Backup-bdg commited on
Commit
593f123
·
verified ·
1 Parent(s): c4629ab

Upload folder using huggingface_hub

Browse files
.gitattributes CHANGED
@@ -33,3 +33,4 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
 
 
33
  *.zip filter=lfs diff=lfs merge=lfs -text
34
  *.zst filter=lfs diff=lfs merge=lfs -text
35
  *tfevents* filter=lfs diff=lfs merge=lfs -text
36
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
added_tokens.json ADDED
@@ -0,0 +1,289 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</tool_call>": 151658,
3
+ "<tool_call>": 151657,
4
+ "<|/add_file|>": 151732,
5
+ "<|/arg_name|>": 151807,
6
+ "<|/arg_value|>": 151809,
7
+ "<|/assistant|>": 151679,
8
+ "<|/audio|>": 151897,
9
+ "<|/branch|>": 151696,
10
+ "<|/cite|>": 151876,
11
+ "<|/code|>": 151822,
12
+ "<|/commit_after|>": 151683,
13
+ "<|/commit_before|>": 151681,
14
+ "<|/commit_msg|>": 151685,
15
+ "<|/conclusion|>": 151859,
16
+ "<|/context|>": 151884,
17
+ "<|/correction|>": 151874,
18
+ "<|/delete_file|>": 151734,
19
+ "<|/diff|>": 151687,
20
+ "<|/doc|>": 151762,
21
+ "<|/edit_file|>": 151738,
22
+ "<|/edit_range|>": 151744,
23
+ "<|/emotion|>": 151899,
24
+ "<|/exec_error|>": 151729,
25
+ "<|/exec_result|>": 151727,
26
+ "<|/exec|>": 151725,
27
+ "<|/file:css|>": 151777,
28
+ "<|/file:csv|>": 151779,
29
+ "<|/file:html|>": 151775,
30
+ "<|/file:ini|>": 151783,
31
+ "<|/file:json|>": 151769,
32
+ "<|/file:log|>": 151785,
33
+ "<|/file:md|>": 151767,
34
+ "<|/file:toml|>": 151781,
35
+ "<|/file:txt|>": 151765,
36
+ "<|/file:xml|>": 151771,
37
+ "<|/file:yaml|>": 151773,
38
+ "<|/file_content|>": 151742,
39
+ "<|/filename|>": 151787,
40
+ "<|/filepath|>": 151789,
41
+ "<|/function_args|>": 151805,
42
+ "<|/function_def|>": 151813,
43
+ "<|/function_name|>": 151803,
44
+ "<|/gen_image|>": 151795,
45
+ "<|/gen_video|>": 151797,
46
+ "<|/gh_stars|>": 151694,
47
+ "<|/hypothesis|>": 151857,
48
+ "<|/image|>": 151791,
49
+ "<|/issue_body|>": 151702,
50
+ "<|/issue_title|>": 151700,
51
+ "<|/issue|>": 151698,
52
+ "<|/jupyter_code|>": 151716,
53
+ "<|/jupyter_error|>": 151722,
54
+ "<|/jupyter_output|>": 151718,
55
+ "<|/jupyter_text|>": 151720,
56
+ "<|/jupyter|>": 151714,
57
+ "<|/line|>": 151746,
58
+ "<|/listen|>": 151893,
59
+ "<|/note|>": 151851,
60
+ "<|/observation|>": 151849,
61
+ "<|/pr_body|>": 151710,
62
+ "<|/pr_title|>": 151708,
63
+ "<|/prompt|>": 151669,
64
+ "<|/prosody|>": 151913,
65
+ "<|/pr|>": 151706,
66
+ "<|/quote|>": 151882,
67
+ "<|/read_file|>": 151740,
68
+ "<|/reflection|>": 151855,
69
+ "<|/ref|>": 151880,
70
+ "<|/rename_file|>": 151736,
71
+ "<|/replace|>": 151750,
72
+ "<|/reponame|>": 151692,
73
+ "<|/response|>": 151673,
74
+ "<|/retrieved|>": 151886,
75
+ "<|/source|>": 151878,
76
+ "<|/speak|>": 151895,
77
+ "<|/step|>": 151853,
78
+ "<|/system|>": 151675,
79
+ "<|/text|>": 151671,
80
+ "<|/think|>": 151847,
81
+ "<|/tool_calls|>": 151818,
82
+ "<|/tool_call|>": 151799,
83
+ "<|/tool_error|>": 151815,
84
+ "<|/tool_id|>": 151820,
85
+ "<|/tool_result|>": 151801,
86
+ "<|/tools|>": 151811,
87
+ "<|/uncertain|>": 151865,
88
+ "<|/user|>": 151677,
89
+ "<|/verify|>": 151870,
90
+ "<|/video|>": 151793,
91
+ "<|add_file|>": 151731,
92
+ "<|arg_name|>": 151806,
93
+ "<|arg_value|>": 151808,
94
+ "<|assistant|>": 151678,
95
+ "<|audio|>": 151896,
96
+ "<|beyond_knowledge|>": 151890,
97
+ "<|bos|>": 151665,
98
+ "<|box_end|>": 151649,
99
+ "<|box_start|>": 151648,
100
+ "<|branch|>": 151695,
101
+ "<|cite|>": 151875,
102
+ "<|code|>": 151821,
103
+ "<|commit_after|>": 151682,
104
+ "<|commit_before|>": 151680,
105
+ "<|commit_msg|>": 151684,
106
+ "<|conclusion|>": 151858,
107
+ "<|confidence:high|>": 151860,
108
+ "<|confidence:low|>": 151862,
109
+ "<|confidence:medium|>": 151861,
110
+ "<|confidence:uncertain|>": 151863,
111
+ "<|context|>": 151883,
112
+ "<|correction|>": 151873,
113
+ "<|delete_file|>": 151733,
114
+ "<|diff_add|>": 151688,
115
+ "<|diff_ctx|>": 151690,
116
+ "<|diff_del|>": 151689,
117
+ "<|diff|>": 151686,
118
+ "<|doc|>": 151761,
119
+ "<|edit_file|>": 151737,
120
+ "<|edit_range|>": 151743,
121
+ "<|emotion:angry|>": 151903,
122
+ "<|emotion:calm|>": 151907,
123
+ "<|emotion:confident|>": 151911,
124
+ "<|emotion:curious|>": 151909,
125
+ "<|emotion:disgusted|>": 151906,
126
+ "<|emotion:excited|>": 151908,
127
+ "<|emotion:fearful|>": 151905,
128
+ "<|emotion:happy|>": 151901,
129
+ "<|emotion:neutral|>": 151900,
130
+ "<|emotion:sad|>": 151902,
131
+ "<|emotion:surprised|>": 151904,
132
+ "<|emotion:sympathetic|>": 151910,
133
+ "<|emotion|>": 151898,
134
+ "<|empty_output|>": 151723,
135
+ "<|endoftext|>": 151643,
136
+ "<|eod|>": 151763,
137
+ "<|eos|>": 151666,
138
+ "<|exec_error|>": 151728,
139
+ "<|exec_result|>": 151726,
140
+ "<|exec_timeout|>": 151730,
141
+ "<|exec|>": 151724,
142
+ "<|fact_check|>": 151871,
143
+ "<|file:css|>": 151776,
144
+ "<|file:csv|>": 151778,
145
+ "<|file:html|>": 151774,
146
+ "<|file:ini|>": 151782,
147
+ "<|file:json|>": 151768,
148
+ "<|file:log|>": 151784,
149
+ "<|file:md|>": 151766,
150
+ "<|file:toml|>": 151780,
151
+ "<|file:txt|>": 151764,
152
+ "<|file:xml|>": 151770,
153
+ "<|file:yaml|>": 151772,
154
+ "<|file_content|>": 151741,
155
+ "<|file_sep|>": 151664,
156
+ "<|filename|>": 151786,
157
+ "<|filepath|>": 151788,
158
+ "<|fim_middle|>": 151660,
159
+ "<|fim_pad|>": 151662,
160
+ "<|fim_prefix|>": 151659,
161
+ "<|fim_suffix|>": 151661,
162
+ "<|function_args|>": 151804,
163
+ "<|function_def|>": 151812,
164
+ "<|function_name|>": 151802,
165
+ "<|gen_image|>": 151794,
166
+ "<|gen_video|>": 151796,
167
+ "<|gh_stars|>": 151693,
168
+ "<|grounded|>": 151887,
169
+ "<|hypothesis|>": 151856,
170
+ "<|im_end|>": 151645,
171
+ "<|im_start|>": 151644,
172
+ "<|image_pad|>": 151655,
173
+ "<|image|>": 151790,
174
+ "<|insert_after|>": 151748,
175
+ "<|insert_before|>": 151747,
176
+ "<|issue_body|>": 151701,
177
+ "<|issue_closed|>": 151703,
178
+ "<|issue_open|>": 151704,
179
+ "<|issue_title|>": 151699,
180
+ "<|issue|>": 151697,
181
+ "<|jupyter_code|>": 151715,
182
+ "<|jupyter_error|>": 151721,
183
+ "<|jupyter_output|>": 151717,
184
+ "<|jupyter_text|>": 151719,
185
+ "<|jupyter|>": 151713,
186
+ "<|knowledge_cutoff|>": 151889,
187
+ "<|lang:bash|>": 151838,
188
+ "<|lang:cpp|>": 151827,
189
+ "<|lang:csharp|>": 151829,
190
+ "<|lang:c|>": 151828,
191
+ "<|lang:go|>": 151830,
192
+ "<|lang:haskell|>": 151844,
193
+ "<|lang:javascript|>": 151824,
194
+ "<|lang:java|>": 151826,
195
+ "<|lang:kotlin|>": 151835,
196
+ "<|lang:lua|>": 151842,
197
+ "<|lang:matlab|>": 151841,
198
+ "<|lang:other|>": 151845,
199
+ "<|lang:perl|>": 151843,
200
+ "<|lang:php|>": 151833,
201
+ "<|lang:python|>": 151823,
202
+ "<|lang:ruby|>": 151832,
203
+ "<|lang:rust|>": 151831,
204
+ "<|lang:r|>": 151840,
205
+ "<|lang:scala|>": 151836,
206
+ "<|lang:shell|>": 151837,
207
+ "<|lang:sql|>": 151839,
208
+ "<|lang:swift|>": 151834,
209
+ "<|lang:typescript|>": 151825,
210
+ "<|line|>": 151745,
211
+ "<|listen|>": 151892,
212
+ "<|mask|>": 151929,
213
+ "<|may_outdated|>": 151868,
214
+ "<|need_verify|>": 151867,
215
+ "<|nl|>": 151928,
216
+ "<|note|>": 151850,
217
+ "<|object_ref_end|>": 151647,
218
+ "<|object_ref_start|>": 151646,
219
+ "<|observation|>": 151848,
220
+ "<|pad|>": 151667,
221
+ "<|pr_body|>": 151709,
222
+ "<|pr_closed|>": 151712,
223
+ "<|pr_merged|>": 151711,
224
+ "<|pr_title|>": 151707,
225
+ "<|prompt|>": 151668,
226
+ "<|prosody:emphasis|>": 151924,
227
+ "<|prosody:fast|>": 151914,
228
+ "<|prosody:high_pitch|>": 151921,
229
+ "<|prosody:loud|>": 151917,
230
+ "<|prosody:low_pitch|>": 151922,
231
+ "<|prosody:normal_pitch|>": 151923,
232
+ "<|prosody:normal_speed|>": 151916,
233
+ "<|prosody:normal_volume|>": 151920,
234
+ "<|prosody:pause_long|>": 151926,
235
+ "<|prosody:pause_short|>": 151925,
236
+ "<|prosody:slow|>": 151915,
237
+ "<|prosody:soft|>": 151918,
238
+ "<|prosody:whisper|>": 151919,
239
+ "<|prosody|>": 151912,
240
+ "<|pr|>": 151705,
241
+ "<|quad_end|>": 151651,
242
+ "<|quad_start|>": 151650,
243
+ "<|quote|>": 151881,
244
+ "<|read_file|>": 151739,
