English
word2vec
lbourdois commited on
Commit
a0c10f5
1 Parent(s): 60c4f65

Upload meta.json with huggingface_hub

Browse files
Files changed (1) hide show
  1. meta.json +68 -0
meta.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "algorithm": {
3
+ "command": null,
4
+ "id": 2,
5
+ "name": "fastText Skipgram",
6
+ "tool": "fastText",
7
+ "url": "https://github.com/facebookresearch/fastText",
8
+ "version": null
9
+ },
10
+ "contents": [
11
+ {
12
+ "filename": "model.txt",
13
+ "format": "text"
14
+ },
15
+ {
16
+ "filename": "parameters.bin",
17
+ "format": "binary"
18
+ },
19
+ {
20
+ "filename": "meta.json",
21
+ "format": "json"
22
+ }
23
+ ],
24
+ "corpus": [
25
+ {
26
+ "NER": false,
27
+ "case preserved": true,
28
+ "description": "English Wikipedia Dump of February 2017",
29
+ "id": 0,
30
+ "language": "eng",
31
+ "lemmatized": true,
32
+ "public": true,
33
+ "stop words removal": "NLTK",
34
+ "tagger": "Stanford Core NLP v. 3.6.0",
35
+ "tagset": null,
36
+ "tokens": 2252637050,
37
+ "tool": "Wikipedia Extractor",
38
+ "url": "https://dumps.wikimedia.org/"
39
+ },
40
+ {
41
+ "NER": false,
42
+ "case preserved": true,
43
+ "description": "Gigaword 5th Edition",
44
+ "id": 3,
45
+ "language": "eng",
46
+ "lemmatized": true,
47
+ "public": false,
48
+ "stop words removal": "NLTK",
49
+ "tagger": "Stanford Core NLP v. 3.6.0",
50
+ "tagset": null,
51
+ "tokens": 4815382730,
52
+ "tool": null,
53
+ "url": "https://catalog.ldc.upenn.edu/LDC2011T07"
54
+ }
55
+ ],
56
+ "creators": [
57
+ {
58
+ "email": "andreku@ifi.uio.no",
59
+ "name": "Andrey Kutuzov"
60
+ }
61
+ ],
62
+ "dimensions": 300,
63
+ "handle": "http://vectors.nlpl.eu/repository/20/21.zip",
64
+ "id": 21,
65
+ "iterations": 5,
66
+ "vocabulary size": 260073,
67
+ "window": 5
68
+ }