# ryankiros/skip-thoughts

Sent2Vec encoder and training code from the paper "Skip-Thought Vectors"

Repository: https://github.com/ryankiros/skip-thoughts
Canonical: https://ross.abutalabs.com/products/skip-thoughts
Language: Python
License Family: other
Last push: 2020-06-09T15:12:51+00:00

## Health v2 (maintenance only)
Score: 32/100 (v2, computed 2026-09-03T02:20:16.233290+00:00)
- activity 0, release rhythm 35, longevity 100
- inputs: {"age_days": 4085, "days_push": 2276, "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 2047, forks 531 (observed 2026-08-28T04:06:08.898779+00:00)

## What it is
A Python implementation of the Skip-Thought Vectors paper, providing a sent2vec encoder that maps sentences to fixed 4800-dimensional vectors. It includes training code and pretrained model files built on Theano.

## Use cases
- encode sentences into fixed-length vectors
- compute semantic similarity between sentences
- extract sentence features for classification tasks
- reproduce skip-thought vector experiments
- train sentence embedding models

## When to choose
- you need to reproduce the Skip-Thought Vectors paper results
- you specifically need the original skip-thought pretrained embeddings for research

## When to avoid
- you need a maintained sentence embedding library
- you cannot use Python 2.7 and Theano 0.7
- you want modern transformer-based sentence embeddings

## Facets
- artifact type: library
- maturity: abandoned
- function: machine-learning, nlp
- domain: machine-learning, deep-learning
- platform: python
- tags: sentence-embeddings, skip-thoughts, theano, sent2vec, research-code, embedding, natural-language-processing

## Member repositories
- ryankiros/skip-thoughts (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:06:08.898779+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 2026-08-30T02:57:58.713454+00:00, confidence not recorded.
  - readme: https://github.com/ryankiros/skip-thoughts (fetched 2026-08-28T04:06:08.898779+00:00, sha 154e01e1002a)
- Data as of 2026-08-30T08:39:29.467469+00:00.