ziadrone commited on
Commit
cbf710a
·
verified ·
1 Parent(s): 5e041d9

Upload tokenizer

Browse files
added_tokens.json ADDED
@@ -0,0 +1,29 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</answer>": 49159,
3
+ "</context>": 49157,
4
+ "</step>": 49155,
5
+ "</think>": 49153,
6
+ "<answer>": 49158,
7
+ "<branch_0>": 49163,
8
+ "<branch_10>": 49173,
9
+ "<branch_11>": 49174,
10
+ "<branch_12>": 49175,
11
+ "<branch_13>": 49176,
12
+ "<branch_14>": 49177,
13
+ "<branch_15>": 49178,
14
+ "<branch_1>": 49164,
15
+ "<branch_2>": 49165,
16
+ "<branch_3>": 49166,
17
+ "<branch_4>": 49167,
18
+ "<branch_5>": 49168,
19
+ "<branch_6>": 49169,
20
+ "<branch_7>": 49170,
21
+ "<branch_8>": 49171,
22
+ "<branch_9>": 49172,
23
+ "<context>": 49156,
24
+ "<step>": 49154,
25
+ "<think>": 49152,
26
+ "<|assistant|>": 49161,
27
+ "<|system|>": 49162,
28
+ "<|user|>": 49160
29
+ }
chat_template.jinja ADDED
@@ -0,0 +1,15 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {% for message in messages %}
2
+ {% if message.role == 'system' %}
3
+ <|system|>
4
+ {{ message.content }}
5
+ {% elif message.role == 'user' %}
6
+ <|user|>
7
+ {{ message.content }}
8
+ {% elif message.role == 'assistant' %}
9
+ <|assistant|>
10
+ <think>{{ message.thought if message.thought else '' }}</think>
11
+ <answer>{{ message.content }}</answer>
12
+ {% endif %}
13
+ {% endfor %}
14
+ <|assistant|>
15
+ <think>
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
special_tokens_map.json ADDED
@@ -0,0 +1,59 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<think>",
4
+ "</think>",
5
+ "<step>",
6
+ "</step>",
7
+ "<context>",
8
+ "</context>",
9
+ "<answer>",
10
+ "</answer>",
11
+ "<|user|>",
12
+ "<|assistant|>",
13
+ "<|system|>",
14
+ "<branch_0>",
15
+ "<branch_1>",
16
+ "<branch_2>",
17
+ "<branch_3>",
18
+ "<branch_4>",
19
+ "<branch_5>",
20
+ "<branch_6>",
21
+ "<branch_7>",
22
+ "<branch_8>",
23
+ "<branch_9>",
24
+ "<branch_10>",
25
+ "<branch_11>",
26
+ "<branch_12>",
27
+ "<branch_13>",
28
+ "<branch_14>",
29
+ "<branch_15>"
30
+ ],
31
+ "bos_token": {
32
+ "content": "<|endoftext|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ "eos_token": {
39
+ "content": "<|endoftext|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ "pad_token": {
46
+ "content": "<|endoftext|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ "unk_token": {
53
+ "content": "<|endoftext|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ }
59
+ }
tokenizer.json ADDED
The diff for this file is too large to render. See raw diff
 
tokenizer_config.json ADDED
@@ -0,0 +1,406 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "added_tokens_decoder": {
4
+ "0": {
5
+ "content": "<|endoftext|>",
6
+ "lstrip": false,
7
+ "normalized": false,
8
+ "rstrip": false,
9
+ "single_word": false,
10
+ "special": true
11
+ },
12
+ "1": {
13
+ "content": "<|im_start|>",
14
+ "lstrip": false,
15
+ "normalized": false,
16
+ "rstrip": false,
17
+ "single_word": false,
18
+ "special": true
19
+ },
20
+ "2": {
21
+ "content": "<|im_end|>",
22
+ "lstrip": false,
23
+ "normalized": false,
24
+ "rstrip": false,
25
+ "single_word": false,
26
+ "special": true
27
+ },
28
+ "3": {
29
+ "content": "<repo_name>",
30
+ "lstrip": false,
31
+ "normalized": false,
32
+ "rstrip": false,
33
+ "single_word": false,
34
+ "special": true
35
+ },
36
+ "4": {
37
+ "content": "<reponame>",
38
+ "lstrip": false,
39
+ "normalized": false,
40
+ "rstrip": false,
41
+ "single_word": false,
42
+ "special": true
43
+ },
44
+ "5": {
45
+ "content": "<file_sep>",
46
+ "lstrip": false,
47
+ "normalized": false,
48
+ "rstrip": false,
49
+ "single_word": false,
50
+ "special": true
51
+ },
52
+ "6": {
53
+ "content": "<filename>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false,
58
+ "special": true
59
+ },
60
+ "7": {
61
+ "content": "<gh_stars>",