245
+ "<|reflection|>": 151854,
246
+ "<|ref|>": 151879,
247
+ "<|rename_file|>": 151735,
248
+ "<|replace|>": 151749,
249
+ "<|repo_name|>": 151663,
250
+ "<|reponame|>": 151691,
251
+ "<|response|>": 151672,
252
+ "<|retrieved|>": 151885,
253
+ "<|self_correct|>": 151872,
254
+ "<|sep|>": 151927,
255
+ "<|source|>": 151877,
256
+ "<|speak|>": 151894,
257
+ "<|step|>": 151852,
258
+ "<|system|>": 151674,
259
+ "<|text|>": 151670,
260
+ "<|think|>": 151846,
261
+ "<|tool_calls|>": 151817,
262
+ "<|tool_call|>": 151798,
263
+ "<|tool_error|>": 151814,
264
+ "<|tool_id|>": 151819,
265
+ "<|tool_result|>": 151800,
266
+ "<|tool_success|>": 151816,
267
+ "<|tools|>": 151810,
268
+ "<|uncertain|>": 151864,
269
+ "<|ungrounded|>": 151888,
270
+ "<|unknown|>": 151866,
271
+ "<|user|>": 151676,
272
+ "<|verify|>": 151869,
273
+ "<|video_pad|>": 151656,
274
+ "<|video|>": 151792,
275
+ "<|vision_end|>": 151653,
276
+ "<|vision_pad|>": 151654,
277
+ "<|vision_start|>": 151652,
278
+ "<|within_knowledge|>": 151891,
279
+ "[d~[": 151753,
280
+ "[e~[": 151751,
281
+ "[m~[": 151759,
282
+ "[p~[": 151755,
283
+ "]~!b[": 151758,
284
+ "]~b]": 151757,
285
+ "]~d]": 151754,
286
+ "]~e]": 151752,
287
+ "]~m]": 151760,
288
+ "]~p]": 151756
289
+ }
chat_template.jinja ADDED
@@ -0,0 +1,74 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set bos = '<|bos|>' -%}
2
+ {%- set eos = '<|eos|>' -%}
3
+ {%- set system_start = '<|system|>' -%}
4
+ {%- set system_end = '<|/system|>' -%}
5
+ {%- set user_start = '<|user|>' -%}
6
+ {%- set user_end = '<|/user|>' -%}
7
+ {%- set assistant_start = '<|assistant|>' -%}
8
+ {%- set assistant_end = '<|/assistant|>' -%}
9
+ {%- set image_start = '<|image|>' -%}
10
+ {%- set image_end = '<|/image|>' -%}
11
+ {%- set video_start = '<|video|>' -%}
12
+ {%- set video_end = '<|/video|>' -%}
13
+ {%- set audio_start = '<|audio|>' -%}
14
+ {%- set audio_end = '<|/audio|>' -%}
15
+ {%- set tool_call_start = '<|tool_call|>' -%}
16
+ {%- set tool_call_end = '<|/tool_call|>' -%}
17
+ {%- set tool_result_start = '<|tool_result|>' -%}
18
+ {%- set tool_result_end = '<|/tool_result|>' -%}
19
+ {%- set think_start = '<|think|>' -%}
20
+ {%- set think_end = '<|/think|>' -%}
21
+ {%- set code_start = '<|code|>' -%}
22
+ {%- set code_end = '<|/code|>' -%}
23
+ {%- set doc_start = '<|doc|>' -%}
24
+ {%- set doc_end = '<|/doc|>' -%}
25
+ {%- set eod = '<|eod|>' -%}
26
+
27
+ {{- bos -}}
28
+ {%- for message in messages -%}
29
+ {%- if message['role'] == 'system' -%}
30
+ {{- system_start + message['content'] + system_end -}}
31
+ {%- elif message['role'] == 'user' -%}
32
+ {{- user_start -}}
33
+ {%- if message.get('images') -%}
34
+ {%- for img in message['images'] -%}
35
+ {{- image_start + img + image_end -}}
36
+ {%- endfor -%}
37
+ {%- endif -%}
38
+ {%- if message.get('videos') -%}
39
+ {%- for vid in message['videos'] -%}
40
+ {{- video_start + vid + video_end -}}
41
+ {%- endfor -%}
42
+ {%- endif -%}
43
+ {%- if message.get('audio') -%}
44
+ {%- for aud in message['audio'] -%}
45
+ {{- audio_start + aud + audio_end -}}
46
+ {%- endfor -%}
47
+ {%- endif -%}
48
+ {%- if message.get('documents') -%}
49
+ {%- for doc in message['documents'] -%}
50
+ {{- doc_start + doc + doc_end -}}
51
+ {%- endfor -%}
52
+ {%- endif -%}
53
+ {{- message['content'] + user_end -}}
54
+ {%- elif message['role'] == 'assistant' -%}
55
+ {{- assistant_start -}}
56
+ {%- if message.get('thinking') -%}
57
+ {{- think_start + message['thinking'] + think_end -}}
58
+ {%- endif -%}
59
+ {%- if message.get('tool_calls') -%}
60
+ {%- for tool in message['tool_calls'] -%}
61
+ {{- tool_call_start + tool + tool_call_end -}}
62
+ {%- endfor -%}
63
+ {%- endif -%}
64
+ {{- message['content'] -}}
65
+ {%- if not loop.last or add_generation_prompt is not defined or not add_generation_prompt -%}
66
+ {{- assistant_end -}}
67
+ {%- endif -%}
68
+ {%- elif message['role'] == 'tool' -%}
69
+ {{- tool_result_start + message['content'] + tool_result_end -}}
70
+ {%- endif -%}
71
+ {%- endfor -%}
72
+ {%- if add_generation_prompt is defined and add_generation_prompt -%}
73
+ {{- assistant_start -}}
74
+ {%- endif -%}
config.json ADDED
@@ -0,0 +1,50 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "model_name": "Xoron-Dev-MultiMoE",
3
+ "hidden_size": 1024,
4
+ "num_layers": 12,
5
+ "num_heads": 16,
6
+ "intermediate_size": 2048,
7
+ "vocab_size": 151643,
8
+ "max_position_embeddings": 131072,
9
+ "use_sliding_window": true,
10
+ "sliding_window": 4096,
11
+ "use_moe": true,
12
+ "num_experts": 8,
13
+ "num_experts_per_tok": 2,
14
+ "moe_layer_freq": 2,
15
+ "router_aux_loss_coef": 0.1,
16
+ "vision_model_name": "openai/clip-vit-base-patch16",
17
+ "freeze_vision": false,
18
+ "num_vision_tokens": 64,
19
+ "max_video_frames": 32,
20
+ "enable_generation": true,
21
+ "generation_image_size": 256,
22
+ "generation_video_size": 256,
23
+ "generation_latent_channels": 4,
24
+ "generation_base_channels": 128,
25
+ "generation_inference_steps": 8,
26
+ "tokenizer_name": "Qwen/Qwen2.5-1.5B",
27
+ "use_lora": true,
28
+ "lora_r": 32,
29
+ "lora_alpha": 64,
30
+ "lora_dropout": 0.05,
31
+ "lora_target_modules": [
32
+ "q_proj",
33
+ "k_proj",
34
+ "v_proj",
35
+ "o_proj",
36
+ "gate_proj",
37
+ "up_proj",
38
+ "down_proj"
39
+ ],
40
+ "train_lora_only": false,
41
+ "use_cross_attention": true,
42
+ "cross_attention_layers": 4,
43
+ "cross_attention_heads": 8,
44
+ "cross_attention_dropout": 0.1,
45
+ "use_flash_attention": true,
46
+ "output_dir": "./xoron-model",
47
+ "has_audio_encoder": true,
48
+ "has_audio_decoder": true,
49
+ "lora_applied": true
50
+ }
merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
model.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3d56b7fd05d000e5e3ada6f81f01c8327c38793e4ad5d48bb0f1bce97d256730
3
+ size 3705372820
special_tokens.json ADDED
@@ -0,0 +1,272 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "bos": "<|bos|>",
3
+ "eos": "<|eos|>",
4
+ "pad": "<|pad|>",
5
+ "prompt_start": "<|prompt|>",
6
+ "prompt_end": "<|/prompt|>",
7
+ "text_start": "<|text|>",
8
+ "text_end": "<|/text|>",
9
+ "response_start": "<|response|>",
10
+ "response_end": "<|/response|>",
11
+ "system_start": "<|system|>",
12
+ "system_end": "<|/system|>",
13
+ "user_start": "<|user|>",
14
+ "user_end": "<|/user|>",
15
+ "assistant_start": "<|assistant|>",
16
+ "assistant_end": "<|/assistant|>",
17
+ "fim_prefix": "<|fim_prefix|>",
18
+ "fim_middle": "<|fim_middle|>",
19
+ "fim_suffix": "<|fim_suffix|>",
20
+ "fim_pad": "<|fim_pad|>",
21
+ "commit_before": "<|commit_before|>",
22
+ "commit_before_end": "<|/commit_before|>",
23
+ "commit_after": "<|commit_after|>",
24
+ "commit_after_end": "<|/commit_after|>",
25
+ "commit_msg": "<|commit_msg|>",
26
+ "commit_msg_end": "<|/commit_msg|>",
27
+ "diff_start": "<|diff|>",
28
+ "diff_end": "<|/diff|>",
29
+ "diff_add": "<|diff_add|>",
30
+ "diff_del": "<|diff_del|>",
31
+ "diff_context": "<|diff_ctx|>",
32
+ "reponame": "<|reponame|>",
33
+ "reponame_end": "<|/reponame|>",
34
+ "gh_stars": "<|gh_stars|>",
35
+ "gh_stars_end": "<|/gh_stars|>",
36
+ "branch": "<|branch|>",
37
+ "branch_end": "<|/branch|>",
38
+ "issue_start": "<|issue|>",
39
+ "issue_end": "<|/issue|>",
40
+ "issue_title": "<|issue_title|>",
41
+ "issue_title_end": "<|/issue_title|>",
42
+ "issue_body": "<|issue_body|>",
43
+ "issue_body_end": "<|/issue_body|>",
44
+ "issue_closed": "<|issue_closed|>",
45
+ "issue_open": "<|issue_open|>",
46
+ "pr_start": "<|pr|>",
47
+ "pr_end": "<|/pr|>",
48
+ "pr_title": "<|pr_title|>",
49
+ "pr_title_end": "<|/pr_title|>",
50
+ "pr_body": "<|pr_body|>",
51
+ "pr_body_end": "<|/pr_body|>",
52
+ "pr_merged": "<|pr_merged|>",
53
+ "pr_closed": "<|pr_closed|>",
54
+ "jupyter_start": "<|jupyter|>",
55
+ "jupyter_end": "<|/jupyter|>",
56
+ "jupyter_code": "<|jupyter_code|>",
57
+ "jupyter_code_end": "<|/jupyter_code|>",
58
+ "jupyter_output": "<|jupyter_output|>",
59
+ "jupyter_output_end": "<|/jupyter_output|>",
60
+ "jupyter_text": "<|jupyter_text|>",
61
+ "jupyter_text_end": "<|/jupyter_text|>",
62
