hama3 commited on
Commit
a16db97
1 Parent(s): 6b54f6b

Upload tokenizer

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ entity_vocab.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "<ent2>": 32771,
3
+ "<ent>": 32770
4
+ }
entity_vocab.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7b06f4585e52d018d7a4b19f1578313b5071c2bc049ee7085c59b668b27fab86
3
+ size 21684396
sentencepiece.bpe.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d8b73a5e054936c920cf5b7d1ec21ce9c281977078269963beb821c6c86fbff7
3
+ size 841889
special_tokens_map.json ADDED
@@ -0,0 +1,95 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<ent>",
5
+ "lstrip": false,
6
+ "normalized": true,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<ent2>",
12
+ "lstrip": false,
13
+ "normalized": true,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<ent>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<ent2>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<ent>",
33
+ "lstrip": false,
34
+ "normalized": true,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<ent2>",
40
+ "lstrip": false,
41
+ "normalized": true,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ }
45
+ ],
46
+ "bos_token": {
47
+ "content": "<s>",
48
+ "lstrip": false,
49
+ "normalized": false,
50
+ "rstrip": false,
51
+ "single_word": false
52
+ },
53
+ "cls_token": {
54
+ "content": "<s>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "eos_token": {
61
+ "content": "</s>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false
66
+ },
67
+ "mask_token": {
68
+ "content": "<mask>",
69
+ "lstrip": true,
70
+ "normalized": true,
71
+ "rstrip": false,
72
+ "single_word": false
73
+ },
74
+ "pad_token": {
75
+ "content": "<pad>",
76
+ "lstrip": false,
77
+ "normalized": false,
78
+ "rstrip": false,
79
+ "single_word": false
80
+ },
81
+ "sep_token": {
82
+ "content": "</s>",
83
+ "lstrip": false,
84
+ "normalized": false,
85
+ "rstrip": false,
86
+ "single_word": false
87
+ },
88
+ "unk_token": {
89
+ "content": "<unk>",
90
+ "lstrip": false,
91
+ "normalized": false,
92
+ "rstrip": false,
93
+ "single_word": false
94
+ }
95
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,104 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<s>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<pad>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "</s>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<unk>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "32769": {
36
+ "content": "<mask>",
37
+ "lstrip": true,
38
+ "normalized": true,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "32770": {
44
+ "content": "<ent>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "32771": {
52
+ "content": "<ent2>",
53
+ "lstrip": false,
54
+ "normalized": true,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ }
59
+ },
60
+ "additional_special_tokens": [
61
+ "<ent>",
62
+ "<ent2>",
63
+ "<ent>",
64
+ "<ent2>",
65
+ "<ent>",
66
+ "<ent2>"
67
+ ],
68
+ "bos_token": "<s>",
69
+ "clean_up_tokenization_spaces": true,
70
+ "cls_token": "<s>",
71
+ "entity_mask2_token": "[MASK2]",
72
+ "entity_mask_token": "[MASK]",
73
+ "entity_pad_token": "[PAD]",
74
+ "entity_token_1": {
75
+ "__type": "AddedToken",
76
+ "content": "<ent>",
77
+ "lstrip": false,
78
+ "normalized": true,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": false
82
+ },
83
+ "entity_token_2": {
84
+ "__type": "AddedToken",
85
+ "content": "<ent2>",
86
+ "lstrip": false,
87
+ "normalized": true,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": false
91
+ },
92
+ "entity_unk_token": "[UNK]",
93
+ "eos_token": "</s>",
94
+ "mask_token": "<mask>",
95
+ "max_entity_length": 32,
96
+ "max_mention_length": 30,
97
+ "model_max_length": 512,
98
+ "pad_token": "<pad>",
99
+ "sep_token": "</s>",
100
+ "sp_model_kwargs": {},
101
+ "task": null,
102
+ "tokenizer_class": "MLukeTokenizer",
103
+ "unk_token": "<unk>"
104
+ }