62
+ "lstrip": false,
63
+ "normalized": false,
64
+ "rstrip": false,
65
+ "single_word": false,
66
+ "special": true
67
+ },
68
+ "8": {
69
+ "content": "<issue_start>",
70
+ "lstrip": false,
71
+ "normalized": false,
72
+ "rstrip": false,
73
+ "single_word": false,
74
+ "special": true
75
+ },
76
+ "9": {
77
+ "content": "<issue_comment>",
78
+ "lstrip": false,
79
+ "normalized": false,
80
+ "rstrip": false,
81
+ "single_word": false,
82
+ "special": true
83
+ },
84
+ "10": {
85
+ "content": "<issue_closed>",
86
+ "lstrip": false,
87
+ "normalized": false,
88
+ "rstrip": false,
89
+ "single_word": false,
90
+ "special": true
91
+ },
92
+ "11": {
93
+ "content": "<jupyter_start>",
94
+ "lstrip": false,
95
+ "normalized": false,
96
+ "rstrip": false,
97
+ "single_word": false,
98
+ "special": true
99
+ },
100
+ "12": {
101
+ "content": "<jupyter_text>",
102
+ "lstrip": false,
103
+ "normalized": false,
104
+ "rstrip": false,
105
+ "single_word": false,
106
+ "special": true
107
+ },
108
+ "13": {
109
+ "content": "<jupyter_code>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false,
114
+ "special": true
115
+ },
116
+ "14": {
117
+ "content": "<jupyter_output>",
118
+ "lstrip": false,
119
+ "normalized": false,
120
+ "rstrip": false,
121
+ "single_word": false,
122
+ "special": true
123
+ },
124
+ "15": {
125
+ "content": "<jupyter_script>",
126
+ "lstrip": false,
127
+ "normalized": false,
128
+ "rstrip": false,
129
+ "single_word": false,
130
+ "special": true
131
+ },
132
+ "16": {
133
+ "content": "<empty_output>",
134
+ "lstrip": false,
135
+ "normalized": false,
136
+ "rstrip": false,
137
+ "single_word": false,
138
+ "special": true
139
+ },
140
+ "49152": {
141
+ "content": "<think>",
142
+ "lstrip": false,
143
+ "normalized": false,
144
+ "rstrip": false,
145
+ "single_word": false,
146
+ "special": true
147
+ },
148
+ "49153": {
149
+ "content": "</think>",
150
+ "lstrip": false,
151
+ "normalized": false,
152
+ "rstrip": false,
153
+ "single_word": false,
154
+ "special": true
155
+ },
156
+ "49154": {
157
+ "content": "<step>",
158
+ "lstrip": false,
159
+ "normalized": false,
160
+ "rstrip": false,
161
+ "single_word": false,
162
+ "special": true
163
+ },
164
+ "49155": {
165
+ "content": "</step>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false,
170
+ "special": true
171
+ },
172
+ "49156": {
173
+ "content": "<context>",
174
+ "lstrip": false,
175
+ "normalized": false,
176
+ "rstrip": false,
177
+ "single_word": false,
178
+ "special": true
179
+ },
180
+ "49157": {
181
+ "content": "</context>",
182
+ "lstrip": false,
183
+ "normalized": false,
184
+ "rstrip": false,
185
+ "single_word": false,
186
+ "special": true
187
+ },
188
+ "49158": {
189
+ "content": "<answer>",
190
+ "lstrip": false,
191
+ "normalized": false,
192
+ "rstrip": false,
193
+ "single_word": false,
194
+ "special": true
195
+ },
196
+ "49159": {
197
+ "content": "</answer>",
198
+ "lstrip": false,
199
+ "normalized": false,
200
+ "rstrip": false,
201
+ "single_word": false,
202
+ "special": true
203
+ },
204
+ "49160": {
205
+ "content": "<|user|>",
206
+ "lstrip": false,
207
+ "normalized": false,
208
+ "rstrip": false,
209
+ "single_word": false,
210
+ "special": true
211
+ },
212
+ "49161": {
213
+ "content": "<|assistant|>",
214
+ "lstrip": false,
215
+ "normalized": false,
216
+ "rstrip": false,
217
+ "single_word": false,
218
+ "special": true
219
+ },
220
+ "49162": {
221
+ "content": "<|system|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false,
226
+ "special": true
227
+ },
228
+ "49163": {
229
+ "content": "<branch_0>",
230
+ "lstrip": false,
231
+ "normalized": false,
232
+ "rstrip": false,
233
+ "single_word": false,
234
+ "special": true
235
+ },
236
+ "49164": {
237
+ "content": "<branch_1>",
238
+ "lstrip": false,
239
