# bentrevett/pytorch-seq2seq

Tutorials on implementing a few sequence-to-sequence (seq2seq) models with PyTorch and TorchText.

Repository: https://github.com/bentrevett/pytorch-seq2seq
Canonical: https://ross.abutalabs.com/products/pytorch-seq2seq
Language: Jupyter Notebook
License: MIT
License Family: permissive
Topics: pytorch, seq2seq, sequence-to-sequence, tutorial, rnn, gru, lstm, torchtext, pytorch-tutorial, pytorch-implmention, encoder-decoder, encoder-decoder-model, neural-machine-translation, pytorch-seq2seq, attention, transformer, cnn-seq2seq, pytorch-implementation, pytorch-tutorials, pytorch-nlp
Last push: 2024-01-20T16:51:04+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": 2969, "days_push": 956, "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 5707, forks 1353 (observed 2026-08-28T04:09:28.156026+00:00)

## What it is
A collection of Jupyter notebook tutorials on implementing sequence-to-sequence (seq2seq) models in PyTorch, covering encoder-decoder RNNs, attention, and transformers, trained for German-to-English translation. It is an educational resource rather than a production library.

## Use cases
- learn how to implement seq2seq models in pytorch
- understand encoder-decoder architectures with attention
- tutorial on building a neural machine translation model
- implement lstm and gru encoder-decoder from scratch
- learn transformers for sequence-to-sequence tasks
- hands-on pytorch nlp tutorial notebooks

## When to choose
- you want to learn seq2seq concepts by implementing models step by step in PyTorch
- you need guided notebooks covering RNN, GRU, LSTM, attention, and transformer variants
- you are studying neural machine translation fundamentals

## When to avoid
- you need a production-ready seq2seq library or pretrained models
- you want maintained, up-to-date tooling (TorchText is deprecated)
- you need large-scale or multilingual translation beyond the tutorial's German-English example

## Facets
- artifact type: learning-resource
- maturity: maintenance
- function: machine-learning, nlp, deep-learning
- domain: deep-learning, tutorials
- platform: python
- tags: seq2seq, pytorch, encoder-decoder, attention, transformer, neural-machine-translation, jupyter-notebooks, torchtext, natural-language-processing

## Member repositories
- bentrevett/pytorch-seq2seq (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:09:28.156026+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 2026-08-29T17:53:32.850256+00:00, confidence not recorded.
  - readme: https://github.com/bentrevett/pytorch-seq2seq (fetched 2026-08-28T04:09:28.156026+00:00, sha 13c0f83311d1)
- Data as of 2026-08-30T08:39:29.467469+00:00.