yulee7566's picture
Upload 2 files
1d73a9f verified
|
Raw
History Blame Contribute Delete
814 Bytes
metadata
license: bsd-3-clause
tags:
  - co-attention
  - efficientformer
  - exponential
  - kaiming
  - linear
  - relu
  - retrieval
  - rmsprop
  - scalenorm
  - small

model_381583436_efficientformer_small.py

Model Overview

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

Architecture

  • Architecture: efficientformer
  • Scale: small
  • Attention: linear
  • Fusion strategy: co attention
  • Task head: retrieval
  • Activation: relu
  • Normalization: scalenorm
  • Initialization: kaiming

Training

  • Optimizer: rmsprop
  • LR scheduler: exponential

Files

  • model_381583436_efficientformer_small.py — main artifact of this repository

License

See the license field above.