segment-finetune / README.md
brssmith's picture
Upload 2 files
d0216e0 verified
|
Raw
History Blame Contribute Delete
719 Bytes
metadata
license: mit
tags:
  - approx-gelu
  - batchnorm
  - kaiming
  - lamb
  - linear
  - linear-warmup
  - mae
  - multitask
  - small
  - tensor-fusion

train.py

Model Overview

A small-scale implementation of the mae architecture, built for multitask tasks.

Architecture

  • Architecture: mae
  • Scale: small
  • Attention: linear
  • Fusion strategy: tensor fusion
  • Task head: multitask
  • Activation: approx gelu
  • Normalization: batchnorm
  • Initialization: kaiming

Training

  • Optimizer: lamb
  • LR scheduler: linear warmup

Files

  • train.py — main artifact of this repository

License

See the license field above.