English
word2vec
lbourdois commited on
Commit
1801925
1 Parent(s): 0c31ae4

Upload meta.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. meta.json +64 -0
meta.json ADDED
@@ -0,0 +1,64 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "algorithm": {
3
+ "command": null,
4
+ "id": 0,
5
+ "name": "Gensim Continuous Skipgram",
6
+ "tool": "Gensim",
7
+ "url": "https://github.com/RaRe-Technologies/gensim",
8
+ "version": "3.6"
9
+ },
10
+ "contents": [
11
+ {
12
+ "filename": "model.txt",
13
+ "format": "text"
14
+ },
15
+ {
16
+ "filename": "meta.json",
17
+ "format": "json"
18
+ }
19
+ ],
20
+ "corpus": [
21
+ {
22
+ "NER": false,
23
+ "case preserved": true,
24
+ "description": "English Wikipedia Dump of February 2017",
25
+ "id": 0,
26
+ "language": "eng",
27
+ "lemmatized": true,
28
+ "public": true,
29
+ "stop words removal": "NLTK",
30
+ "tagger": "Stanford Core NLP v. 3.6.0",
31
+ "tagset": null,
32
+ "tokens": 2252637050,
33
+ "tool": "Wikipedia Extractor",
34
+ "url": "https://dumps.wikimedia.org/"
35
+ },
36
+ {
37
+ "NER": false,
38
+ "case preserved": true,
39
+ "description": "Gigaword 5th Edition",
40
+ "id": 3,
41
+ "language": "eng",
42
+ "lemmatized": true,
43
+ "public": false,
44
+ "stop words removal": "NLTK",
45
+ "tagger": "Stanford Core NLP v. 3.6.0",
46
+ "tagset": null,
47
+ "tokens": 4815382730,
48
+ "tool": null,
49
+ "url": "https://catalog.ldc.upenn.edu/LDC2011T07"
50
+ }
51
+ ],
52
+ "creators": [
53
+ {
54
+ "email": "andreku@ifi.uio.no",
55
+ "name": "Andrey Kutuzov"
56
+ }
57
+ ],
58
+ "dimensions": 300,
59
+ "handle": "http://vectors.nlpl.eu/repository/20/17.zip",
60
+ "id": 17,
61
+ "iterations": 5,
62
+ "vocabulary size": 259882,
63
+ "window": 5
64
+ }