+ "jupyter_error": "<|jupyter_error|>",
63
+ "jupyter_error_end": "<|/jupyter_error|>",
64
+ "empty_output": "<|empty_output|>",
65
+ "exec_start": "<|exec|>",
66
+ "exec_end": "<|/exec|>",
67
+ "exec_result": "<|exec_result|>",
68
+ "exec_result_end": "<|/exec_result|>",
69
+ "exec_error": "<|exec_error|>",
70
+ "exec_error_end": "<|/exec_error|>",
71
+ "exec_timeout": "<|exec_timeout|>",
72
+ "add_file": "<|add_file|>",
73
+ "add_file_end": "<|/add_file|>",
74
+ "delete_file": "<|delete_file|>",
75
+ "delete_file_end": "<|/delete_file|>",
76
+ "rename_file": "<|rename_file|>",
77
+ "rename_file_end": "<|/rename_file|>",
78
+ "edit_file": "<|edit_file|>",
79
+ "edit_file_end": "<|/edit_file|>",
80
+ "read_file": "<|read_file|>",
81
+ "read_file_end": "<|/read_file|>",
82
+ "file_sep": "<|file_sep|>",
83
+ "file_content": "<|file_content|>",
84
+ "file_content_end": "<|/file_content|>",
85
+ "edit_range": "<|edit_range|>",
86
+ "edit_range_end": "<|/edit_range|>",
87
+ "line_num": "<|line|>",
88
+ "line_num_end": "<|/line|>",
89
+ "insert_before": "<|insert_before|>",
90
+ "insert_after": "<|insert_after|>",
91
+ "replace": "<|replace|>",
92
+ "replace_end": "<|/replace|>",
93
+ "encoder_start": "[e~[",
94
+ "encoder_end": "]~e]",
95
+ "decoder_start": "[d~[",
96
+ "decoder_end": "]~d]",
97
+ "projection_start": "[p~[",
98
+ "projection_end": "]~p]",
99
+ "state_begin": "]~b]",
100
+ "state_end": "]~!b[",
101
+ "modal_switch": "[m~[",
102
+ "modal_switch_end": "]~m]",
103
+ "doc_start": "<|doc|>",
104
+ "doc_end": "<|/doc|>",
105
+ "eod": "<|eod|>",
106
+ "file_txt": "<|file:txt|>",
107
+ "file_txt_end": "<|/file:txt|>",
108
+ "file_md": "<|file:md|>",
109
+ "file_md_end": "<|/file:md|>",
110
+ "file_json": "<|file:json|>",
111
+ "file_json_end": "<|/file:json|>",
112
+ "file_xml": "<|file:xml|>",
113
+ "file_xml_end": "<|/file:xml|>",
114
+ "file_yaml": "<|file:yaml|>",
115
+ "file_yaml_end": "<|/file:yaml|>",
116
+ "file_html": "<|file:html|>",
117
+ "file_html_end": "<|/file:html|>",
118
+ "file_css": "<|file:css|>",
119
+ "file_css_end": "<|/file:css|>",
120
+ "file_csv": "<|file:csv|>",
121
+ "file_csv_end": "<|/file:csv|>",
122
+ "file_toml": "<|file:toml|>",
123
+ "file_toml_end": "<|/file:toml|>",
124
+ "file_ini": "<|file:ini|>",
125
+ "file_ini_end": "<|/file:ini|>",
126
+ "file_log": "<|file:log|>",
127
+ "file_log_end": "<|/file:log|>",
128
+ "filename_start": "<|filename|>",
129
+ "filename_end": "<|/filename|>",
130
+ "filepath_start": "<|filepath|>",
131
+ "filepath_end": "<|/filepath|>",
132
+ "image_start": "<|image|>",
133
+ "image_end": "<|/image|>",
134
+ "video_start": "<|video|>",
135
+ "video_end": "<|/video|>",
136
+ "gen_image_start": "<|gen_image|>",
137
+ "gen_image_end": "<|/gen_image|>",
138
+ "gen_video_start": "<|gen_video|>",
139
+ "gen_video_end": "<|/gen_video|>",
140
+ "tool_call_start": "<|tool_call|>",
141
+ "tool_call_end": "<|/tool_call|>",
142
+ "tool_result_start": "<|tool_result|>",
143
+ "tool_result_end": "<|/tool_result|>",
144
+ "function_name_start": "<|function_name|>",
145
+ "function_name_end": "<|/function_name|>",
146
+ "function_args_start": "<|function_args|>",
147
+ "function_args_end": "<|/function_args|>",
148
+ "arg_name_start": "<|arg_name|>",
149
+ "arg_name_end": "<|/arg_name|>",
150
+ "arg_value_start": "<|arg_value|>",
151
+ "arg_value_end": "<|/arg_value|>",
152
+ "tools_start": "<|tools|>",
153
+ "tools_end": "<|/tools|>",
154
+ "function_def_start": "<|function_def|>",
155
+ "function_def_end": "<|/function_def|>",
156
+ "tool_error_start": "<|tool_error|>",
157
+ "tool_error_end": "<|/tool_error|>",
158
+ "tool_success": "<|tool_success|>",
159
+ "tool_calls_start": "<|tool_calls|>",
160
+ "tool_calls_end": "<|/tool_calls|>",
161
+ "tool_id_start": "<|tool_id|>",
162
+ "tool_id_end": "<|/tool_id|>",
163
+ "code_start": "<|code|>",
164
+ "code_end": "<|/code|>",
165
+ "lang_python": "<|lang:python|>",
166
+ "lang_javascript": "<|lang:javascript|>",
167
+ "lang_typescript": "<|lang:typescript|>",
168
+ "lang_java": "<|lang:java|>",
169
+ "lang_cpp": "<|lang:cpp|>",
170
+ "lang_c": "<|lang:c|>",
171
+ "lang_csharp": "<|lang:csharp|>",
172
+ "lang_go": "<|lang:go|>",
173
+ "lang_rust": "<|lang:rust|>",
174
+ "lang_ruby": "<|lang:ruby|>",
175
+ "lang_php": "<|lang:php|>",
176
+ "lang_swift": "<|lang:swift|>",
177
+ "lang_kotlin": "<|lang:kotlin|>",
178
+ "lang_scala": "<|lang:scala|>",
179
+ "lang_shell": "<|lang:shell|>",
180
+ "lang_bash": "<|lang:bash|>",
181
+ "lang_sql": "<|lang:sql|>",
182
+ "lang_r": "<|lang:r|>",
183
+ "lang_matlab": "<|lang:matlab|>",
184
+ "lang_lua": "<|lang:lua|>",
185
+ "lang_perl": "<|lang:perl|>",
186
+ "lang_haskell": "<|lang:haskell|>",
187
+ "lang_other": "<|lang:other|>",
188
+ "think_start": "<|think|>",
189
+ "think_end": "<|/think|>",
190
+ "observation_start": "<|observation|>",
191
+ "observation_end": "<|/observation|>",
192
+ "note_start": "<|note|>",
193
+ "note_end": "<|/note|>",
194
+ "step_start": "<|step|>",
195
+ "step_end": "<|/step|>",
196
+ "reflection_start": "<|reflection|>",
197
+ "reflection_end": "<|/reflection|>",
198
+ "hypothesis_start": "<|hypothesis|>",
199
+ "hypothesis_end": "<|/hypothesis|>",
200
+ "conclusion_start": "<|conclusion|>",
201
+ "conclusion_end": "<|/conclusion|>",
202
+ "confidence_high": "<|confidence:high|>",
203
+ "confidence_medium": "<|confidence:medium|>",
204
+ "confidence_low": "<|confidence:low|>",
205
+ "confidence_uncertain": "<|confidence:uncertain|>",
206
+ "uncertain_start": "<|uncertain|>",
207
+ "uncertain_end": "<|/uncertain|>",
208
+ "unknown": "<|unknown|>",
209
+ "need_verification": "<|need_verify|>",
210
+ "may_be_outdated": "<|may_outdated|>",
211
+ "verify_start": "<|verify|>",
212
+ "verify_end": "<|/verify|>",
213
+ "fact_check": "<|fact_check|>",
214
+ "self_correct": "<|self_correct|>",
215
+ "correction_start": "<|correction|>",
216
+ "correction_end": "<|/correction|>",
217
+ "cite_start": "<|cite|>",
218
+ "cite_end": "<|/cite|>",
219
+ "source_start": "<|source|>",
220
+ "source_end": "<|/source|>",
221
+ "reference_start": "<|ref|>",
222
+ "reference_end": "<|/ref|>",
223
+ "quote_start": "<|quote|>",
224
+ "quote_end": "<|/quote|>",
225
+ "context_start": "<|context|>",
226
+ "context_end": "<|/context|>",
227
+ "retrieved_start": "<|retrieved|>",
228
+ "retrieved_end": "<|/retrieved|>",
229
+ "grounded": "<|grounded|>",
230
+ "ungrounded": "<|ungrounded|>",
231
+ "knowledge_cutoff": "<|knowledge_cutoff|>",
232
+ "beyond_knowledge": "<|beyond_knowledge|>",
233
+ "within_knowledge": "<|within_knowledge|>",
234
+ "listen_start": "<|listen|>",
235
+ "listen_end": "<|/listen|>",
236
+ "speak_start": "<|speak|>",
237
+ "speak_end": "<|/speak|>",
238
+ "audio_start": "<|audio|>",
239
+ "audio_end": "<|/audio|>",
240
+ "emotion_start": "<|emotion|>",
241
+ "emotion_end": "<|/emotion|>",
242
+ "emotion_neutral": "<|emotion:neutral|>",
243
+ "emotion_happy": "<|emotion:happy|>",
244
+ "emotion_sad": "<|emotion:sad|>",
245
+ "emotion_angry": "<|emotion:angry|>",
246
+ "emotion_surprised": "<|emotion:surprised|>",
247
+ "emotion_fearful": "<|emotion:fearful|>",
248
+ "emotion_disgusted": "<|emotion:disgusted|>",
249
+ "emotion_calm": "<|emotion:calm|>",
250
+ "emotion_excited": "<|emotion:excited|>",
251
+ "emotion_curious": "<|emotion:curious|>",
252
+ "emotion_sympathetic": "<|emotion:sympathetic|>",
253
+ "emotion_confident": "<|emotion:confident|>",
254
+ "prosody_start": "<|prosody|>",
255
+ "prosody_end": "<|/prosody|>",
256
+ "prosody_fast": "<|prosody:fast|>",
257
+ "prosody_slow": "<|prosody:slow|>",
258
+ "prosody_normal_speed": "<|prosody:normal_speed|>",
259
+ "prosody_loud": "<|prosody:loud|>",
260
+ "prosody_soft": "<|prosody:soft|>",
261
+ "prosody_whisper": "<|prosody:whisper|>",
262
+ "prosody_normal_volume": "<|prosody:normal_volume|>",
263
+ "prosody_high_pitch": "<|prosody:high_pitch|>",
264
+ "prosody_low_pitch": "<|prosody:low_pitch|>",
265
+ "prosody_normal_pitch": "<|prosody:normal_pitch|>",
266
+ "prosody_emphasis": "<|prosody:emphasis|>",
267
+ "prosody_pause_short": "<|prosody:pause_short|>",
