Hugging Face's logo

Seastell
/
tutorial-model

Safetensors
collie
Model card Files
xet
 Community
Seastell commited on
Commit
de63e51
·
verified ·
1 Parent(s): accb80b

Upload folder using huggingface_hub

Browse files
Files changed (3) hide show
  1. special_tokens_map.json +4 -0
  2. tokenizer.json +239 -0
  3. tokenizer_config.json +26 -0
special_tokens_map.json ADDED
@@ -0,0 +1,4 @@
 
 
 
 
 
1
+ {
2
+ "bos_token": "[BOS]",
3
+ "pad_token": "[PAD]"
4
+ }
tokenizer.json ADDED
@@ -0,0 +1,239 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[BOS]",
18
+ "single_word": false,
19
+ "lstrip": false,
20
+ "rstrip": false,
21
+ "normalized": false,
22
+ "special": true
23
+ }
24
+ ],
25
+ "normalizer": null,
26
+ "pre_tokenizer": null,
27
+ "post_processor": null,
28
+ "decoder": {
29
+ "type": "Fuse"
30
+ },
31
+ "model": {
32
+ "type": "BPE",
33
+ "dropout": null,
34
+ "unk_token": null,
35
+ "continuing_subword_prefix": null,
36
+ "end_of_word_suffix": null,
37
+ "fuse_unk": false,
38
+ "byte_fallback": false,
39
+ "ignore_merges": false,
40
+ "vocab": {
41
+ "[PAD]": 0,
42
+ "[BOS]": 1,
43
+ " ": 2,
44
+ "!": 3,
45
+ "\"": 4,
46
+ "#": 5,
47
+ "$": 6,
48
+ "%": 7,
49
+ "&": 8,
50
+ "'": 9,
51
+ "(": 10,
52
+ ")": 11,
53
+ "*": 12,
54
+ "+": 13,
55
+ ",": 14,
56
+ "-": 15,
57
+ ".": 16,
58
+ "/": 17,
59
+ "0": 18,
60
+ "1": 19,
61
+ "2": 20,
62
+ "3": 21,
63
+ "4": 22,
64
+ "5": 23,
65
+ "6": 24,
66
+ "7": 25,
67
+ "8": 26,
68
+ "9": 27,
69
+ ":": 28,
70
+ ";": 29,
71
+ "<": 30,
72
+ "=": 31,
73
+ ">": 32,
74
+ "?": 33,
75
+ "0 ": 34,
76
+ "0 0 ": 35,
77
+ "0!": 36,
78
+ "/?": 37,
79
+ "0 0 0 0 ": 38,
80
+ "0\"": 39,
81
+ "/>": 40,
82
+ "0 /?": 41,
83
+ "0 0!": 42,
84
+ "0 0 0 0 0 0 0 0 ": 43,
85
+ "0 0 /?": 44,
86
+ "0%": 45,
87
+ "0 0 0!": 46,
88
+ "/;": 47,
89
+ "0#": 48,
90
+ "/=": 49,
91
+ "/3": 50,
92
+ "0-": 51,
93
+ "0 /?0!": 52,
94
+ "0 0 0 ": 53,
95
+ "0 0 0 0 0 0 0 0 0 0 0 ": 54,
96
+ "/?0!": 55,
97
+ "0 /": 56,
98
+ "0$": 57,
99
+ ",,": 58,
100
+ "34": 59,
101
+ "0 0 /?0!": 60,
102
+ "0 0 0 0 0 0 0 0 0 0 0 0 ": 61,
103
+ "0 0 0!0!": 62,
104
+ "0 />": 63,
105
+ "0 0 0!/?": 64,
106
+ "0 0!0!": 65
107
+ },
108
+ "merges": [
109
+ [
110
+ "0",
111
+ " "
112
+ ],
113
+ [
114
+ "0 ",
115
+ "0 "
116
+ ],
117
+ [
118
+ "0",
119
+ "!"
120
+ ],
121
+ [
122
+ "/",
123
+ "?"
124
+ ],
125
+ [
126
+ "0 0 ",
127
+ "0 0 "
128
+ ],
129
+ [
130
+ "0",
131
+ "\""
132
+ ],
133
+ [
134
+ "/",
135
+ ">"
136
+ ],
137
+ [
138
+ "0 ",
139
+ "/?"
140
+ ],
141
+ [
142
+ "0 ",
143
+ "0!"
144
+ ],
145
+ [
146
+ "0 0 0 0 ",
147
+ "0 0 0 0 "
148
+ ],
149
+ [
150
+ "0 0 ",
151
+ "/?"
152
+ ],
153
+ [
154
+ "0",
155
+ "%"
156
+ ],
157
+ [
158
+ "0 0 ",
159
+ "0!"
160
+ ],
161
+ [
162
+ "/",
163
+ ";"
164
+ ],
165
+ [
166
+ "0",
167
+ "#"
168
+ ],
169
+ [
170
+ "/",
171
+ "="
172
+ ],
173
+ [
174
+ "/",
175
+ "3"
176
+ ],
177
+ [
178
+ "0",
179
+ "-"
180
+ ],
181
+ [
182
+ "0 /?",
183
+ "0!"
184
+ ],
185
+ [
186
+ "0 0 ",
187
+ "0 "
188
+ ],
189
+ [
190
+ "0 0 0 0 0 0 0 0 ",
191
+ "0 0 0 "
192
+ ],
193
+ [
194
+ "/?",
195
+ "0!"
196
+ ],
197
+ [
198
+ "0 ",
199
+ "/"
200
+ ],
201
+ [
202
+ "0",
203
+ "$"
204
+ ],
205
+ [
206
+ ",",
207
+ ","
208
+ ],
209
+ [
210
+ "3",
211
+ "4"
212
+ ],
213
+ [
214
+ "0 0 /?",
215
+ "0!"
216
+ ],
217
+ [
218
+ "0 0 0 0 0 0 0 0 ",
219
+ "0 0 0 0 "
220
+ ],
221
+ [
222
+ "0 0 0!",
223
+ "0!"
224
+ ],
225
+ [
226
+ "0 ",
227
+ "/>"
228
+ ],
229
+ [
230
+ "0 0 0!",
231
+ "/?"
232
+ ],
233
+ [
234
+ "0 0!",
235
+ "0!"
236
+ ]
237
+ ]
238
+ }
239
+ }
tokenizer_config.json ADDED
@@ -0,0 +1,26 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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": "[BOS]",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ }
19
+ },
20
+ "bos_token": "[BOS]",
21
+ "clean_up_tokenization_spaces": false,
22
+ "extra_special_tokens": {},
23
+ "model_max_length": 1000000000000000019884624838656,
24
+ "pad_token": "[PAD]",
25
+ "tokenizer_class": "PreTrainedTokenizer"
26
+ }