nielsr HF staff commited on
Commit
6456470
1 Parent(s): 9af2c77

Upload tokenizer

Browse files
added_tokens.json CHANGED
@@ -1 +1,4 @@
1
- {"<end-of-node>": 50266, "[empty-title]": 50265}
 
 
 
1
+ {
2
+ "<end-of-node>": 50266,
3
+ "[empty-title]": 50265
4
+ }
special_tokens_map.json CHANGED
@@ -1 +1,15 @@
1
- {"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos_token": "<s>",
3
+ "cls_token": "<s>",
4
+ "eos_token": "</s>",
5
+ "mask_token": {
6
+ "content": "<mask>",
7
+ "lstrip": true,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "pad_token": "<pad>",
13
+ "sep_token": "</s>",
14
+ "unk_token": "<unk>"
15
+ }
tokenizer.json CHANGED
The diff for this file is too large to render. See raw diff
tokenizer_config.json CHANGED
@@ -1,17 +1,288 @@
1
  {
2
- "unk_token": "<unk>",
3
- "bos_token": "<s>",
4
- "eos_token": "</s>",
5
- "add_prefix_space": false,
6
- "errors": "replace",
7
- "sep_token": "</s>",
8
- "cls_token": "<s>",
9
- "pad_token": "<pad>",
10
- "mask_token": "<mask>",
11
- "model_max_length": 512,
12
- "from_slow": true,
13
- "special_tokens_map_file": null,
14
- "name_or_path": "markuplm-base",
15
- "tokenizer_class": "MarkupLMTokenizer",
16
- "tags_dict": {"a": 0, "abbr": 1, "acronym": 2, "address": 3, "altGlyph": 4, "altGlyphDef": 5, "altGlyphItem": 6, "animate": 7, "animateColor": 8, "animateMotion": 9, "animateTransform": 10, "applet": 11, "area": 12, "article": 13, "aside": 14, "audio": 15, "b": 16, "base": 17, "basefont": 18, "bdi": 19, "bdo": 20, "bgsound": 21, "big": 22, "blink": 23, "blockquote": 24, "body": 25, "br": 26, "button": 27, "canvas": 28, "caption": 29, "center": 30, "circle": 31, "cite": 32, "clipPath": 33, "code": 34, "col": 35, "colgroup": 36, "color-profile": 37, "content": 38, "cursor": 39, "data": 40, "datalist": 41, "dd": 42, "defs": 43, "del": 44, "desc": 45, "details": 46, "dfn": 47, "dialog": 48, "dir": 49, "div": 50, "dl": 51, "dt": 52, "ellipse": 53, "em": 54, "embed": 55, "feBlend": 56, "feColorMatrix": 57, "feComponentTransfer": 58, "feComposite": 59, "feConvolveMatrix": 60, "feDiffuseLighting": 61, "feDisplacementMap": 62, "feDistantLight": 63, "feFlood": 64, "feFuncA": 65, "feFuncB": 66, "feFuncG": 67, "feFuncR": 68, "feGaussianBlur": 69, "feImage": 70, "feMerge": 71, "feMergeNode": 72, "feMorphology": 73, "feOffset": 74, "fePointLight": 75, "feSpecularLighting": 76, "feSpotLight": 77, "feTile": 78, "feTurbulence": 79, "fieldset": 80, "figcaption": 81, "figure": 82, "filter": 83, "font-face-format": 84, "font-face-name": 85, "font-face-src": 86, "font-face-uri": 87, "font-face": 88, "font": 89, "footer": 90, "foreignObject": 91, "form": 92, "frame": 93, "frameset": 94, "g": 95, "glyph": 96, "glyphRef": 97, "h1": 98, "h2": 99, "h3": 100, "h4": 101, "h5": 102, "h6": 103, "head": 104, "header": 105, "hgroup": 106, "hkern": 107, "hr": 108, "html": 109, "i": 110, "iframe": 111, "image": 112, "img": 113, "input": 114, "ins": 115, "kbd": 116, "keygen": 117, "label": 118, "legend": 119, "li": 120, "line": 121, "linearGradient": 122, "link": 123, "main": 124, "map": 125, "mark": 126, "marker": 127, "marquee": 128, "mask": 129, "math": 130, "menu": 131, "menuitem": 132, "meta": 133, "metadata": 134, "meter": 135, "missing-glyph": 136, "mpath": 137, "nav": 138, "nobr": 139, "noembed": 140, "noframes": 141, "noscript": 142, "object": 143, "ol": 144, "optgroup": 145, "option": 146, "output": 147, "p": 148, "param": 149, "path": 150, "pattern": 151, "picture": 