268
+ "prosody_pause_long": "<|prosody:pause_long|>",
269
+ "separator": "<|sep|>",
270
+ "newline": "<|nl|>",
271
+ "mask": "<|mask|>"
272
+ }
special_tokens_map.json ADDED
@@ -0,0 +1,1897 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ {
4
+ "content": "<|bos|>",
5
+ "lstrip": false,
6
+ "normalized": false,
7
+ "rstrip": false,
8
+ "single_word": false
9
+ },
10
+ {
11
+ "content": "<|eos|>",
12
+ "lstrip": false,
13
+ "normalized": false,
14
+ "rstrip": false,
15
+ "single_word": false
16
+ },
17
+ {
18
+ "content": "<|pad|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ {
25
+ "content": "<|prompt|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ },
31
+ {
32
+ "content": "<|/prompt|>",
33
+ "lstrip": false,
34
+ "normalized": false,
35
+ "rstrip": false,
36
+ "single_word": false
37
+ },
38
+ {
39
+ "content": "<|text|>",
40
+ "lstrip": false,
41
+ "normalized": false,
42
+ "rstrip": false,
43
+ "single_word": false
44
+ },
45
+ {
46
+ "content": "<|/text|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false
51
+ },
52
+ {
53
+ "content": "<|response|>",
54
+ "lstrip": false,
55
+ "normalized": false,
56
+ "rstrip": false,
57
+ "single_word": false
58
+ },
59
+ {
60
+ "content": "<|/response|>",
61
+ "lstrip": false,
62
+ "normalized": false,
63
+ "rstrip": false,
64
+ "single_word": false
65
+ },
66
+ {
67
+ "content": "<|system|>",
68
+ "lstrip": false,
69
+ "normalized": false,
70
+ "rstrip": false,
71
+ "single_word": false
72
+ },
73
+ {
74
+ "content": "<|/system|>",
75
+ "lstrip": false,
76
+ "normalized": false,
77
+ "rstrip": false,
78
+ "single_word": false
79
+ },
80
+ {
81
+ "content": "<|user|>",
82
+ "lstrip": false,
83
+ "normalized": false,
84
+ "rstrip": false,
85
+ "single_word": false
86
+ },
87
+ {
88
+ "content": "<|/user|>",
89
+ "lstrip": false,
90
+ "normalized": false,
91
+ "rstrip": false,
92
+ "single_word": false
93
+ },
94
+ {
95
+ "content": "<|assistant|>",
96
+ "lstrip": false,
97
+ "normalized": false,
98
+ "rstrip": false,
99
+ "single_word": false
100
+ },
101
+ {
102
+ "content": "<|/assistant|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false
107
+ },
108
+ {
109
+ "content": "<|fim_prefix|>",
110
+ "lstrip": false,
111
+ "normalized": false,
112
+ "rstrip": false,
113
+ "single_word": false
114
+ },
115
+ {
116
+ "content": "<|fim_middle|>",
117
+ "lstrip": false,
118
+ "normalized": false,
119
+ "rstrip": false,
120
+ "single_word": false
121
+ },
122
+ {
123
+ "content": "<|fim_suffix|>",
124
+ "lstrip": false,
125
+ "normalized": false,
126
+ "rstrip": false,
127
+ "single_word": false
128
+ },
129
+ {
130
+ "content": "<|fim_pad|>",
131
+ "lstrip": false,
132
+ "normalized": false,
133
+ "rstrip": false,
134
+ "single_word": false
135
+ },
136
+ {
137
+ "content": "<|commit_before|>",
138
+ "lstrip": false,
139
+ "normalized": false,
140
+ "rstrip": false,
141
+ "single_word": false
142
+ },
143
+ {
144
+ "content": "<|/commit_before|>",
145
+ "lstrip": false,
146
+ "normalized": false,
147
+ "rstrip": false,
148
+ "single_word": false
149
+ },
150
+ {
151
+ "content": "<|commit_after|>",
152
+ "lstrip": false,
153
+ "normalized": false,
154
+ "rstrip": false,
155
+ "single_word": false
156
+ },
157
+ {
158
+ "content": "<|/commit_after|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false
163
+ },
164
+ {
165
+ "content": "<|commit_msg|>",
166
+ "lstrip": false,
167
+ "normalized": false,
168
+ "rstrip": false,
169
+ "single_word": false
170
+ },
171
+ {
172
+ "content": "<|/commit_msg|>",
173
+ "lstrip": false,
174
+ "normalized": false,
175
+ "rstrip": false,
176
+ "single_word": false
177
+ },
178
+ {
179
+ "content": "<|diff|>",
180
+ "lstrip": false,
181
+ "normalized": false,
182
+ "rstrip": false,
183
+ "single_word": false
184
+ },
185
+ {
186
+ "content": "<|/diff|>",
187
+ "lstrip": false,
188
+ "normalized": false,
189
+ "rstrip": false,
190
+ "single_word": false
191
+ },
192
+ {
193
+ "content": "<|diff_add|>",
194
+ "lstrip": false,
195
+ "normalized": false,
196
+ "rstrip": false,
197
+ "single_word": false
198
+ },
199
+ {
200
+ "content": "<|diff_del|>",
201
+ "lstrip": false,
202
+ "normalized": false,
203
+ "rstrip": false,
204
+ "single_word": false
205
+ },
206
+ {
207
+ "content": "<|diff_ctx|>",
208
+ "lstrip": false,
209
+ "normalized": false,
210
+ "rstrip": false,
211
+ "single_word": false
212
+ },
213
+ {
214
+ "content": "<|reponame|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false
219
+ },
220
+ {
221
+ "content": "<|/reponame|>",
222
+ "lstrip": false,
223
+ "normalized": false,
224
+ "rstrip": false,
225
+ "single_word": false
226
+ },
227
+ {
228
+ "content": "<|gh_stars|>",
229
+ "lstrip": false,
230
+ "normalized": false,
231
+ "rstrip": false,
232
+ "single_word": false
233
+ },
234
+ {
235
+ "content": "<|/gh_stars|>",
236
+ "lstrip": false,
237
+ "normalized": false,
238
+ "rstrip": false,
239
+ "single_word": false
240
+ },
241
+ {
242
+ "content": "<|branch|>",
243
+ "lstrip": false,
244
+ "normalized": false,
245
+ "rstrip": false,
246
+ "single_word": false
247
+ },
248
+ {
249
+ "content": "<|/branch|>",
250
+ "lstrip": false,
251
+ "normalized": false,
252
+ "rstrip": false,
253
+ "single_word": false
254
+ },
255
+ {
256
+ "content": "<|issue|>",
257
+ "lstrip": false,
258
+ "normalized": false,
259
+ "rstrip": false,
260
+ "single_word": false
261
+ },
262
+ {
263
+ "content": "<|/issue|>",
264
+ "lstrip": false,
265
+ "normalized": false,
266
+ "rstrip": false,
267
+ "single_word": false
268
+ },
269
+ {
270
+ "content": "<|issue_title|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false
275
+ },
276
+ {
277
+ "content": "<|/issue_title|>",
278
+ "lstrip": false,
279
+ "normalized": false,
280
+ "rstrip": false,
281
+ "single_word": false
282
+ },
283
+ {
284
+ "content": "<|issue_body|>",
285
+ "lstrip": false,
286
+ "normalized": false,
287
+ "rstrip": false,
288
+ "single_word": false
289
+ },
290
+ {
291
+ "content": "<|/issue_body|>",
292
+ "lstrip": false,
293
+ "normalized": false,
294
+ "rstrip": false,
295
+ "single_word": false
296
+ },
297
+ {
298
+ "content": "<|issue_closed|>",
299
+ "lstrip": false,
300
+ "normalized": false,
301
+ "rstrip": false,
302
+ "single_word": false
303
+ },
304
+ {
305
+ "content": "<|issue_open|>",
306
+ "lstrip": false,
307
+ "normalized": false,
308
+ "rstrip": false,
309
+ "single_word": false
310
+ },
311
+ {
312
+ "content": "<|pr|>",
313
+ "lstrip": false,
314
+ "normalized": false,
315
+ "rstrip": false,
316
+ "single_word": false
317
+ },
318
+ {
319
+ "content": "<|/pr|>",
320
+ "lstrip": false,
321
+ "normalized": false,
322
+ "rstrip": false,
323
+ "single_word": false
324
+ },
325
+ {
326
+ "content": "<|pr_title|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false
331
+ },
332
+ {
333
+ "content": "<|/pr_title|>",
334
+ "lstrip": false,
335
+ "normalized": false,
336
+ "rstrip": false,
337
+ "single_word": false
338
+ },
339
+ {
340
+ "content": "<|pr_body|>",
341
+ "lstrip": false,
342
+ "normalized": false,
343
+ "rstrip": false,
344
+ "single_word": false
345
+ },
346
+ {
347
+ "content": "<|/pr_body|>",
348
+ "lstrip": false,
349
+ "normalized": false,
350
+ "rstrip": false,
351
+ "single_word": false
352
+ },
353
+ {
354
+ "content": "<|pr_merged|>",
355
+ "lstrip": false,
356
+ "normalized": false,
357
+ "rstrip": false,
358
+ "single_word": false
359
+ },
360
+ {
361
+ "content": "<|pr_closed|>",
362
+ "lstrip": false,
363
+ "normalized": false,
364
+ "rstrip": false,
365
+ "single_word": false
366
+ },
367
+ {
368
+ "content": "<|jupyter|>",
369
+ "lstrip": false,
370
+ "normalized": false,
371
+ "rstrip": false,
372
+ "single_word": false
373
+ },
374
+ {
375
+ "content": "<|/jupyter|>",
376
+ "lstrip": false,
377
+ "normalized": false,
378
+ "rstrip": false,
379
+ "single_word": false
380
+ },
381
+ {
382
+ "content": "<|jupyter_code|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false
387
+ },
388
+ {
389
+ "content": "<|/jupyter_code|>",
390
+ "lstrip": false,
391
+ "normalized": false,
392
+ "rstrip": false,
