austindavis commited on
Commit
e685e45
·
verified ·
1 Parent(s): eaf08b5

Upload tokenizer files

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +6 -0
  2. tokenizer.json +181 -0
  3. tokenizer_config.json +43 -0
special_tokens_map.json ADDED
@@ -0,0 +1,6 @@
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<|startoftext|>",
3
+ "eos_token": "<|endoftext|>",
4
+ "pad_token": "<|pad|>",
5
+ "unk_token": "<|unknown|>"
6
+ }
tokenizer.json ADDED
@@ -0,0 +1,181 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "version": "1.0",
3
+ "truncation": null,
4
+ "padding": null,
5
+ "added_tokens": [
6
+ {
7
+ "id": 0,
8
+ "content": "<|pad|>",
9
+ "single_word": false,
10
+ "lstrip": false,
11
+ "rstrip": false,
12
+ "normalized": false,
13
+ "special": true
14
+ },
15
+ {
16
+ "id": 1,
17
+ "content": "<|startoftext|>",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ },
24
+ {
25
+ "id": 2,
26
+ "content": "<|endoftext|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ {
34
+ "id": 3,
35
+ "content": "<|unknown|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ }
42
+ ],
43
+ "normalizer": null,
44
+ "pre_tokenizer": {
45
+ "type": "Sequence",
46
+ "pretokenizers": [
47
+ {
48
+ "type": "Whitespace"
49
+ },
50
+ {
51
+ "type": "Split",
52
+ "pattern": {
53
+ "Regex": "\\d|[QBRN]"
54
+ },
55
+ "behavior": "MergedWithPrevious",
56
+ "invert": false
57
+ }
58
+ ]
59
+ },
60
+ "post_processor": {
61
+ "type": "TemplateProcessing",
62
+ "single": [
63
+ {
64
+ "SpecialToken": {
65
+ "id": "<|startoftext|>",
66
+ "type_id": 0
67
+ }
68
+ },
69
+ {
70
+ "Sequence": {
71
+ "id": "A",
72
+ "type_id": 0
73
+ }
74
+ }
75
+ ],
76
+ "pair": [
77
+ {
78
+ "Sequence": {
79
+ "id": "A",
80
+ "type_id": 0
81
+ }
82
+ },
83
+ {
84
+ "Sequence": {
85
+ "id": "B",
86
+ "type_id": 1
87
+ }
88
+ }
89
+ ],
90
+ "special_tokens": {
91
+ "<|startoftext|>": {
92
+ "id": "<|startoftext|>",
93
+ "ids": [
94
+ 1
95
+ ],
96
+ "tokens": [
97
+ "<|startoftext|>"
98
+ ]
99
+ }
100
+ }
101
+ },
102
+ "decoder": null,
103
+ "model": {
104
+ "type": "WordLevel",
105
+ "vocab": {
106
+ "<|pad|>": 0,
107
+ "<|startoftext|>": 1,
108
+ "<|endoftext|>": 2,
109
+ "<|unknown|>": 3,
110
+ "a1": 4,
111
+ "b1": 5,
112
+ "c1": 6,
113
+ "d1": 7,
114
+ "e1": 8,
115
+ "f1": 9,
116
+ "g1": 10,
117
+ "h1": 11,
118
+ "a2": 12,
119
+ "b2": 13,
120
+ "c2": 14,
121
+ "d2": 15,
122
+ "e2": 16,
123
+ "f2": 17,
124
+ "g2": 18,
125
+ "h2": 19,
126
+ "a3": 20,
127
+ "b3": 21,
128
+ "c3": 22,
129
+ "d3": 23,
130
+ "e3": 24,
131
+ "f3": 25,
132
+ "g3": 26,
133
+ "h3": 27,
134
+ "a4": 28,
135
+ "b4": 29,
136
+ "c4": 30,
137
+ "d4": 31,
138
+ "e4": 32,
139
+ "f4": 33,
140
+ "g4": 34,
141
+ "h4": 35,
142
+ "a5": 36,
143
+ "b5": 37,
144
+ "c5": 38,
145
+ "d5": 39,
146
+ "e5": 40,
147
+ "f5": 41,
148
+ "g5": 42,
149
+ "h5": 43,
150
+ "a6": 44,
151
+ "b6": 45,
152
+ "c6": 46,
153
+ "d6": 47,
154
+ "e6": 48,
155
+ "f6": 49,
156
+ "g6": 50,
157
+ "h6": 51,
158
+ "a7": 52,
159
+ "b7": 53,
160
+ "c7": 54,
161
+ "d7": 55,
162
+ "e7": 56,
163
+ "f7": 57,
164
+ "g7": 58,
165
+ "h7": 59,
166
+ "a8": 60,
167
+ "b8": 61,
168
+ "c8": 62,
169
+ "d8": 63,
170
+ "e8": 64,
171
+ "f8": 65,
172
+ "g8": 66,
173
+ "h8": 67,
174
+ "Q": 68,
175
+ "R": 69,
176
+ "B": 70,
177
+ "N": 71
178
+ },
179
+ "unk_token": "<|unknown|>"
180
+ }
181
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,43 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "0": {
4
+ "content": "<|pad|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "1": {
12
+ "content": "<|startoftext|>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "2": {
20
+ "content": "<|endoftext|>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "3": {
28
+ "content": "<|unknown|>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ }
35
+ },
36
+ "bos_token": "<|startoftext|>",
37
+ "clean_up_tokenization_spaces": false,
38
+ "eos_token": "<|endoftext|>",
39
+ "model_max_length": 1024,
40
+ "pad_token": "<|pad|>",
41
+ "tokenizer_class": "UciTileTokenizer",
42
+ "unk_token": "<|unknown|>"
43
+ }