tokenizer_config.json
9.8 KB · 343 lines · json Raw
1 {
2 "add_prefix_space": false,
3 "added_tokens_decoder": {
4 "248044": {
5 "content": "<|endoftext|>",
6 "lstrip": false,
7 "normalized": false,
8 "rstrip": false,
9 "single_word": false,
10 "special": true
11 },
12 "248045": {
13 "content": "<|im_start|>",
14 "lstrip": false,
15 "normalized": false,
16 "rstrip": false,
17 "single_word": false,
18 "special": true
19 },
20 "248046": {
21 "content": "<|im_end|>",
22 "lstrip": false,
23 "normalized": false,
24 "rstrip": false,
25 "single_word": false,
26 "special": true
27 },
28 "248047": {
29 "content": "<|object_ref_start|>",
30 "lstrip": false,
31 "normalized": false,
32 "rstrip": false,
33 "single_word": false,
34 "special": true
35 },
36 "248048": {
37 "content": "<|object_ref_end|>",
38 "lstrip": false,
39 "normalized": false,
40 "rstrip": false,
41 "single_word": false,
42 "special": true
43 },
44 "248049": {
45 "content": "<|box_start|>",
46 "lstrip": false,
47 "normalized": false,
48 "rstrip": false,
49 "single_word": false,
50 "special": true
51 },
52 "248050": {
53 "content": "<|box_end|>",
54 "lstrip": false,
55 "normalized": false,
56 "rstrip": false,
57 "single_word": false,
58 "special": true
59 },
60 "248051": {
61 "content": "<|quad_start|>",
62 "lstrip": false,
63 "normalized": false,
64 "rstrip": false,
65 "single_word": false,
66 "special": true
67 },
68 "248052": {
69 "content": "<|quad_end|>",
70 "lstrip": false,
71 "normalized": false,
72 "rstrip": false,
73 "single_word": false,
74 "special": true
75 },
76 "248053": {
77 "content": "<|vision_start|>",
78 "lstrip": false,
79 "normalized": false,
80 "rstrip": false,
81 "single_word": false,
82 "special": true
83 },
84 "248054": {
85 "content": "<|vision_end|>",
86 "lstrip": false,
87 "normalized": false,
88 "rstrip": false,
89 "single_word": false,
90 "special": true
91 },
92 "248055": {
93 "content": "<|vision_pad|>",
94 "lstrip": false,
95 "normalized": false,
96 "rstrip": false,
97 "single_word": false,
98 "special": true
99 },
100 "248056": {
101 "content": "<|image_pad|>",
102 "lstrip": false,
103 "normalized": false,
104 "rstrip": false,
105 "single_word": false,
106 "special": true
107 },
108 "248057": {
109 "content": "<|video_pad|>",
110 "lstrip": false,
111 "normalized": false,
112 "rstrip": false,
113 "single_word": false,
114 "special": true
115 },
116 "248058": {
117 "content": "<tool_call>",
118 "lstrip": false,
119 "normalized": false,
120 "rstrip": false,
121 "single_word": false,
122 "special": false
123 },
124 "248059": {
125 "content": "</tool_call>",
126 "lstrip": false,
127 "normalized": false,
128 "rstrip": false,
129 "single_word": false,
130 "special": false
131 },
132 "248060": {
133 "content": "<|fim_prefix|>",
134 "lstrip": false,
135 "normalized": false,
136 "rstrip": false,
137 "single_word": false,
138 "special": false
139 },
140 "248061": {
141 "content": "<|fim_middle|>",
142 "lstrip": false,
143 "normalized": false,
144 "rstrip": false,
145 "single_word": false,
146 "special": false
147 },
148 "248062": {
149 "content": "<|fim_suffix|>",
150 "lstrip": false,
151 "normalized": false,
152 "rstrip": false,
153 "single_word": false,
154 "special": false
155 },
156 "248063": {
157 "content": "<|fim_pad|>",
158 "lstrip": false,
159 "normalized": false,
160 "rstrip": false,
161 "single_word": false,
162 "special": false
163 },
164 "248064": {
165 "content": "<|repo_name|>",
166 "lstrip": false,
167 "normalized": false,
168 "rstrip": false,
169 "single_word": false,
170 "special": false
171 },
172 "248065": {
173 "content": "<|file_sep|>",
174 "lstrip": false,
175 "normalized": false,
176 "rstrip": false,
177 "single_word": false,
178 "special": false
179 },
180 "248066": {