152, "plaintext": 153, "polygon": 154, "polyline": 155, "portal": 156, "pre": 157, "progress": 158, "q": 159, "radialGradient": 160, "rb": 161, "rect": 162, "rp": 163, "rt": 164, "rtc": 165, "ruby": 166, "s": 167, "samp": 168, "script": 169, "section": 170, "select": 171, "set": 172, "shadow": 173, "slot": 174, "small": 175, "source": 176, "spacer": 177, "span": 178, "stop": 179, "strike": 180, "strong": 181, "style": 182, "sub": 183, "summary": 184, "sup": 185, "svg": 186, "switch": 187, "symbol": 188, "table": 189, "tbody": 190, "td": 191, "template": 192, "text": 193, "textPath": 194, "textarea": 195, "tfoot": 196, "th": 197, "thead": 198, "time": 199, "title": 200, "tr": 201, "track": 202, "tref": 203, "tspan": 204, "tt": 205, "u": 206, "ul": 207, "use": 208, "var": 209, "video": 210, "view": 211, "vkern": 212, "wbr": 213, "xmp": 214}
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
17
  }
1
  {
2
+ "add_prefix_space": false,
3
+ "bos_token": {
4
+ "__type": "AddedToken",
5
+ "content": "<s>",
6
+ "lstrip": false,
7
+ "normalized": true,
8
+ "rstrip": false,
9
+ "single_word": false
10
+ },
11
+ "cls_token": {
12
+ "__type": "AddedToken",
13
+ "content": "<s>",
14
+ "lstrip": false,
15
+ "normalized": true,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "eos_token": {
20
+ "__type": "AddedToken",
21
+ "content": "</s>",
22
+ "lstrip": false,
23
+ "normalized": true,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ },
27
+ "errors": "replace",
28
+ "from_slow": true,
29
+ "mask_token": {
30
+ "__type": "AddedToken",
31
+ "content": "<mask>",
32
+ "lstrip": true,
33
+ "normalized": true,
34
+ "rstrip": false,
35
+ "single_word": false
36
+ },
37
+ "max_depth": 50,
38
+ "max_width": 1000,
39
+ "model_max_length": 512,
40
+ "name_or_path": "microsoft/markuplm-base",
41
+ "only_label_first_subword": true,
42
+ "pad_token": {
43
+ "__type": "AddedToken",
44
+ "content": "<pad>",
45
+ "lstrip": false,
46
+ "normalized": true,
47
+ "rstrip": false,
48
+ "single_word": false
49
+ },
50
+ "pad_token_label": -100,
51
+ "pad_width": 1001,
52
+ "sep_token": {
53
+ "__type": "AddedToken",
54
+ "content": "</s>",
55
+ "lstrip": false,
56
+ "normalized": true,
57
+ "rstrip": false,
58
+ "single_word": false
59
+ },
60
+ "special_tokens_map_file": null,
61
+ "tags_dict": {
62
+ "a": 0,
63
+ "abbr": 1,
64
+ "acronym": 2,
65
+ "address": 3,
66
+ "altGlyph": 4,
67
+ "altGlyphDef": 5,
68
+ "altGlyphItem": 6,
69
+ "animate": 7,
70
+ "animateColor": 8,
71
+ "animateMotion": 9,
72
+ "animateTransform": 10,
73
+ "applet": 11,
74
+ "area": 12,
75
+ "article": 13,
76
+ "aside": 14,
77
+ "audio": 15,
78
+ "b": 16,
79
+ "base": 17,
80
+ "basefont": 18,
81
+ "bdi": 19,
82
+ "bdo": 20,
83
+ "bgsound": 21,
84
+ "big": 22,
85
+ "blink": 23,
86
+ "blockquote": 24,
87
+ "body": 25,
88
+ "br": 26,
89
+ "button": 27,
90
+ "canvas": 28,
91
+ "caption": 29,
92
+ "center": 30,
93
+ "circle": 31,
94
+ "cite": 32,
95
+ "clipPath": 33,
96
+ "code": 34,
97
+ "col": 35,
98
+ "colgroup": 36,
99
+ "color-profile": 37,
100
+ "content": 38,
101
+ "cursor": 39,
102
+ "data": 40,
103
+ "datalist": 41,
104
+ "dd": 42,
105
+ "defs": 43,
106
+ "del": 44,
107
+ "desc": 45,
108
+ "details": 46,
109
+ "dfn": 47,
110
+ "dialog": 48,
111
+ "dir": 49,
112
+ "div": 50,
113
+ "dl": 51,
114
+ "dt": 52,
115
+ "ellipse": 53,
116
+ "em": 54,
117
+ "embed": 55,
118
+ "feBlend": 56,
119
+ "feColorMatrix": 57,
120
+ "feComponentTransfer": 58,
121
+ "feComposite": 59,
122
