jpacifico commited on
Commit
19c88d9
1 Parent(s): 8efee9a

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,40 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "<|/code|>": 32014,
3
+ "<|/data|>": 32033,
4
+ "<|/inst|>": 32037,
5
+ "<|/query|>": 32031,
6
+ "<|/sys|>": 32035,
7
+ "<|assistant_mask|>": 32017,
8
+ "<|assistant|>": 32001,
9
+ "<|calc|>": 32012,
10
+ "<|code|>": 32013,
11
+ "<|continue|>": 32009,
12
+ "<|data|>": 32032,
13
+ "<|diff_marker|>": 32025,
14
+ "<|disc_sep|>": 32029,
15
+ "<|disc_start|>": 32028,
16
+ "<|disc_thread|><|query|>": 32030,
17
+ "<|endoftext|>": 32000,
18
+ "<|end|>": 32007,
19
+ "<|fim_middle|>": 32021,
20
+ "<|fim_prefix|>": 32020,
21
+ "<|fim_suffix|>": 32022,
22
+ "<|function_call|>": 32005,
23
+ "<|function_list|>": 32011,
24
+ "<|function_output|>": 32003,
25
+ "<|ghissue|>": 32026,
26
+ "<|ghreview|>": 32027,
27
+ "<|inst|>": 32036,
28
+ "<|ipynb_marker|>": 32024,
29
+ "<|message|>": 32019,
30
+ "<|meta_start|>": 32023,
31
+ "<|raw|>": 32008,
32
+ "<|resource|>": 32016,
33
+ "<|start|>": 32018,
34
+ "<|step|>": 32002,
35
+ "<|summary|>": 32015,
36
+ "<|system|>": 32006,
37
+ "<|sys|>": 32034,
38
+ "<|tag|>": 32004,
39
+ "<|user|>": 32010
40
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,27 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|/inst|>"
4
+ ],
5
+ "bos_token": {
6
+ "content": "<s>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false
11
+ },
12
+ "eos_token": {
13
+ "content": "<|endoftext|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false
18
+ },
19
+ "pad_token": "<|endoftext|>",
20
+ "unk_token": {
21
+ "content": "<unk>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false
26
+ }
27
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer.model ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9e556afd44213b6bd1be2b850ebbbd98f5481437a8021afaf58ee7fb1818d347
3
+ size 499723
tokenizer_config.json ADDED
@@ -0,0 +1,348 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": true,
3
+ "add_eos_token": true,
4
+ "added_tokens_decoder": {
5
+ "0": {
6
+ "content": "<unk>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "1": {
14
+ "content": "<s>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "2": {
22
+ "content": "</s>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": true,
26
+ "single_word": false,
27
+ "special": false
28
+ },
29
+ "32000": {
30
+ "content": "<|endoftext|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "32001": {
38
+ "content": "<|assistant|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": true,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "32002": {
46
+ "content": "<|step|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": true,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "32003": {
54
+ "content": "<|function_output|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": true,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "32004": {
62
+ "content": "<|tag|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": true,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "32005": {
70
+ "content": "<|function_call|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": true,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "32006": {
78
+ "content": "<|system|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": true,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "32007": {
86
+ "content": "<|end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": true,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "32008": {
94
+ "content": "<|raw|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": true,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "32009": {
102
+ "content": "<|continue|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": true,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "32010": {
110
+ "content": "<|user|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": true,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "32011": {
118
+ "content": "<|function_list|>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": true,
122
+ "single_word": false,
123
+ "special": true
124
+ },
125
+ "32012": {
126
+ "content": "<|calc|>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": true,
130
+ "single_word": false,
131
+ "special": true
132
+ },
133
+ "32013": {
134
+ "content": "<|code|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": true,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "32014": {
142
+ "content": "<|/code|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": true,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "32015": {
150
+ "content": "<|summary|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": true,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "32016": {
158
+ "content": "<|resource|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": true,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "32017": {
166
+ "content": "<|assistant_mask|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": true,
170
+ "single_word": false,
171
+ "special": true
172
+ },
173
+ "32018": {
174
+ "content": "<|start|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": true,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "32019": {
182
+ "content": "<|message|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": true,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "32020": {
190
+ "content": "<|fim_prefix|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": true,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "32021": {
198
+ "content": "<|fim_middle|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": true,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "32022": {
206
+ "content": "<|fim_suffix|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": true,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "32023": {
214
+ "content": "<|meta_start|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": true,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "32024": {
222
+ "content": "<|ipynb_marker|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": true,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "32025": {
230
+ "content": "<|diff_marker|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": true,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "32026": {
238
+ "content": "<|ghissue|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": true,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "32027": {
246
+ "content": "<|ghreview|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": true,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "32028": {
254
+ "content": "<|disc_start|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": true,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "32029": {
262
+ "content": "<|disc_sep|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": true,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "32030": {
270
+ "content": "<|disc_thread|><|query|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": true,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "32031": {
278
+ "content": "<|/query|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": true,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "32032": {
286
+ "content": "<|data|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": true,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "32033": {
294
+ "content": "<|/data|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": true,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "32034": {
302
+ "content": "<|sys|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": true,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "32035": {
310
+ "content": "<|/sys|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": true,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "32036": {
318
+ "content": "<|inst|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": true,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "32037": {
326
+ "content": "<|/inst|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": true,
330
+ "single_word": false,
331
+ "special": true
332
+ }
333
+ },
334
+ "additional_special_tokens": [
335
+ "<|/inst|>"
336
+ ],
337
+ "bos_token": "<s>",
338
+ "chat_template": "{{ bos_token }}{% for message in messages %}{{'<|' + message['role'] + '|>' + '\n' + message['content'] + '<|end|>\n' }}{% endfor %}{% if add_generation_prompt %}{{ '<|assistant|>\n' }}{% else %}{{ eos_token }}{% endif %}",
339
+ "clean_up_tokenization_spaces": false,
340
+ "eos_token": "<|endoftext|>",
341
+ "model_max_length": 4096,
342
+ "pad_token": "<|endoftext|>",
343
+ "padding_side": "left",
344
+ "sp_model_kwargs": {},
345
+ "tokenizer_class": "LlamaTokenizer",
346
+ "unk_token": "<unk>",
347
+ "use_default_system_prompt": false
348
+ }