ChibuUkachi commited on
Commit
b610afe
·
1 Parent(s): 87d4068

add tokenizer json files

Browse files
Files changed (3) hide show
  1. tokenizer.json +0 -0
  2. tokenizer_config.json +495 -0
  3. vocab.json +0 -0
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,495 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "added_tokens_decoder": {
3
+ "200000": {
4
+ "content": "]!p~[",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false,
9
+ "special": true
10
+ },
11
+ "200001": {
12
+ "content": "<fim_prefix>",
13
+ "lstrip": false,
14
+ "normalized": false,
15
+ "rstrip": false,
16
+ "single_word": false,
17
+ "special": true
18
+ },
19
+ "200002": {
20
+ "content": "<fim_middle>",
21
+ "lstrip": false,
22
+ "normalized": false,
23
+ "rstrip": false,
24
+ "single_word": false,
25
+ "special": true
26
+ },
27
+ "200003": {
28
+ "content": "<fim_suffix>",
29
+ "lstrip": false,
30
+ "normalized": false,
31
+ "rstrip": false,
32
+ "single_word": false,
33
+ "special": true
34
+ },
35
+ "200004": {
36
+ "content": "<fim_pad>",
37
+ "lstrip": false,
38
+ "normalized": false,
39
+ "rstrip": false,
40
+ "single_word": false,
41
+ "special": true
42
+ },
43
+ "200005": {
44
+ "content": "<reponame>",
45
+ "lstrip": false,
46
+ "normalized": false,
47
+ "rstrip": false,
48
+ "single_word": false,
49
+ "special": true
50
+ },
51
+ "200006": {
52
+ "content": "<filename>",
53
+ "lstrip": false,
54
+ "normalized": false,
55
+ "rstrip": false,
56
+ "single_word": false,
57
+ "special": true
58
+ },
59
+ "200007": {
60
+ "content": "<gh_stars>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false,
65
+ "special": true
66
+ },
67
+ "200008": {
68
+ "content": "<issue_start>",
69
+ "lstrip": false,
70
+ "normalized": false,
71
+ "rstrip": false,
72
+ "single_word": false,
73
+ "special": true
74
+ },
75
+ "200009": {
76
+ "content": "<issue_comment>",
77
+ "lstrip": false,
78
+ "normalized": false,
79
+ "rstrip": false,
80
+ "single_word": false,
81
+ "special": true
82
+ },
83
+ "200010": {
84
+ "content": "<issue_closed>",
85
+ "lstrip": false,
86
+ "normalized": false,
87
+ "rstrip": false,
88
+ "single_word": false,
89
+ "special": true
90
+ },
91
+ "200011": {
92
+ "content": "<jupyter_start>",
93
+ "lstrip": false,
94
+ "normalized": false,
95
+ "rstrip": false,
96
+ "single_word": false,
97
+ "special": true
98
+ },
99
+ "200012": {
100
+ "content": "<jupyter_text>",
101
+ "lstrip": false,
102
+ "normalized": false,
103
+ "rstrip": false,
104
+ "single_word": false,
105
+ "special": true
106
+ },
107
+ "200013": {
108
+ "content": "<jupyter_code>",
109
+ "lstrip": false,
110
+ "normalized": false,
111
+ "rstrip": false,
112
+ "single_word": false,
113
+ "special": true
114
+ },
115
+ "200014": {
116
+ "content": "<jupyter_output>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false,
121
+ "special": true
122
+ },
123
+ "200015": {
124
+ "content": "<empty_output>",
125
+ "lstrip": false,
126
+ "normalized": false,
127
+ "rstrip": false,
128
+ "single_word": false,
129
+ "special": true
130
+ },
131
+ "200016": {
132
+ "content": "<commit_before>",
133
+ "lstrip": false,
134
+ "normalized": false,
135
+ "rstrip": false,
136
+ "single_word": false,
137
+ "special": true
138
+ },
139
+ "200017": {
140
+ "content": "<commit_msg>",
141
+ "lstrip": false,
142
+ "normalized": false,
143
+ "rstrip": false,
144
+ "single_word": false,
145
+ "special": true
146
+ },
147
+ "200018": {
148
+ "content": "<commit_after>",
149
+ "lstrip": false,
150
+ "normalized": false,
151
+ "rstrip": false,
152
+ "single_word": false,
153
+ "special": true
154
+ },
155
+ "200019": {
156
+ "content": "]~b]",
157
+ "lstrip": false,
158
+ "normalized": false,
159
+ "rstrip": false,
160
+ "single_word": false,
161
+ "special": true
162
+ },
163
+ "200020": {
