English
word2vec
nlpl_21 / meta.json
lbourdois's picture
Upload meta.json with huggingface_hub
a0c10f5
{
"algorithm": {
"command": null,
"id": 2,
"name": "fastText Skipgram",
"tool": "fastText",
"url": "https://github.com/facebookresearch/fastText",
"version": null
},
"contents": [
{
"filename": "model.txt",
"format": "text"
},
{
"filename": "parameters.bin",
"format": "binary"
},
{
"filename": "meta.json",
"format": "json"
}
],
"corpus": [
{
"NER": false,
"case preserved": true,
"description": "English Wikipedia Dump of February 2017",
"id": 0,
"language": "eng",
"lemmatized": true,
"public": true,
"stop words removal": "NLTK",
"tagger": "Stanford Core NLP v. 3.6.0",
"tagset": null,
"tokens": 2252637050,
"tool": "Wikipedia Extractor",
"url": "https://dumps.wikimedia.org/"
},
{
"NER": false,
"case preserved": true,
"description": "Gigaword 5th Edition",
"id": 3,
"language": "eng",
"lemmatized": true,
"public": false,
"stop words removal": "NLTK",
"tagger": "Stanford Core NLP v. 3.6.0",
"tagset": null,
"tokens": 4815382730,
"tool": null,
"url": "https://catalog.ldc.upenn.edu/LDC2011T07"
}
],
"creators": [
{
"email": "andreku@ifi.uio.no",
"name": "Andrey Kutuzov"
}
],
"dimensions": 300,
"handle": "http://vectors.nlpl.eu/repository/20/21.zip",
"id": 21,
"iterations": 5,
"vocabulary size": 260073,
"window": 5
}