393
+ "single_word": false
394
+ },
395
+ {
396
+ "content": "<|jupyter_output|>",
397
+ "lstrip": false,
398
+ "normalized": false,
399
+ "rstrip": false,
400
+ "single_word": false
401
+ },
402
+ {
403
+ "content": "<|/jupyter_output|>",
404
+ "lstrip": false,
405
+ "normalized": false,
406
+ "rstrip": false,
407
+ "single_word": false
408
+ },
409
+ {
410
+ "content": "<|jupyter_text|>",
411
+ "lstrip": false,
412
+ "normalized": false,
413
+ "rstrip": false,
414
+ "single_word": false
415
+ },
416
+ {
417
+ "content": "<|/jupyter_text|>",
418
+ "lstrip": false,
419
+ "normalized": false,
420
+ "rstrip": false,
421
+ "single_word": false
422
+ },
423
+ {
424
+ "content": "<|jupyter_error|>",
425
+ "lstrip": false,
426
+ "normalized": false,
427
+ "rstrip": false,
428
+ "single_word": false
429
+ },
430
+ {
431
+ "content": "<|/jupyter_error|>",
432
+ "lstrip": false,
433
+ "normalized": false,
434
+ "rstrip": false,
435
+ "single_word": false
436
+ },
437
+ {
438
+ "content": "<|empty_output|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false
443
+ },
444
+ {
445
+ "content": "<|exec|>",
446
+ "lstrip": false,
447
+ "normalized": false,
448
+ "rstrip": false,
449
+ "single_word": false
450
+ },
451
+ {
452
+ "content": "<|/exec|>",
453
+ "lstrip": false,
454
+ "normalized": false,
455
+ "rstrip": false,
456
+ "single_word": false
457
+ },
458
+ {
459
+ "content": "<|exec_result|>",
460
+ "lstrip": false,
461
+ "normalized": false,
462
+ "rstrip": false,
463
+ "single_word": false
464
+ },
465
+ {
466
+ "content": "<|/exec_result|>",
467
+ "lstrip": false,
468
+ "normalized": false,
469
+ "rstrip": false,
470
+ "single_word": false
471
+ },
472
+ {
473
+ "content": "<|exec_error|>",
474
+ "lstrip": false,
475
+ "normalized": false,
476
+ "rstrip": false,
477
+ "single_word": false
478
+ },
479
+ {
480
+ "content": "<|/exec_error|>",
481
+ "lstrip": false,
482
+ "normalized": false,
483
+ "rstrip": false,
484
+ "single_word": false
485
+ },
486
+ {
487
+ "content": "<|exec_timeout|>",
488
+ "lstrip": false,
489
+ "normalized": false,
490
+ "rstrip": false,
491
+ "single_word": false
492
+ },
493
+ {
494
+ "content": "<|add_file|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false
499
+ },
500
+ {
501
+ "content": "<|/add_file|>",
502
+ "lstrip": false,
503
+ "normalized": false,
504
+ "rstrip": false,
505
+ "single_word": false
506
+ },
507
+ {
508
+ "content": "<|delete_file|>",
509
+ "lstrip": false,
510
+ "normalized": false,
511
+ "rstrip": false,
512
+ "single_word": false
513
+ },
514
+ {
515
+ "content": "<|/delete_file|>",
516
+ "lstrip": false,
517
+ "normalized": false,
518
+ "rstrip": false,
519
+ "single_word": false
520
+ },
521
+ {
522
+ "content": "<|rename_file|>",
523
+ "lstrip": false,
524
+ "normalized": false,
525
+ "rstrip": false,
526
+ "single_word": false
527
+ },
528
+ {
529
+ "content": "<|/rename_file|>",
530
+ "lstrip": false,
531
+ "normalized": false,
532
+ "rstrip": false,
533
+ "single_word": false
534
+ },
535
+ {
536
+ "content": "<|edit_file|>",
537
+ "lstrip": false,
538
+ "normalized": false,
539
+ "rstrip": false,
540
+ "single_word": false
541
+ },
542
+ {
543
+ "content": "<|/edit_file|>",
544
+ "lstrip": false,
545
+ "normalized": false,
546
+ "rstrip": false,
547
+ "single_word": false
548
+ },
549
+ {
550
+ "content": "<|read_file|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false
555
+ },
556
+ {
557
+ "content": "<|/read_file|>",
558
+ "lstrip": false,
559
+ "normalized": false,
560
+ "rstrip": false,
561
+ "single_word": false
562
+ },
563
+ {
564
+ "content": "<|file_sep|>",
565
+ "lstrip": false,
566
+ "normalized": false,
567
+ "rstrip": false,
568
+ "single_word": false
569
+ },
570
+ {
571
+ "content": "<|file_content|>",
572
+ "lstrip": false,
573
+ "normalized": false,
574
+ "rstrip": false,
575
+ "single_word": false
576
+ },
577
+ {
578
+ "content": "<|/file_content|>",
579
+ "lstrip": false,
580
+ "normalized": false,
581
+ "rstrip": false,
582
+ "single_word": false
583
+ },
584
+ {
585
+ "content": "<|edit_range|>",
586
+ "lstrip": false,
587
+ "normalized": false,
588
+ "rstrip": false,
589
+ "single_word": false
590
+ },
591
+ {
592
+ "content": "<|/edit_range|>",
593
+ "lstrip": false,
594
+ "normalized": false,
595
+ "rstrip": false,
596
+ "single_word": false
597
+ },
598
+ {
599
+ "content": "<|line|>",
600
+ "lstrip": false,
601
+ "normalized": false,
602
+ "rstrip": false,
603
+ "single_word": false
604
+ },
605
+ {
606
+ "content": "<|/line|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false
611
+ },
612
+ {
613
+ "content": "<|insert_before|>",
614
+ "lstrip": false,
615
+ "normalized": false,
616
+ "rstrip": false,
617
+ "single_word": false
618
+ },
619
+ {
620
+ "content": "<|insert_after|>",
621
+ "lstrip": false,
622
+ "normalized": false,
623
+ "rstrip": false,
624
+ "single_word": false
625
+ },
626
+ {
627
+ "content": "<|replace|>",
628
+ "lstrip": false,
629
+ "normalized": false,
630
+ "rstrip": false,
631
+ "single_word": false
632
+ },
633
+ {
634
+ "content": "<|/replace|>",
635
+ "lstrip": false,
636
+ "normalized": false,
637
+ "rstrip": false,
638
+ "single_word": false
639
+ },
640
+ {
641
+ "content": "[e~[",
642
+ "lstrip": false,
643
+ "normalized": false,
644
+ "rstrip": false,
645
+ "single_word": false
646
+ },
647
+ {
648
+ "content": "]~e]",
649
+ "lstrip": false,
650
+ "normalized": false,
651
+ "rstrip": false,
652
+ "single_word": false
653
+ },
654
+ {
655
+ "content": "[d~[",
656
+ "lstrip": false,
657
+ "normalized": false,
658
+ "rstrip": false,
659
+ "single_word": false
660
+ },
661
+ {
662
+ "content": "]~d]",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false
667
+ },
668
+ {
669
+ "content": "[p~[",
670
+ "lstrip": false,
671
+ "normalized": false,
672
+ "rstrip": false,
673
+ "single_word": false
674
+ },
675
+ {
676
+ "content": "]~p]",
677
+ "lstrip": false,
678
+ "normalized": false,
679
+ "rstrip": false,
680
+ "single_word": false
681
+ },
682
+ {
683
+ "content": "]~b]",
684
+ "lstrip": false,
685
+ "normalized": false,
686
+ "rstrip": false,
687
+ "single_word": false
688
+ },
689
+ {
690
+ "content": "]~!b[",
691
+ "lstrip": false,
692
+ "normalized": false,
693
+ "rstrip": false,
694
+ "single_word": false
695
+ },
696
+ {
697
+ "content": "[m~[",
698
+ "lstrip": false,
699
+ "normalized": false,
700
+ "rstrip": false,
701
+ "single_word": false
702
+ },
703
+ {
704
+ "content": "]~m]",
705
+ "lstrip": false,
706
+ "normalized": false,
707
+ "rstrip": false,
708
+ "single_word": false
709
+ },
710
+ {
711
+ "content": "<|doc|>",
712
+ "lstrip": false,
713
+ "normalized": false,
714
+ "rstrip": false,
715
+ "single_word": false
716
+ },
717
+ {
718
+ "content": "<|/doc|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false
723
+ },
724
+ {
725
+ "content": "<|eod|>",
726
+ "lstrip": false,
727
+ "normalized": false,
728
+ "rstrip": false,
729
+ "single_word": false
730
+ },
731
+ {
732
+ "content": "<|file:txt|>",
733
+ "lstrip": false,
734
+ "normalized": false,
735
+ "rstrip": false,
736
+ "single_word": false
737
+ },
738
+ {
739
+ "content": "<|/file:txt|>",
740
+ "lstrip": false,
741
+ "normalized": false,
742
+ "rstrip": false,
743
+ "single_word": false
744
+ },
745
+ {
746
+ "content": "<|file:md|>",
747
+ "lstrip": false,
748
+ "normalized": false,
749
+ "rstrip": false,
750
+ "single_word": false
751
+ },
752
+ {
753
+ "content": "<|/file:md|>",
754
+ "lstrip": false,
755
+ "normalized": false,
756
+ "rstrip": false,
757
+ "single_word": false
758
+ },
759
+ {
760
+ "content": "<|file:json|>",
761
+ "lstrip": false,
762
+ "normalized": false,
763
+ "rstrip": false,
764
+ "single_word": false
765
+ },
766
+ {
767
+ "content": "<|/file:json|>",
768
+ "lstrip": false,
769
+ "normalized": false,
770
+ "rstrip": false,
771
+ "single_word": false
772
+ },
773
+ {
774
+ "content": "<|file:xml|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false
779
+ },
780
+ {
781
+ "content": "<|/file:xml|>",
782
+ "lstrip": false,
783
+ "normalized": false,
784
+ "rstrip": false,
785