164
+ "content": "[e~[",
165
+ "lstrip": false,
166
+ "normalized": false,
167
+ "rstrip": false,
168
+ "single_word": false,
169
+ "special": true
170
+ },
171
+ "200021": {
172
+ "content": "]!d~[",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false,
177
+ "special": true
178
+ },
179
+ "200022": {
180
+ "content": "<function_call>",
181
+ "lstrip": false,
182
+ "normalized": false,
183
+ "rstrip": false,
184
+ "single_word": false,
185
+ "special": true
186
+ },
187
+ "200023": {
188
+ "content": "<code_interpreter>",
189
+ "lstrip": false,
190
+ "normalized": false,
191
+ "rstrip": false,
192
+ "single_word": false,
193
+ "special": true
194
+ },
195
+ "200024": {
196
+ "content": "]<]speech[>[",
197
+ "lstrip": false,
198
+ "normalized": false,
199
+ "rstrip": false,
200
+ "single_word": false,
201
+ "special": true
202
+ },
203
+ "200025": {
204
+ "content": "]<]image[>[",
205
+ "lstrip": false,
206
+ "normalized": false,
207
+ "rstrip": false,
208
+ "single_word": false,
209
+ "special": true
210
+ },
211
+ "200026": {
212
+ "content": "]<]video[>[",
213
+ "lstrip": false,
214
+ "normalized": false,
215
+ "rstrip": false,
216
+ "single_word": false,
217
+ "special": true
218
+ },
219
+ "200027": {
220
+ "content": "]<]start of speech[>[",
221
+ "lstrip": false,
222
+ "normalized": false,
223
+ "rstrip": false,
224
+ "single_word": false,
225
+ "special": true
226
+ },
227
+ "200028": {
228
+ "content": "]<]end of speech[>[",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false,
233
+ "special": true
234
+ },
235
+ "200029": {
236
+ "content": "]<]start of image[>[",
237
+ "lstrip": false,
238
+ "normalized": false,
239
+ "rstrip": false,
240
+ "single_word": false,
241
+ "special": true
242
+ },
243
+ "200030": {
244
+ "content": "]<]end of image[>[",
245
+ "lstrip": false,
246
+ "normalized": false,
247
+ "rstrip": false,
248
+ "single_word": false,
249
+ "special": true
250
+ },
251
+ "200031": {
252
+ "content": "]<]start of video[>[",
253
+ "lstrip": false,
254
+ "normalized": false,
255
+ "rstrip": false,
256
+ "single_word": false,
257
+ "special": true
258
+ },
259
+ "200032": {
260
+ "content": "]<]end of video[>[",
261
+ "lstrip": false,
262
+ "normalized": false,
263
+ "rstrip": false,
264
+ "single_word": false,
265
+ "special": true
266
+ },
267
+ "200033": {
268
+ "content": "]<]vision pad[>[",
269
+ "lstrip": false,
270
+ "normalized": false,
271
+ "rstrip": false,
272
+ "single_word": false,
273
+ "special": true
274
+ },
275
+ "200034": {
276
+ "content": "]~!b[",
277
+ "lstrip": false,
278
+ "normalized": false,
279
+ "rstrip": false,
280
+ "single_word": false,
281
+ "special": true
282
+ },
283
+ "200035": {
284
+ "content": "<jupyter_error>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false,
289
+ "special": true
290
+ },
291
+ "200036": {
292
+ "content": "<add_file>",
293
+ "single_word": false,
294
+ "lstrip": false,
295
+ "rstrip": false,
296
+ "normalized": false,
297
+ "special": true
298
+ },
299
+ "200037": {
300
+ "content": "<delete_file>",
301
+ "lstrip": false,
302
+ "normalized": false,
303
+ "rstrip": false,
304
+ "single_word": false,
305
+ "special": true
306
+ },
307
+ "200038": {
308
+ "content": "<rename_file>",
309
+ "lstrip": false,
310
+ "normalized": false,
311
+ "rstrip": false,
312
+ "single_word": false,
313
+ "special": true
314
+ },
315
+ "200039": {
316
+ "content": "<edit_file>",
317
+ "lstrip": false,
318
+ "normalized": false,
319
+ "rstrip": false,
320
+ "single_word": false,
321
+ "special": true
322
+ },
323
+ "200040": {
324
+ "content": "<commit_message>",
325
+ "lstrip": false,
326
+ "normalized": false,
327
+ "rstrip": false,
328
+ "single_word": false,
329
+ "special": true
330
+ },
331
+ "200041": {
332
+ "content": "<empty_source_file>",
