# jiachenzhu/DyT

Code release for DynamicTanh (DyT)

Repository: https://github.com/jiachenzhu/DyT
Canonical: https://ross.abutalabs.com/products/dyt
Language: Python
License: MIT
License Family: permissive
Last push: 2025-03-30T18:24:45+00:00

## Health v2 (maintenance only)
Score: 26/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 14, release rhythm 35, longevity 38
- inputs: {"age_days": 538, "days_push": 521, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1043, forks 87 (observed 2026-08-28T04:03:20.935228+00:00)

## What it is
Official PyTorch implementation of DynamicTanh (DyT), a learnable element-wise tanh operation that replaces normalization layers in Transformers. Released as research code accompanying the CVPR 2025 paper 'Transformers without Normalization', with training scripts for ViT and ConvNeXt on ImageNet-1K.

## Use cases
- replace layer normalization in transformers with dynamic tanh
- train ViT models without normalization layers
- reproduce CVPR 2025 DyT paper results on ImageNet
- experiment with normalization-free deep learning architectures
- apply DyT to ConvNeXt models
- compare LayerNorm vs DyT performance in vision transformers

## When to choose
- you want to replace normalization layers in a Transformer with a learnable tanh operation
- you are reproducing or extending the 'Transformers without Normalization' paper
- you are researching normalization-free deep learning architectures

## When to avoid
- you need a production-ready, pip-installable library with broad model support
- you are not working in PyTorch
- you need stable, well-maintained software rather than research code

## Facets
- artifact type: library
- maturity: active
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning, computer-vision
- platform: python
- tags: pytorch, transformers, normalization, research-code, cvpr-2025, dynamic-tanh, gpu

## Member repositories
- jiachenzhu/DyT (main) score 26

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:03:20.935228+00:00.
- Health v2: computed from the inputs above; adoption is never an input.
- Inferred fields (summary, facets, guidance): AI-extracted, prompt v1, taxonomy v1, on 2026-08-30T07:02:30.215738+00:00, confidence not recorded.
  - readme: https://github.com/jiachenzhu/DyT (fetched 2026-08-28T04:03:20.935228+00:00, sha 5c957bafc65c)
- Data as of 2026-08-30T08:39:29.467469+00:00.