+ "normalized": false,
240
+ "rstrip": false,
241
+ "single_word": false,
242
+ "special": true
243
+ },
244
+ "49165": {
245
+ "content": "<branch_2>",
246
+ "lstrip": false,
247
+ "normalized": false,
248
+ "rstrip": false,
249
+ "single_word": false,
250
+ "special": true
251
+ },
252
+ "49166": {
253
+ "content": "<branch_3>",
254
+ "lstrip": false,
255
+ "normalized": false,
256
+ "rstrip": false,
257
+ "single_word": false,
258
+ "special": true
259
+ },
260
+ "49167": {
261
+ "content": "<branch_4>",
262
+ "lstrip": false,
263
+ "normalized": false,
264
+ "rstrip": false,
265
+ "single_word": false,
266
+ "special": true
267
+ },
268
+ "49168": {
269
+ "content": "<branch_5>",
270
+ "lstrip": false,
271
+ "normalized": false,
272
+ "rstrip": false,
273
+ "single_word": false,
274
+ "special": true
275
+ },
276
+ "49169": {
277
+ "content": "<branch_6>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false,
282
+ "special": true
283
+ },
284
+ "49170": {
285
+ "content": "<branch_7>",
286
+ "lstrip": false,
287
+ "normalized": false,
288
+ "rstrip": false,
289
+ "single_word": false,
290
+ "special": true
291
+ },
292
+ "49171": {
293
+ "content": "<branch_8>",
294
+ "lstrip": false,
295
+ "normalized": false,
296
+ "rstrip": false,
297
+ "single_word": false,
298
+ "special": true
299
+ },
300
+ "49172": {
301
+ "content": "<branch_9>",
302
+ "lstrip": false,
303
+ "normalized": false,
304
+ "rstrip": false,
305
+ "single_word": false,
306
+ "special": true
307
+ },
308
+ "49173": {
309
+ "content": "<branch_10>",
310
+ "lstrip": false,
311
+ "normalized": false,
312
+ "rstrip": false,
313
+ "single_word": false,
314
+ "special": true
315
+ },
316
+ "49174": {
317
+ "content": "<branch_11>",
318
+ "lstrip": false,
319
+ "normalized": false,
320
+ "rstrip": false,
321
+ "single_word": false,
322
+ "special": true
323
+ },
324
+ "49175": {
325
+ "content": "<branch_12>",
326
+ "lstrip": false,
327
+ "normalized": false,
328
+ "rstrip": false,
329
+ "single_word": false,
330
+ "special": true
331
+ },
332
+ "49176": {
333
+ "content": "<branch_13>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false,
338
+ "special": true
339
+ },
340
+ "49177": {
341
+ "content": "<branch_14>",
342
+ "lstrip": false,
343
+ "normalized": false,
344
+ "rstrip": false,
345
+ "single_word": false,
346
+ "special": true
347
+ },
348
+ "49178": {
349
+ "content": "<branch_15>",
350
+ "lstrip": false,
351
+ "normalized": false,
352
+ "rstrip": false,
353
+ "single_word": false,
354
+ "special": true
355
+ }
356
+ },
357
+ "additional_special_tokens": [
358
+ "<think>",
359
+ "</think>",
360
+ "<step>",
361
+ "</step>",
362
+ "<context>",
363
+ "</context>",
364
+ "<answer>",
365
+ "</answer>",
366
+ "<|user|>",
367
+ "<|assistant|>",
368
+ "<|system|>",
369
+ "<branch_0>",
370
+ "<branch_1>",
371
+ "<branch_2>",
372
+ "<branch_3>",
373
+ "<branch_4>",
374
+ "<branch_5>",
375
+ "<branch_6>",
376
+ "<branch_7>",
377
+ "<branch_8>",
378
+ "<branch_9>",
379
+ "<branch_10>",
380
+ "<branch_11>",
381
+ "<branch_12>",
382
+ "<branch_13>",
383
+ "<branch_14>",
384
+ "<branch_15>"
385
+ ],
386
+ "bos_token": "<|endoftext|>",
387
+ "clean_up_tokenization_spaces": false,
388
+ "eos_token": "<|endoftext|>",
389
+ "extra_special_tokens": {},
390
+ "max_length": 256,
391
+ "model_input_names": [
392
+ "input_ids",
393
+ "attention_mask"
394
+ ],
395
+ "model_max_length": 4096,
396
+ "pad_to_multiple_of": null,
397
+ "pad_token": "<|endoftext|>",
398
+ "pad_token_type_id": 0,
399
+ "padding_side": "right",
400
+ "stride": 0,
401
+ "tokenizer_class": "GPT2Tokenizer",
402
+ "truncation_side": "right",
403
+ "truncation_strategy": "longest_first",
404
+ "unk_token": "<|endoftext|>",
405
+ "vocab_size": 49152
406
+ }
vocab.json ADDED
The diff for this file is too large to render. See raw diff