333
+ "lstrip": false,
334
+ "normalized": false,
335
+ "rstrip": false,
336
+ "single_word": false,
337
+ "special": true
338
+ },
339
+ "200042": {
340
+ "content": "<repo_struct>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false,
345
+ "special": true
346
+ },
347
+ "200043": {
348
+ "content": "<code_context>",
349
+ "single_word": false,
350
+ "lstrip": false,
351
+ "rstrip": false,
352
+ "normalized": false,
353
+ "special": true
354
+ },
355
+ "200044": {
356
+ "content": "<file_content>",
357
+ "single_word": false,
358
+ "lstrip": false,
359
+ "rstrip": false,
360
+ "normalized": false,
361
+ "special": true
362
+ },
363
+ "200045": {
364
+ "content": "<source_files>",
365
+ "single_word": false,
366
+ "lstrip": false,
367
+ "rstrip": false,
368
+ "normalized": false,
369
+ "special": true
370
+ },
371
+ "200046": {
372
+ "content": "<pr_start>",
373
+ "single_word": false,
374
+ "lstrip": false,
375
+ "rstrip": false,
376
+ "normalized": false,
377
+ "special": true
378
+ },
379
+ "200047": {
380
+ "content": "<review_comment>",
381
+ "single_word": false,
382
+ "lstrip": false,
383
+ "rstrip": false,
384
+ "normalized": false,
385
+ "special": true
386
+ },
387
+ "200048": {
388
+ "content": "<filepath>",
389
+ "single_word": false,
390
+ "lstrip": false,
391
+ "rstrip": false,
392
+ "normalized": false,
393
+ "special": true
394
+ },
395
+ "200049": {
396
+ "content": "<file_sep>",
397
+ "single_word": false,
398
+ "lstrip": false,
399
+ "rstrip": false,
400
+ "normalized": false,
401
+ "special": true
402
+ },
403
+ "200050": {
404
+ "content": "<think>",
405
+ "single_word": false,
406
+ "lstrip": false,
407
+ "rstrip": false,
408
+ "normalized": false,
409
+ "special": false
410
+ },
411
+ "200051": {
412
+ "content": "</think>",
413
+ "single_word": false,
414
+ "lstrip": false,
415
+ "rstrip": false,
416
+ "normalized": false,
417
+ "special": false
418
+ },
419
+ "200052": {
420
+ "content": "<minimax:tool_call>",
421
+ "single_word": false,
422
+ "lstrip": false,
423
+ "rstrip": false,
424
+ "normalized": false,
425
+ "special": false
426
+ },
427
+ "200053": {
428
+ "content": "</minimax:tool_call>",
429
+ "single_word": false,
430
+ "lstrip": false,
431
+ "rstrip": false,
432
+ "normalized": false,
433
+ "special": false
434
+ }
435
+ },
436
+ "additional_special_tokens": [
437
+ "<code_interpreter>",
438
+ "<commit_after>",
439
+ "<commit_before>",
440
+ "<commit_msg>",
441
+ "<empty_output>",
442
+ "<filename>",
443
+ "<fim_middle>",
444
+ "<fim_pad>",
445
+ "<fim_prefix>",
446
+ "<fim_suffix>",
447
+ "<function_call>",
448
+ "<gh_stars>",
449
+ "]<]speech[>[",
450
+ "]<]image[>[",
451
+ "]<]video[>[",
452
+ "]<]start of speech[>[",
453
+ "]<]end of speech[>[",
454
+ "]<]start of image[>[",
455
+ "]<]end of image[>[",
456
+ "]<]start of video[>[",
457
+ "]<]end of video[>[",
458
+ "]<]vision pad[>[",
459
+ "]~!b[",
460
+ "<issue_closed>",
461
+ "<issue_comment>",
462
+ "<issue_start>",
463
+ "<jupyter_code>",
464
+ "<jupyter_output>",
465
+ "<jupyter_start>",
466
+ "<jupyter_text>",
467
+ "<reponame>",
468
+ "[e~[",
469
+ "]!d~[",
470
+ "]!p~[",
471
+ "]~b]",
472
+ "<jupyter_error>",
473
+ "<add_file>",
474
+ "<delete_file>",
475
+ "<rename_file>",
476
+ "<edit_file>",
477
+ "<commit_message>",
478
+ "<empty_source_file>",
479
+ "<repo_struct>",
480
+ "<code_context>",
481
+ "<file_content>",
482
+ "<source_files>",
483
+ "<pr_start>",
484
+ "<review_comment>",
485
+ "<filepath>",
486
+ "<file_sep>"
487
+ ],
488
+ "add_prefix_space": false,
489
+ "bos_token": "]~!b[",
490
+ "clean_up_tokenization_spaces": false,
491
+ "eos_token": "[e~[",
492
+ "model_max_length": 40960000,
493
+ "tokenizer_class": "GPT2Tokenizer",
494
+ "unk_token": "]!d~["
495
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff