# tmikolov/word2vec

Automatically exported from code.google.com/p/word2vec

Repository: https://github.com/tmikolov/word2vec
Canonical: https://ross.abutalabs.com/products/tmikolov-word2vec
Language: C
License: Apache-2.0
License Family: permissive
Last push: 2023-02-28T21:31:53+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": 4039, "days_push": 1282, "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 1592, forks 546 (observed 2026-08-28T04:05:08.764903+00:00)

## What it is
The original C implementation of word2vec, which trains word embeddings using the Continuous Bag-of-Words (CBOW) and Skip-gram neural network architectures. It includes command-line tools and demo scripts for training word vectors from a text corpus and exploring word similarity.

## Use cases
- train word embeddings from a text corpus
- compute distributed representations of words
- find semantically similar words
- run skip-gram or CBOW models
- generate word vectors for NLP pipelines

## When to choose
- you need the original, lightweight C implementation of word2vec
- you want to train word embeddings on your own corpus without heavy dependencies
- you need fast CPU-based training with hierarchical softmax or negative sampling

## When to avoid
- you need modern contextual embeddings like BERT or transformer models
- you want GPU acceleration or deep learning framework integration
- you need actively maintained features or extensive documentation

## Facets
- artifact type: library
- maturity: maintenance
- function: machine-learning, nlp, cli
- domain: machine-learning, developer-tools
- platform: cpp, c
- tags: word2vec, word-embeddings, cbow, skip-gram, vector-representations, natural-language-processing, linux, macos

## Member repositories
- tmikolov/word2vec (main) score 32

## Provenance
- Observed fields: from GitHub, fetched 2026-08-28T04:05:08.764903+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 2026-08-30T03:54:41.977473+00:00, confidence not recorded.
  - readme: https://github.com/tmikolov/word2vec (fetched 2026-08-28T04:05:08.764903+00:00, sha 3d4d38c72e77)
- Data as of 2026-08-30T08:39:29.467469+00:00.