+ "single_word": false
786
+ },
787
+ {
788
+ "content": "<|file:yaml|>",
789
+ "lstrip": false,
790
+ "normalized": false,
791
+ "rstrip": false,
792
+ "single_word": false
793
+ },
794
+ {
795
+ "content": "<|/file:yaml|>",
796
+ "lstrip": false,
797
+ "normalized": false,
798
+ "rstrip": false,
799
+ "single_word": false
800
+ },
801
+ {
802
+ "content": "<|file:html|>",
803
+ "lstrip": false,
804
+ "normalized": false,
805
+ "rstrip": false,
806
+ "single_word": false
807
+ },
808
+ {
809
+ "content": "<|/file:html|>",
810
+ "lstrip": false,
811
+ "normalized": false,
812
+ "rstrip": false,
813
+ "single_word": false
814
+ },
815
+ {
816
+ "content": "<|file:css|>",
817
+ "lstrip": false,
818
+ "normalized": false,
819
+ "rstrip": false,
820
+ "single_word": false
821
+ },
822
+ {
823
+ "content": "<|/file:css|>",
824
+ "lstrip": false,
825
+ "normalized": false,
826
+ "rstrip": false,
827
+ "single_word": false
828
+ },
829
+ {
830
+ "content": "<|file:csv|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false
835
+ },
836
+ {
837
+ "content": "<|/file:csv|>",
838
+ "lstrip": false,
839
+ "normalized": false,
840
+ "rstrip": false,
841
+ "single_word": false
842
+ },
843
+ {
844
+ "content": "<|file:toml|>",
845
+ "lstrip": false,
846
+ "normalized": false,
847
+ "rstrip": false,
848
+ "single_word": false
849
+ },
850
+ {
851
+ "content": "<|/file:toml|>",
852
+ "lstrip": false,
853
+ "normalized": false,
854
+ "rstrip": false,
855
+ "single_word": false
856
+ },
857
+ {
858
+ "content": "<|file:ini|>",
859
+ "lstrip": false,
860
+ "normalized": false,
861
+ "rstrip": false,
862
+ "single_word": false
863
+ },
864
+ {
865
+ "content": "<|/file:ini|>",
866
+ "lstrip": false,
867
+ "normalized": false,
868
+ "rstrip": false,
869
+ "single_word": false
870
+ },
871
+ {
872
+ "content": "<|file:log|>",
873
+ "lstrip": false,
874
+ "normalized": false,
875
+ "rstrip": false,
876
+ "single_word": false
877
+ },
878
+ {
879
+ "content": "<|/file:log|>",
880
+ "lstrip": false,
881
+ "normalized": false,
882
+ "rstrip": false,
883
+ "single_word": false
884
+ },
885
+ {
886
+ "content": "<|filename|>",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false
891
+ },
892
+ {
893
+ "content": "<|/filename|>",
894
+ "lstrip": false,
895
+ "normalized": false,
896
+ "rstrip": false,
897
+ "single_word": false
898
+ },
899
+ {
900
+ "content": "<|filepath|>",
901
+ "lstrip": false,
902
+ "normalized": false,
903
+ "rstrip": false,
904
+ "single_word": false
905
+ },
906
+ {
907
+ "content": "<|/filepath|>",
908
+ "lstrip": false,
909
+ "normalized": false,
910
+ "rstrip": false,
911
+ "single_word": false
912
+ },
913
+ {
914
+ "content": "<|image|>",
915
+ "lstrip": false,
916
+ "normalized": false,
917
+ "rstrip": false,
918
+ "single_word": false
919
+ },
920
+ {
921
+ "content": "<|/image|>",
922
+ "lstrip": false,
923
+ "normalized": false,
924
+ "rstrip": false,
925
+ "single_word": false
926
+ },
927
+ {
928
+ "content": "<|video|>",
929
+ "lstrip": false,
930
+ "normalized": false,
931
+ "rstrip": false,
932
+ "single_word": false
933
+ },
934
+ {
935
+ "content": "<|/video|>",
936
+ "lstrip": false,
937
+ "normalized": false,
938
+ "rstrip": false,
939
+ "single_word": false
940
+ },
941
+ {
942
+ "content": "<|gen_image|>",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false
947
+ },
948
+ {
949
+ "content": "<|/gen_image|>",
950
+ "lstrip": false,
951
+ "normalized": false,
952
+ "rstrip": false,
953
+ "single_word": false
954
+ },
955
+ {
956
+ "content": "<|gen_video|>",
957
+ "lstrip": false,
958
+ "normalized": false,
959
+ "rstrip": false,
960
+ "single_word": false
961
+ },
962
+ {
963
+ "content": "<|/gen_video|>",
964
+ "lstrip": false,
965
+ "normalized": false,
966
+ "rstrip": false,
967
+ "single_word": false
968
+ },
969
+ {
970
+ "content": "<|tool_call|>",
971
+ "lstrip": false,
972
+ "normalized": false,
973
+ "rstrip": false,
974
+ "single_word": false
975
+ },
976
+ {
977
+ "content": "<|/tool_call|>",
978
+ "lstrip": false,
979
+ "normalized": false,
980
+ "rstrip": false,
981
+ "single_word": false
982
+ },
983
+ {
984
+ "content": "<|tool_result|>",
985
+ "lstrip": false,
986
+ "normalized": false,
987
+ "rstrip": false,
988
+ "single_word": false
989
+ },
990
+ {
991
+ "content": "<|/tool_result|>",
992
+ "lstrip": false,
993
+ "normalized": false,
994
+ "rstrip": false,
995
+ "single_word": false
996
+ },
997
+ {
998
+ "content": "<|function_name|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false
1003
+ },
1004
+ {
1005
+ "content": "<|/function_name|>",
1006
+ "lstrip": false,
1007
+ "normalized": false,
1008
+ "rstrip": false,
1009
+ "single_word": false
1010
+ },
1011
+ {
1012
+ "content": "<|function_args|>",
1013
+ "lstrip": false,
1014
+ "normalized": false,
1015
+ "rstrip": false,
1016
+ "single_word": false
1017
+ },
1018
+ {
1019
+ "content": "<|/function_args|>",
1020
+ "lstrip": false,
1021
+ "normalized": false,
1022
+ "rstrip": false,
1023
+ "single_word": false
1024
+ },
1025
+ {
1026
+ "content": "<|arg_name|>",
1027
+ "lstrip": false,
1028
+ "normalized": false,
1029
+ "rstrip": false,
1030
+ "single_word": false
1031
+ },
1032
+ {
1033
+ "content": "<|/arg_name|>",
1034
+ "lstrip": false,
1035
+ "normalized": false,
1036
+ "rstrip": false,
1037
+ "single_word": false
1038
+ },
1039
+ {
1040
+ "content": "<|arg_value|>",
1041
+ "lstrip": false,
1042
+ "normalized": false,
1043
+ "rstrip": false,
1044
+ "single_word": false
1045
+ },
1046
+ {
1047
+ "content": "<|/arg_value|>",
1048
+ "lstrip": false,
1049
+ "normalized": false,
1050
+ "rstrip": false,
1051
+ "single_word": false
1052
+ },
1053
+ {
1054
+ "content": "<|tools|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false
1059
+ },
1060
+ {
1061
+ "content": "<|/tools|>",
1062
+ "lstrip": false,
1063
+ "normalized": false,
1064
+ "rstrip": false,
1065
+ "single_word": false
1066
+ },
1067
+ {
1068
+ "content": "<|function_def|>",
1069
+ "lstrip": false,
1070
+ "normalized": false,
1071
+ "rstrip": false,
1072
+ "single_word": false
1073
+ },
1074
+ {
1075
+ "content": "<|/function_def|>",
1076
+ "lstrip": false,
1077
+ "normalized": false,
1078
+ "rstrip": false,
1079
+ "single_word": false
1080
+ },
1081
+ {
1082
+ "content": "<|tool_error|>",
1083
+ "lstrip": false,
1084
+ "normalized": false,
1085
+ "rstrip": false,
1086
+ "single_word": false
1087
+ },
1088
+ {
1089
+ "content": "<|/tool_error|>",
1090
+ "lstrip": false,
1091
+ "normalized": false,
1092
+ "rstrip": false,
1093
+ "single_word": false
1094
+ },
1095
+ {
1096
+ "content": "<|tool_success|>",
1097
+ "lstrip": false,
1098
+ "normalized": false,
1099
+ "rstrip": false,
1100
+ "single_word": false
1101
+ },
1102
+ {
1103
+ "content": "<|tool_calls|>",
1104
+ "lstrip": false,
1105
+ "normalized": false,
1106
+ "rstrip": false,
1107
+ "single_word": false
1108
+ },
1109
+ {
1110
+ "content": "<|/tool_calls|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false
1115
+ },
1116
+ {
1117
+ "content": "<|tool_id|>",
1118
+ "lstrip": false,
1119
+ "normalized": false,
1120
+ "rstrip": false,
1121
+ "single_word": false
1122
+ },
1123
+ {
1124
+ "content": "<|/tool_id|>",
1125
+ "lstrip": false,
1126
+ "normalized": false,
1127
+ "rstrip": false,
1128
+ "single_word": false
1129
+ },
1130
+ {
1131
+ "content": "<|code|>",
1132
+ "lstrip": false,
1133
+ "normalized": false,
1134
+ "rstrip": false,
1135
+ "single_word": false
1136
+ },
1137
+ {
1138
+ "content": "<|/code|>",
1139
+ "lstrip": false,
1140
+ "normalized": false,
1141
+ "rstrip": false,
1142
+ "single_word": false
1143
+ },
1144
+ {
1145
+ "content": "<|lang:python|>",
1146
+ "lstrip": false,
1147
+ "normalized": false,
1148
+ "rstrip": false,
1149
+ "single_word": false
1150
+ },
1151
+ {
1152
+ "content": "<|lang:javascript|>",
1153
+ "lstrip": false,
1154
+ "normalized": false,
1155
+ "rstrip": false,
1156
+ "single_word": false
1157
+ },
1158
+ {
1159
+ "content": "<|lang:typescript|>",
1160
+ "lstrip": false,
1161
+ "normalized": false,
1162
+ "rstrip": false,
1163
+ "single_word": false
1164
+ },
1165
