the license field above.