Polish
word2vec
nlpl_208 / meta.json
lbourdois's picture
Upload meta.json with huggingface_hub
ff957a9
raw
history blame
1.34 kB
{
"algorithm": {
"command": null,
"id": 0,
"name": "Gensim Continuous Skipgram",
"tool": "Gensim",
"url": "https://github.com/RaRe-Technologies/gensim",
"version": "3.8.1"
},
"contents": [
{
"filename": "model.txt",
"format": "text"
},
{
"filename": "model.bin",
"format": "data"
},
{
"filename": "meta.json",
"format": "json"
}
],
"corpus": [
{
"NER": false,
"case preserved": true,
"description": "Polish CommonCrawl Dump of December 2019",
"id": 117,
"language": "pol",
"lemmatized": false,
"public": true,
"stop words removal": null,
"tagger": null,
"tagset": null,
"tokens": 32565035188,
"tool": "http://dx.doi.org/10.15439/2017F432",
"url": "https://commoncrawl.org/"
}
],
"creators": [
{
"email": "kwolk@pja.edu.pl",
"name": "Krzysztof Wolk"
}
],
"dimensions": 100,
"handle": "http://vectors.nlpl.eu/repository/20/208.zip",
"id": 208,
"iterations": 5,
"vocabulary size": 35193029,
"window": 5
}