+ "feConvolveMatrix": 60,
123
+ "feDiffuseLighting": 61,
124
+ "feDisplacementMap": 62,
125
+ "feDistantLight": 63,
126
+ "feFlood": 64,
127
+ "feFuncA": 65,
128
+ "feFuncB": 66,
129
+ "feFuncG": 67,
130
+ "feFuncR": 68,
131
+ "feGaussianBlur": 69,
132
+ "feImage": 70,
133
+ "feMerge": 71,
134
+ "feMergeNode": 72,
135
+ "feMorphology": 73,
136
+ "feOffset": 74,
137
+ "fePointLight": 75,
138
+ "feSpecularLighting": 76,
139
+ "feSpotLight": 77,
140
+ "feTile": 78,
141
+ "feTurbulence": 79,
142
+ "fieldset": 80,
143
+ "figcaption": 81,
144
+ "figure": 82,
145
+ "filter": 83,
146
+ "font": 89,
147
+ "font-face": 88,
148
+ "font-face-format": 84,
149
+ "font-face-name": 85,
150
+ "font-face-src": 86,
151
+ "font-face-uri": 87,
152
+ "footer": 90,
153
+ "foreignObject": 91,
154
+ "form": 92,
155
+ "frame": 93,
156
+ "frameset": 94,
157
+ "g": 95,
158
+ "glyph": 96,
159
+ "glyphRef": 97,
160
+ "h1": 98,
161
+ "h2": 99,
162
+ "h3": 100,
163
+ "h4": 101,
164
+ "h5": 102,
165
+ "h6": 103,
166
+ "head": 104,
167
+ "header": 105,
168
+ "hgroup": 106,
169
+ "hkern": 107,
170
+ "hr": 108,
171
+ "html": 109,
172
+ "i": 110,
173
+ "iframe": 111,
174
+ "image": 112,
175
+ "img": 113,
176
+ "input": 114,
177
+ "ins": 115,
178
+ "kbd": 116,
179
+ "keygen": 117,
180
+ "label": 118,
181
+ "legend": 119,
182
+ "li": 120,
183
+ "line": 121,
184
+ "linearGradient": 122,
185
+ "link": 123,
186
+ "main": 124,
187
+ "map": 125,
188
+ "mark": 126,
189
+ "marker": 127,
190
+ "marquee": 128,
191
+ "mask": 129,
192
+ "math": 130,
193
+ "menu": 131,
194
+ "menuitem": 132,
195
+ "meta": 133,
196
+ "metadata": 134,
197
+ "meter": 135,
198
+ "missing-glyph": 136,
199
+ "mpath": 137,
200
+ "nav": 138,
201
+ "nobr": 139,
202
+ "noembed": 140,
203
+ "noframes": 141,
204
+ "noscript": 142,
205
+ "object": 143,
206
+ "ol": 144,
207
+ "optgroup": 145,
208
+ "option": 146,
209
+ "output": 147,
210
+ "p": 148,
211
+ "param": 149,
212
+ "path": 150,
213
+ "pattern": 151,
214
+ "picture": 152,
215
+ "plaintext": 153,
216
+ "polygon": 154,
217
+ "polyline": 155,
218
+ "portal": 156,
219
+ "pre": 157,
220
+ "progress": 158,
221
+ "q": 159,
222
+ "radialGradient": 160,
223
+ "rb": 161,
224
+ "rect": 162,
225
+ "rp": 163,
226
+ "rt": 164,
227
+ "rtc": 165,
228
+ "ruby": 166,
229
+ "s": 167,
230
+ "samp": 168,
231
+ "script": 169,
232
+ "section": 170,
233
+ "select": 171,
234
+ "set": 172,
235
+ "shadow": 173,
236
+ "slot": 174,
237
+ "small": 175,
238
+ "source": 176,
239
+ "spacer": 177,
240
+ "span": 178,
241
+ "stop": 179,
242
+ "strike": 180,
243
+ "strong": 181,
244
+ "style": 182,
245
+ "sub": 183,
246
+ "summary": 184,
247
+ "sup": 185,
248
+ "svg": 186,
249
+ "switch": 187,
250
+ "symbol": 188,
251
+ "table": 189,
252
+ "tbody": 190,
253
+ "td": 191,
254
+ "template": 192,
255
+ "text": 193,
256
+ "textPath": 194,
257
+ "textarea": 195,
258
+ "tfoot": 196,
259
+ "th": 197,
260
+ "thead": 198,
261
+ "time": 199,
262
+ "title": 200,
263
+ "tr": 201,
264
+ "track": 202,
265
+ "tref": 203,
266
+ "tspan": 204,
267
+ "tt": 205,
268
+ "u": 206,
269
+ "ul": 207,
270
+ "use": 208,
271
+ "var": 209,
272
+ "video": 210,
273
+ "view": 211,
274
+ "vkern": 212,
275
+ "wbr": 213,
276
+ "xmp": 214
277
+ },
278
+ "tokenizer_class": "MarkupLMTokenizer",
279
+ "trim_offsets": false,
280
+ "unk_token": {
281
+ "__type": "AddedToken",
282
+ "content": "<unk>",
283
+ "lstrip": false,
284
+ "normalized": true,
285
+ "rstrip": false,
286
+ "single_word": false
287
+ }
288
  }