fivetech commited on
Commit
3b56fca
·
verified ·
1 Parent(s): 42df544

v2: add tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +307 -0
tokenizer_config.json ADDED
@@ -0,0 +1,307 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "audio_bos_token": "<|audio_start|>",
4
+ "audio_eos_token": "<|audio_end|>",
5
+ "audio_token": "<|audio_pad|>",
6
+ "backend": "tokenizers",
7
+ "bos_token": null,
8
+ "clean_up_tokenization_spaces": false,
9
+ "eos_token": "<|im_end|>",
10
+ "errors": "replace",
11
+ "image_token": "<|image_pad|>",
12
+ "is_local": true,
13
+ "model_max_length": 262144,
14
+ "model_specific_special_tokens": {
15
+ "audio_bos_token": "<|audio_start|>",
16
+ "audio_eos_token": "<|audio_end|>",
17
+ "audio_token": "<|audio_pad|>",
18
+ "image_token": "<|image_pad|>",
19
+ "video_token": "<|video_pad|>",
20
+ "vision_bos_token": "<|vision_start|>",
21
+ "vision_eos_token": "<|vision_end|>"
22
+ },
23
+ "pad_token": "<|PAD_TOKEN|>",
24
+ "padding_side": "left",
25
+ "pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+",
26
+ "processor_class": "Qwen3VLProcessor",
27
+ "split_special_tokens": false,
28
+ "tokenizer_class": "TokenizersBackend",
29
+ "unk_token": null,
30
+ "video_token": "<|video_pad|>",
31
+ "vision_bos_token": "<|vision_start|>",
32
+ "vision_eos_token": "<|vision_end|>",
33
+ "added_tokens_decoder": {
34
+ "248044": {
35
+ "content": "<|endoftext|>",
36
+ "single_word": false,
37
+ "lstrip": false,
38
+ "rstrip": false,
39
+ "normalized": false,
40
+ "special": true
41
+ },
42
+ "248045": {
43
+ "content": "<|im_start|>",
44
+ "single_word": false,
45
+ "lstrip": false,
46
+ "rstrip": false,
47
+ "normalized": false,
48
+ "special": true
49
+ },
50
+ "248046": {
51
+ "content": "<|im_end|>",
52
+ "single_word": false,
53
+ "lstrip": false,
54
+ "rstrip": false,
55
+ "normalized": false,
56
+ "special": true
57
+ },
58
+ "248047": {
59
+ "content": "<|object_ref_start|>",
60
+ "single_word": false,
61
+ "lstrip": false,
62
+ "rstrip": false,
63
+ "normalized": false,
64
+ "special": true
65
+ },
66
+ "248048": {
67
+ "content": "<|object_ref_end|>",
68
+ "single_word": false,
69
+ "lstrip": false,
70
+ "rstrip": false,
71
+ "normalized": false,
72
+ "special": true
73
+ },
74
+ "248049": {
75
+ "content": "<|box_start|>",
76
+ "single_word": false,
77
+ "lstrip": false,
78
+ "rstrip": false,
79
+ "normalized": false,
80
+ "special": true
81
+ },
82
+ "248050": {
83
+ "content": "<|box_end|>",
84
+ "single_word": false,
85
+ "lstrip": false,
86
+ "rstrip": false,
87
+ "normalized": false,
88
+ "special": true
89
+ },
90
+ "248051": {
91
+ "content": "<|quad_start|>",
92
+ "single_word": false,
93
+ "lstrip": false,
94
+ "rstrip": false,
95
+ "normalized": false,
96
+ "special": true
97
+ },
98
+ "248052": {
99
+ "content": "<|quad_end|>",
100
+ "single_word": false,
101
+ "lstrip": false,
102
+ "rstrip": false,
103
+ "normalized": false,
104
+ "special": true
105
+ },
106
+ "248053": {
107
+ "content": "<|vision_start|>",
108
+ "single_word": false,
109
+ "lstrip": false,
110
+ "rstrip": false,
111
+ "normalized": false,
112
+ "special": true
113
+ },
114
+ "248054": {
115
+ "content": "<|vision_end|>",
116
+ "single_word": false,
117
+ "lstrip": false,
118
+ "rstrip": false,
119
+ "normalized": false,
120
+ "special": true
121
+ },
122
+ "248055": {
123
+ "content": "<|vision_pad|>",
124
+ "single_word": false,
125
+ "lstrip": false,
126
+ "rstrip": false,
127
+ "normalized": false,
128
+ "special": true
129
+ },
130
+ "248056": {
131
+ "content": "<|image_pad|>",
132
+ "single_word": false,
133
+ "lstrip": false,
134
+ "rstrip": false,
135
+ "normalized": false,
136
+ "special": true
137
+ },
138
+ "248057": {
139
+ "content": "<|video_pad|>",
140
+ "single_word": false,
141
+ "lstrip": false,
