# bojone/attention

some attention implements

Repository: https://github.com/bojone/attention
Canonical: https://ross.abutalabs.com/products/attention
Language: Python
License Family: other
Last push: 2019-11-20T10:17:44+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-02T17:46:02.011165+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 3161, "days_push": 2478, "days_rel": null, "gap_med": null, "n_releases_24m": 0}
- flags: no_releases, no_license
- formula: round(0.45*activity + 0.35*rhythm + 0.20*longevity); archived -> min(score, 10)

## Adoption (not part of the score)
Stars 1448, forks 508 (observed 2026-08-28T04:04:45.542614+00:00)

## What it is
A small Python library providing implementations of the attention mechanism from 'Attention is All You Need' for TensorFlow/Keras. It is no longer actively updated, with users directed to bert4keras for newer versions.

## Use cases
- implement attention mechanism in keras
- understand how transformer attention works
- add attention layer to seq2seq model
- reproduce attention is all you need in tensorflow

## When to choose
- you need a minimal, readable attention implementation on old TensorFlow/Keras versions
- you want to study the math behind attention layers

## When to avoid
- you use modern TensorFlow 2.x or Keras versions
- you need maintained, production-ready transformer libraries

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, deep-learning
- domain: deep-learning, machine-learning
- platform: python
- tags: attention-mechanism, keras, tensorflow, transformers, natural-language-processing

## Member repositories
- bojone/attention (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:04:45.542614+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 2026-08-30T04:36:03.069765+00:00, confidence not recorded.
  - readme: https://github.com/bojone/attention (fetched 2026-08-28T04:04:45.542614+00:00, sha d0f256c21757)
- Data as of 2026-08-30T08:39:29.467469+00:00.