# sherjilozair/char-rnn-tensorflow

Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

Repository: https://github.com/sherjilozair/char-rnn-tensorflow
Canonical: https://ross.abutalabs.com/products/char-rnn-tensorflow
Language: Python
License: MIT
License Family: permissive
Last push: 2020-12-24T06:52:01+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": 3932, "days_push": 2078, "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 2659, forks 944 (observed 2026-08-28T04:07:07.442467+00:00)

## What it is
A Python/TensorFlow implementation of multi-layer recurrent neural networks (LSTM) for character-level language modeling, inspired by Andrej Karpathy's char-rnn. It includes training and sampling scripts that work on any plain-text corpus.

## Use cases
- train a character-level language model on plain text
- generate text in the style of a corpus like Shakespeare
- experiment with LSTM hyperparameters like rnn_size and dropout
- visualize RNN training progress with TensorBoard
- resume interrupted training from a checkpoint

## When to choose
- you want a minimal, readable char-RNN implementation for learning or research
- you need to train a text-generation model on a custom plain-text dataset
- you are reproducing classic char-rnn experiments in TensorFlow

## When to avoid
- you need modern tooling — it requires TensorFlow 1.0 and is unmaintained
- you want transformer-based or production-grade language models
- you need GPU sampling during training or recent framework support

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, deep-learning, nlp
- domain: machine-learning, deep-learning
- platform: python, windows
- tags: char-rnn, lstm, tensorflow, language-model, text-generation, character-level, natural-language-processing, linux, macos

## Member repositories
- sherjilozair/char-rnn-tensorflow (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:07:07.442467+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 2026-08-30T02:18:25.287552+00:00, confidence not recorded.
  - readme: https://github.com/sherjilozair/char-rnn-tensorflow (fetched 2026-08-28T04:07:07.442467+00:00, sha 66358057db56)
- Data as of 2026-08-30T08:39:29.467469+00:00.