{
  "lang":"fa",
  "name":"floret_full_wiki",
  "version":"0.1.0",
  "description":"Persian floret static vector table: 50,000 rows x 300 dimensions, floret mode, minn=maxn=5, hash_count=2, trained with floret-torch on the full Persian Wikipedia dump. Vectors only, no pipeline components. Same table size as fa_floret_400k over a larger corpus; the fa_*_news_lg tier uses the 200,000-row fa_floret_wiki_200k instead.",
  "author":"Kiyarash Fazeli",
  "email":"kiyarash@nlogn.ir",
  "url":"https://github.com/Fazel94/spacy-persian",
  "license":"CC BY-SA 4.0",
  "sources":[
    {
      "name":"fa_floret static vectors (50k rows x 300d, floret mode, full Persian Wikipedia dump, trained with floret-torch)",
      "url":"https://github.com/Fazel94/spacy-persian",
      "author":"Kiyarash Fazeli",
      "license":"CC BY-SA 4.0"
    },
    {
      "name":"Persian Wikipedia dump (fawiki), the text the vector table is trained on",
      "url":"https://dumps.wikimedia.org/fawiki/",
      "author":"Wikipedia contributors",
      "license":"CC BY-SA 4.0"
    }
  ],
  "spacy_version":">=3.8.15,<3.9.0",
  "spacy_git_version":"f69c32f",
  "vectors":{
    "width":300,
    "vectors":50000,
    "keys":-1,
    "name":"floret"
  },
  "labels":{

  },
  "pipeline":[

  ],
  "components":[

  ],
  "disabled":[

  ],
  "requirements":[
    "spacy>=3.8.15,<3.9.0",
    "spacy>=3.8.15,<3.9.0"
  ],
  "vectors_training":{
    "corpus":"full Persian Wikipedia (`fawiki`) dump, extracted with WikiExtractor `--no-templates`, sentence-tokenized with spaCy `blank(\"fa\")`",
    "minn":5,
    "maxn":5,
    "hash_count":2,
    "min_count":20,
    "tool":"[floret-torch](https://github.com/Fazel94/floret-torch) (GPU port of [explosion/floret](https://github.com/explosion/floret)), cbow, on a Colab T4",
    "dump_date":"not pinned: the run used `wikipedia_date: latest`"
  }
}