181 "content": "<tool_response>",
182 "lstrip": false,
183 "normalized": false,
184 "rstrip": false,
185 "single_word": false,
186 "special": false
187 },
188 "248067": {
189 "content": "</tool_response>",
190 "lstrip": false,
191 "normalized": false,
192 "rstrip": false,
193 "single_word": false,
194 "special": false
195 },
196 "248068": {
197 "content": "<think>",
198 "lstrip": false,
199 "normalized": false,
200 "rstrip": false,
201 "single_word": false,
202 "special": false
203 },
204 "248069": {
205 "content": "</think>",
206 "lstrip": false,
207 "normalized": false,
208 "rstrip": false,
209 "single_word": false,
210 "special": false
211 },
212 "248070": {
213 "content": "<|audio_start|>",
214 "lstrip": false,
215 "normalized": false,
216 "rstrip": false,
217 "single_word": false,
218 "special": true
219 },
220 "248071": {
221 "content": "<|audio_end|>",
222 "lstrip": false,
223 "normalized": false,
224 "rstrip": false,
225 "single_word": false,
226 "special": true
227 },
228 "248072": {
229 "content": "<tts_pad>",
230 "lstrip": false,
231 "normalized": false,
232 "rstrip": false,
233 "single_word": false,
234 "special": true
235 },
236 "248073": {
237 "content": "<tts_text_bos>",
238 "lstrip": false,
239 "normalized": false,
240 "rstrip": false,
241 "single_word": false,
242 "special": true
243 },
244 "248074": {
245 "content": "<tts_text_eod>",
246 "lstrip": false,
247 "normalized": false,
248 "rstrip": false,
249 "single_word": false,
250 "special": true
251 },
252 "248075": {
253 "content": "<tts_text_bos_single>",
254 "lstrip": false,
255 "normalized": false,
256 "rstrip": false,
257 "single_word": false,
258 "special": true
259 },
260 "248076": {
261 "content": "<|audio_pad|>",
262 "lstrip": false,
263 "normalized": false,
264 "rstrip": false,
265 "single_word": false,
266 "special": true
267 }
268 },
269 "additional_special_tokens": [
270 "<|im_start|>",
271 "<|im_end|>",
272 "<|object_ref_start|>",
273 "<|object_ref_end|>",
274 "<|box_start|>",
275 "<|box_end|>",
276 "<|quad_start|>",
277 "<|quad_end|>",
278 "<|vision_start|>",
279 "<|vision_end|>",
280 "<|vision_pad|>",
281 "<|image_pad|>",
282 "<|video_pad|>"
283 ],
284 "bos_token": null,
285 "clean_up_tokenization_spaces": false,
286 "eos_token": "<|im_end|>",
287 "errors": "replace",
288 "model_max_length": 262144,
289 "pad_token": "<|endoftext|>",
290 "split_special_tokens": false,
291 "tokenizer_class": "Qwen2Tokenizer",
292 "unk_token": null,
293 "add_bos_token": false,
294 "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+",
295 "extra_special_tokens": {
296 "audio_bos_token": "<|audio_start|>",
297 "audio_eos_token": "<|audio_end|>",
298 "audio_token": "<|audio_pad|>",
299 "image_token": "<|image_pad|>",
300 "video_token": "<|video_pad|>",
301 "vision_bos_token": "<|vision_start|>",
302 "vision_eos_token": "<|vision_end|>"
303 },
304 "response_template": {
305 "defaults": {
306 "role": "assistant"
307 },
308 "start_anchor": "<|im_start|>assistant\n",
309 "fields": {
310 "reasoning_content": {
311 "open": "<think>",
312 "close_pattern": "</think>|(?=<tool_call>)",
313 "content": "text"
314 },
315 "tool_calls": {
316 "open_pattern": "<tool_call>\\s*<function=(?P<name>[^>\\n]+)>",
317 "close_pattern": "</tool_call>|(?=<tool_call>)",
318 "repeats": true,
319 "content": "xml-inline",
320 "content_args": {
321 "tag_pattern": "<parameter=(?P<key>[^>\\n]+)>\\n?(?P<value>.*?)\\n?(?:</parameter>|(?=<parameter=)|(?=</function>))"
322 },
323 "transform": {
324 "type": "function",
325 "function": {
326 "name": "{name}",
327 "arguments": "{content}"
328 }
329 }
330 },
331 "content": {
332 "close": [
333 "<|im_end|>",
334 "<|endoftext|>"
335 ],
336 "content": "text",
337 "repeats": true,
338 "join": ""
339 }
340 }
341 }
342 }
343