+ {
1166
+ "content": "<|lang:java|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false
1171
+ },
1172
+ {
1173
+ "content": "<|lang:cpp|>",
1174
+ "lstrip": false,
1175
+ "normalized": false,
1176
+ "rstrip": false,
1177
+ "single_word": false
1178
+ },
1179
+ {
1180
+ "content": "<|lang:c|>",
1181
+ "lstrip": false,
1182
+ "normalized": false,
1183
+ "rstrip": false,
1184
+ "single_word": false
1185
+ },
1186
+ {
1187
+ "content": "<|lang:csharp|>",
1188
+ "lstrip": false,
1189
+ "normalized": false,
1190
+ "rstrip": false,
1191
+ "single_word": false
1192
+ },
1193
+ {
1194
+ "content": "<|lang:go|>",
1195
+ "lstrip": false,
1196
+ "normalized": false,
1197
+ "rstrip": false,
1198
+ "single_word": false
1199
+ },
1200
+ {
1201
+ "content": "<|lang:rust|>",
1202
+ "lstrip": false,
1203
+ "normalized": false,
1204
+ "rstrip": false,
1205
+ "single_word": false
1206
+ },
1207
+ {
1208
+ "content": "<|lang:ruby|>",
1209
+ "lstrip": false,
1210
+ "normalized": false,
1211
+ "rstrip": false,
1212
+ "single_word": false
1213
+ },
1214
+ {
1215
+ "content": "<|lang:php|>",
1216
+ "lstrip": false,
1217
+ "normalized": false,
1218
+ "rstrip": false,
1219
+ "single_word": false
1220
+ },
1221
+ {
1222
+ "content": "<|lang:swift|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false
1227
+ },
1228
+ {
1229
+ "content": "<|lang:kotlin|>",
1230
+ "lstrip": false,
1231
+ "normalized": false,
1232
+ "rstrip": false,
1233
+ "single_word": false
1234
+ },
1235
+ {
1236
+ "content": "<|lang:scala|>",
1237
+ "lstrip": false,
1238
+ "normalized": false,
1239
+ "rstrip": false,
1240
+ "single_word": false
1241
+ },
1242
+ {
1243
+ "content": "<|lang:shell|>",
1244
+ "lstrip": false,
1245
+ "normalized": false,
1246
+ "rstrip": false,
1247
+ "single_word": false
1248
+ },
1249
+ {
1250
+ "content": "<|lang:bash|>",
1251
+ "lstrip": false,
1252
+ "normalized": false,
1253
+ "rstrip": false,
1254
+ "single_word": false
1255
+ },
1256
+ {
1257
+ "content": "<|lang:sql|>",
1258
+ "lstrip": false,
1259
+ "normalized": false,
1260
+ "rstrip": false,
1261
+ "single_word": false
1262
+ },
1263
+ {
1264
+ "content": "<|lang:r|>",
1265
+ "lstrip": false,
1266
+ "normalized": false,
1267
+ "rstrip": false,
1268
+ "single_word": false
1269
+ },
1270
+ {
1271
+ "content": "<|lang:matlab|>",
1272
+ "lstrip": false,
1273
+ "normalized": false,
1274
+ "rstrip": false,
1275
+ "single_word": false
1276
+ },
1277
+ {
1278
+ "content": "<|lang:lua|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false
1283
+ },
1284
+ {
1285
+ "content": "<|lang:perl|>",
1286
+ "lstrip": false,
1287
+ "normalized": false,
1288
+ "rstrip": false,
1289
+ "single_word": false
1290
+ },
1291
+ {
1292
+ "content": "<|lang:haskell|>",
1293
+ "lstrip": false,
1294
+ "normalized": false,
1295
+ "rstrip": false,
1296
+ "single_word": false
1297
+ },
1298
+ {
1299
+ "content": "<|lang:other|>",
1300
+ "lstrip": false,
1301
+ "normalized": false,
1302
+ "rstrip": false,
1303
+ "single_word": false
1304
+ },
1305
+ {
1306
+ "content": "<|think|>",
1307
+ "lstrip": false,
1308
+ "normalized": false,
1309
+ "rstrip": false,
1310
+ "single_word": false
1311
+ },
1312
+ {
1313
+ "content": "<|/think|>",
1314
+ "lstrip": false,
1315
+ "normalized": false,
1316
+ "rstrip": false,
1317
+ "single_word": false
1318
+ },
1319
+ {
1320
+ "content": "<|observation|>",
1321
+ "lstrip": false,
1322
+ "normalized": false,
1323
+ "rstrip": false,
1324
+ "single_word": false
1325
+ },
1326
+ {
1327
+ "content": "<|/observation|>",
1328
+ "lstrip": false,
1329
+ "normalized": false,
1330
+ "rstrip": false,
1331
+ "single_word": false
1332
+ },
1333
+ {
1334
+ "content": "<|note|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false
1339
+ },
1340
+ {
1341
+ "content": "<|/note|>",
1342
+ "lstrip": false,
1343
+ "normalized": false,
1344
+ "rstrip": false,
1345
+ "single_word": false
1346
+ },
1347
+ {
1348
+ "content": "<|step|>",
1349
+ "lstrip": false,
1350
+ "normalized": false,
1351
+ "rstrip": false,
1352
+ "single_word": false
1353
+ },
1354
+ {
1355
+ "content": "<|/step|>",
1356
+ "lstrip": false,
1357
+ "normalized": false,
1358
+ "rstrip": false,
1359
+ "single_word": false
1360
+ },
1361
+ {
1362
+ "content": "<|reflection|>",
1363
+ "lstrip": false,
1364
+ "normalized": false,
1365
+ "rstrip": false,
1366
+ "single_word": false
1367
+ },
1368
+ {
1369
+ "content": "<|/reflection|>",
1370
+ "lstrip": false,
1371
+ "normalized": false,
1372
+ "rstrip": false,
1373
+ "single_word": false
1374
+ },
1375
+ {
1376
+ "content": "<|hypothesis|>",
1377
+ "lstrip": false,
1378
+ "normalized": false,
1379
+ "rstrip": false,
1380
+ "single_word": false
1381
+ },
1382
+ {
1383
+ "content": "<|/hypothesis|>",
1384
+ "lstrip": false,
1385
+ "normalized": false,
1386
+ "rstrip": false,
1387
+ "single_word": false
1388
+ },
1389
+ {
1390
+ "content": "<|conclusion|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false
1395
+ },
1396
+ {
1397
+ "content": "<|/conclusion|>",
1398
+ "lstrip": false,
1399
+ "normalized": false,
1400
+ "rstrip": false,
1401
+ "single_word": false
1402
+ },
1403
+ {
1404
+ "content": "<|confidence:high|>",
1405
+ "lstrip": false,
1406
+ "normalized": false,
1407
+ "rstrip": false,
1408
+ "single_word": false
1409
+ },
1410
+ {
1411
+ "content": "<|confidence:medium|>",
1412
+ "lstrip": false,
1413
+ "normalized": false,
1414
+ "rstrip": false,
1415
+ "single_word": false
1416
+ },
1417
+ {
1418
+ "content": "<|confidence:low|>",
1419
+ "lstrip": false,
1420
+ "normalized": false,
1421
+ "rstrip": false,
1422
+ "single_word": false
1423
+ },
1424
+ {
1425
+ "content": "<|confidence:uncertain|>",
1426
+ "lstrip": false,
1427
+ "normalized": false,
1428
+ "rstrip": false,
1429
+ "single_word": false
1430
+ },
1431
+ {
1432
+ "content": "<|uncertain|>",
1433
+ "lstrip": false,
1434
+ "normalized": false,
1435
+ "rstrip": false,
1436
+ "single_word": false
1437
+ },
1438
+ {
1439
+ "content": "<|/uncertain|>",
1440
+ "lstrip": false,
1441
+ "normalized": false,
1442
+ "rstrip": false,
1443
+ "single_word": false
1444
+ },
1445
+ {
1446
+ "content": "<|unknown|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false
1451
+ },
1452
+ {
1453
+ "content": "<|need_verify|>",
1454
+ "lstrip": false,
1455
+ "normalized": false,
1456
+ "rstrip": false,
1457
+ "single_word": false
1458
+ },
1459
+ {
1460
+ "content": "<|may_outdated|>",
1461
+ "lstrip": false,
1462
+ "normalized": false,
1463
+ "rstrip": false,
1464
+ "single_word": false
1465
+ },
1466
+ {
1467
+ "content": "<|verify|>",
1468
+ "lstrip": false,
1469
+ "normalized": false,
1470
+ "rstrip": false,
1471
+ "single_word": false
1472
+ },
1473
+ {
1474
+ "content": "<|/verify|>",
1475
+ "lstrip": false,
1476
+ "normalized": false,
1477
+ "rstrip": false,
1478
+ "single_word": false
1479
+ },
1480
+ {
1481
+ "content": "<|fact_check|>",
1482
+ "lstrip": false,
1483
+ "normalized": false,
1484
+ "rstrip": false,
1485
+ "single_word": false
1486
+ },
1487
+ {
1488
+ "content": "<|self_correct|>",
1489
+ "lstrip": false,
1490
+ "normalized": false,
1491
+ "rstrip": false,
1492
+ "single_word": false
1493
+ },
1494
+ {
1495
+ "content": "<|correction|>",
1496
+ "lstrip": false,
1497
+ "normalized": false,
1498
+ "rstrip": false,
1499
+ "single_word": false
1500
+ },
1501
+ {
1502
+ "content": "<|/correction|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false
1507
+ },
1508
+ {
1509
+ "content": "<|cite|>",
1510
+ "lstrip": false,
1511
+ "normalized": false,
1512
+ "rstrip": false,
1513
+ "single_word": false
1514
+ },
1515
+ {
1516
+ "content": "<|/cite|>",
1517
+ "lstrip": false,
1518
+ "normalized": false,
1519
+ "rstrip": false,
1520
+ "single_word": false
1521
+ },
1522
+ {
1523
+ "content": "<|source|>",
1524
+ "lstrip": false,
1525
+ "normalized": false,
1526
+ "rstrip": false,
1527
+ "single_word": false
1528
+ },
1529
+ {
1530
+ "content": "<|/source|>",
1531
+ "lstrip": false,
1532
+ "normalized": false,
1533
+ "rstrip": false,
1534
+ "single_word": false
1535
+ },
1536
+ {
1537
+ "content": "<|ref|>",
1538
+ "lstrip": false,