142
+ "rstrip": false,
143
+ "normalized": false,
144
+ "special": true
145
+ },
146
+ "248058": {
147
+ "content": "<tool_call>",
148
+ "single_word": false,
149
+ "lstrip": false,
150
+ "rstrip": false,
151
+ "normalized": false,
152
+ "special": false
153
+ },
154
+ "248059": {
155
+ "content": "</tool_call>",
156
+ "single_word": false,
157
+ "lstrip": false,
158
+ "rstrip": false,
159
+ "normalized": false,
160
+ "special": false
161
+ },
162
+ "248060": {
163
+ "content": "<|fim_prefix|>",
164
+ "single_word": false,
165
+ "lstrip": false,
166
+ "rstrip": false,
167
+ "normalized": false,
168
+ "special": false
169
+ },
170
+ "248061": {
171
+ "content": "<|fim_middle|>",
172
+ "single_word": false,
173
+ "lstrip": false,
174
+ "rstrip": false,
175
+ "normalized": false,
176
+ "special": false
177
+ },
178
+ "248062": {
179
+ "content": "<|fim_suffix|>",
180
+ "single_word": false,
181
+ "lstrip": false,
182
+ "rstrip": false,
183
+ "normalized": false,
184
+ "special": false
185
+ },
186
+ "248063": {
187
+ "content": "<|fim_pad|>",
188
+ "single_word": false,
189
+ "lstrip": false,
190
+ "rstrip": false,
191
+ "normalized": false,
192
+ "special": false
193
+ },
194
+ "248064": {
195
+ "content": "<|repo_name|>",
196
+ "single_word": false,
197
+ "lstrip": false,
198
+ "rstrip": false,
199
+ "normalized": false,
200
+ "special": false
201
+ },
202
+ "248065": {
203
+ "content": "<|file_sep|>",
204
+ "single_word": false,
205
+ "lstrip": false,
206
+ "rstrip": false,
207
+ "normalized": false,
208
+ "special": false
209
+ },
210
+ "248066": {
211
+ "content": "<tool_response>",
212
+ "single_word": false,
213
+ "lstrip": false,
214
+ "rstrip": false,
215
+ "normalized": false,
216
+ "special": false
217
+ },
218
+ "248067": {
219
+ "content": "</tool_response>",
220
+ "single_word": false,
221
+ "lstrip": false,
222
+ "rstrip": false,
223
+ "normalized": false,
224
+ "special": false
225
+ },
226
+ "248068": {
227
+ "content": "<think>",
228
+ "single_word": false,
229
+ "lstrip": false,
230
+ "rstrip": false,
231
+ "normalized": false,
232
+ "special": false
233
+ },
234
+ "248069": {
235
+ "content": "</think>",
236
+ "single_word": false,
237
+ "lstrip": false,
238
+ "rstrip": false,
239
+ "normalized": false,
240
+ "special": false
241
+ },
242
+ "248070": {
243
+ "content": "<|audio_start|>",
244
+ "single_word": false,
245
+ "lstrip": false,
246
+ "rstrip": false,
247
+ "normalized": false,
248
+ "special": true
249
+ },
250
+ "248071": {
251
+ "content": "<|audio_end|>",
252
+ "single_word": false,
253
+ "lstrip": false,
254
+ "rstrip": false,
255
+ "normalized": false,
256
+ "special": true
257
+ },
258
+ "248072": {
259
+ "content": "<tts_pad>",
260
+ "single_word": false,
261
+ "lstrip": false,
262
+ "rstrip": false,
263
+ "normalized": false,
264
+ "special": true
265
+ },
266
+ "248073": {
267
+ "content": "<tts_text_bos>",
268
+ "single_word": false,
269
+ "lstrip": false,
270
+ "rstrip": false,
271
+ "normalized": false,
272
+ "special": true
273
+ },
274
+ "248074": {
275
+ "content": "<tts_text_eod>",
276
+ "single_word": false,
277
+ "lstrip": false,
278
+ "rstrip": false,
279
+ "normalized": false,
280
+ "special": true
281
+ },
282
+ "248075": {
283
+ "content": "<tts_text_bos_single>",
284
+ "single_word": false,
285
+ "lstrip": false,
286
+ "rstrip": false,
287
+ "normalized": false,
288
+ "special": true
289
+ },
290
+ "248076": {
291
+ "content": "<|audio_pad|>",
292
+ "single_word": false,
293
+ "lstrip": false,
294
+ "rstrip": false,
295
+ "normalized": false,
296
+ "special": true
297
+ },
298
+ "248077": {
299
+ "content": "<|PAD_TOKEN|>",
300
+ "single_word": false,
301
+ "lstrip": false,
302
+ "rstrip": false,
303
+ "normalized": false,
304
+ "special": true
305
+ }
306
+ }
307
+ }