1539
+ "normalized": false,
1540
+ "rstrip": false,
1541
+ "single_word": false
1542
+ },
1543
+ {
1544
+ "content": "<|/ref|>",
1545
+ "lstrip": false,
1546
+ "normalized": false,
1547
+ "rstrip": false,
1548
+ "single_word": false
1549
+ },
1550
+ {
1551
+ "content": "<|quote|>",
1552
+ "lstrip": false,
1553
+ "normalized": false,
1554
+ "rstrip": false,
1555
+ "single_word": false
1556
+ },
1557
+ {
1558
+ "content": "<|/quote|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false
1563
+ },
1564
+ {
1565
+ "content": "<|context|>",
1566
+ "lstrip": false,
1567
+ "normalized": false,
1568
+ "rstrip": false,
1569
+ "single_word": false
1570
+ },
1571
+ {
1572
+ "content": "<|/context|>",
1573
+ "lstrip": false,
1574
+ "normalized": false,
1575
+ "rstrip": false,
1576
+ "single_word": false
1577
+ },
1578
+ {
1579
+ "content": "<|retrieved|>",
1580
+ "lstrip": false,
1581
+ "normalized": false,
1582
+ "rstrip": false,
1583
+ "single_word": false
1584
+ },
1585
+ {
1586
+ "content": "<|/retrieved|>",
1587
+ "lstrip": false,
1588
+ "normalized": false,
1589
+ "rstrip": false,
1590
+ "single_word": false
1591
+ },
1592
+ {
1593
+ "content": "<|grounded|>",
1594
+ "lstrip": false,
1595
+ "normalized": false,
1596
+ "rstrip": false,
1597
+ "single_word": false
1598
+ },
1599
+ {
1600
+ "content": "<|ungrounded|>",
1601
+ "lstrip": false,
1602
+ "normalized": false,
1603
+ "rstrip": false,
1604
+ "single_word": false
1605
+ },
1606
+ {
1607
+ "content": "<|knowledge_cutoff|>",
1608
+ "lstrip": false,
1609
+ "normalized": false,
1610
+ "rstrip": false,
1611
+ "single_word": false
1612
+ },
1613
+ {
1614
+ "content": "<|beyond_knowledge|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false
1619
+ },
1620
+ {
1621
+ "content": "<|within_knowledge|>",
1622
+ "lstrip": false,
1623
+ "normalized": false,
1624
+ "rstrip": false,
1625
+ "single_word": false
1626
+ },
1627
+ {
1628
+ "content": "<|listen|>",
1629
+ "lstrip": false,
1630
+ "normalized": false,
1631
+ "rstrip": false,
1632
+ "single_word": false
1633
+ },
1634
+ {
1635
+ "content": "<|/listen|>",
1636
+ "lstrip": false,
1637
+ "normalized": false,
1638
+ "rstrip": false,
1639
+ "single_word": false
1640
+ },
1641
+ {
1642
+ "content": "<|speak|>",
1643
+ "lstrip": false,
1644
+ "normalized": false,
1645
+ "rstrip": false,
1646
+ "single_word": false
1647
+ },
1648
+ {
1649
+ "content": "<|/speak|>",
1650
+ "lstrip": false,
1651
+ "normalized": false,
1652
+ "rstrip": false,
1653
+ "single_word": false
1654
+ },
1655
+ {
1656
+ "content": "<|audio|>",
1657
+ "lstrip": false,
1658
+ "normalized": false,
1659
+ "rstrip": false,
1660
+ "single_word": false
1661
+ },
1662
+ {
1663
+ "content": "<|/audio|>",
1664
+ "lstrip": false,
1665
+ "normalized": false,
1666
+ "rstrip": false,
1667
+ "single_word": false
1668
+ },
1669
+ {
1670
+ "content": "<|emotion|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false
1675
+ },
1676
+ {
1677
+ "content": "<|/emotion|>",
1678
+ "lstrip": false,
1679
+ "normalized": false,
1680
+ "rstrip": false,
1681
+ "single_word": false
1682
+ },
1683
+ {
1684
+ "content": "<|emotion:neutral|>",
1685
+ "lstrip": false,
1686
+ "normalized": false,
1687
+ "rstrip": false,
1688
+ "single_word": false
1689
+ },
1690
+ {
1691
+ "content": "<|emotion:happy|>",
1692
+ "lstrip": false,
1693
+ "normalized": false,
1694
+ "rstrip": false,
1695
+ "single_word": false
1696
+ },
1697
+ {
1698
+ "content": "<|emotion:sad|>",
1699
+ "lstrip": false,
1700
+ "normalized": false,
1701
+ "rstrip": false,
1702
+ "single_word": false
1703
+ },
1704
+ {
1705
+ "content": "<|emotion:angry|>",
1706
+ "lstrip": false,
1707
+ "normalized": false,
1708
+ "rstrip": false,
1709
+ "single_word": false
1710
+ },
1711
+ {
1712
+ "content": "<|emotion:surprised|>",
1713
+ "lstrip": false,
1714
+ "normalized": false,
1715
+ "rstrip": false,
1716
+ "single_word": false
1717
+ },
1718
+ {
1719
+ "content": "<|emotion:fearful|>",
1720
+ "lstrip": false,
1721
+ "normalized": false,
1722
+ "rstrip": false,
1723
+ "single_word": false
1724
+ },
1725
+ {
1726
+ "content": "<|emotion:disgusted|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false
1731
+ },
1732
+ {
1733
+ "content": "<|emotion:calm|>",
1734
+ "lstrip": false,
1735
+ "normalized": false,
1736
+ "rstrip": false,
1737
+ "single_word": false
1738
+ },
1739
+ {
1740
+ "content": "<|emotion:excited|>",
1741
+ "lstrip": false,
1742
+ "normalized": false,
1743
+ "rstrip": false,
1744
+ "single_word": false
1745
+ },
1746
+ {
1747
+ "content": "<|emotion:curious|>",
1748
+ "lstrip": false,
1749
+ "normalized": false,
1750
+ "rstrip": false,
1751
+ "single_word": false
1752
+ },
1753
+ {
1754
+ "content": "<|emotion:sympathetic|>",
1755
+ "lstrip": false,
1756
+ "normalized": false,
1757
+ "rstrip": false,
1758
+ "single_word": false
1759
+ },
1760
+ {
1761
+ "content": "<|emotion:confident|>",
1762
+ "lstrip": false,
1763
+ "normalized": false,
1764
+ "rstrip": false,
1765
+ "single_word": false
1766
+ },
1767
+ {
1768
+ "content": "<|prosody|>",
1769
+ "lstrip": false,
1770
+ "normalized": false,
1771
+ "rstrip": false,
1772
+ "single_word": false
1773
+ },
1774
+ {
1775
+ "content": "<|/prosody|>",
1776
+ "lstrip": false,
1777
+ "normalized": false,
1778
+ "rstrip": false,
1779
+ "single_word": false
1780
+ },
1781
+ {
1782
+ "content": "<|prosody:fast|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false
1787
+ },
1788
+ {
1789
+ "content": "<|prosody:slow|>",
1790
+ "lstrip": false,
1791
+ "normalized": false,
1792
+ "rstrip": false,
1793
+ "single_word": false
1794
+ },
1795
+ {
1796
+ "content": "<|prosody:normal_speed|>",
1797
+ "lstrip": false,
1798
+ "normalized": false,
1799
+ "rstrip": false,
1800
+ "single_word": false
1801
+ },
1802
+ {
1803
+ "content": "<|prosody:loud|>",
1804
+ "lstrip": false,
1805
+ "normalized": false,
1806
+ "rstrip": false,
1807
+ "single_word": false
1808
+ },
1809
+ {
1810
+ "content": "<|prosody:soft|>",
1811
+ "lstrip": false,
1812
+ "normalized": false,
1813
+ "rstrip": false,
1814
+ "single_word": false
1815
+ },
1816
+ {
1817
+ "content": "<|prosody:whisper|>",
1818
+ "lstrip": false,
1819
+ "normalized": false,
1820
+ "rstrip": false,
1821
+ "single_word": false
1822
+ },
1823
+ {
1824
+ "content": "<|prosody:normal_volume|>",
1825
+ "lstrip": false,
1826
+ "normalized": false,
1827
+ "rstrip": false,
1828
+ "single_word": false
1829
+ },
1830
+ {
1831
+ "content": "<|prosody:high_pitch|>",
1832
+ "lstrip": false,
1833
+ "normalized": false,
1834
+ "rstrip": false,
1835
+ "single_word": false
1836
+ },
1837
+ {
1838
+ "content": "<|prosody:low_pitch|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false
1843
+ },
1844
+ {
1845
+ "content": "<|prosody:normal_pitch|>",
1846
+ "lstrip": false,
1847
+ "normalized": false,
1848
+ "rstrip": false,
1849
+ "single_word": false
1850
+ },
1851
+ {
1852
+ "content": "<|prosody:emphasis|>",
1853
+ "lstrip": false,
1854
+ "normalized": false,
1855
+ "rstrip": false,
1856
+ "single_word": false
1857
+ },
1858
+ {
1859
+ "content": "<|prosody:pause_short|>",
1860
+ "lstrip": false,
1861
+ "normalized": false,
1862
+ "rstrip": false,
1863
+ "single_word": false
1864
+ },
1865
+ {
1866
+ "content": "<|prosody:pause_long|>",
1867
+ "lstrip": false,
1868
+ "normalized": false,
1869
+ "rstrip": false,
1870
+ "single_word": false
1871
+ },
1872
+ {
1873
+ "content": "<|sep|>",
1874
+ "lstrip": false,
1875
+ "normalized": false,
1876
+ "rstrip": false,
1877
+ "single_word": false
1878
+ },
1879
+ {
1880
+ "content": "<|nl|>",
1881
+ "lstrip": false,
1882
+ "normalized": false,
1883
+ "rstrip": false,
1884
+ "single_word": false
1885
+ },
1886
+ {
1887
+ "content": "<|mask|>",
1888
+ "lstrip": false,
1889
+ "normalized": false,
1890
+ "rstrip": false,
1891
+ "single_word": false
1892
+ }
1893
+ ],
1894
+ "bos_token": "<|bos|>",
1895
+ "eos_token": "<|eos|>",
1896
+ "pad_token": "<|pad|>"
1897
+ }
tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:07134de730f10d8b2931f89cd086b374dbbba1a3ce6d2431b38d94584daad60a
3
+ size 11472555
tokenizer_config.json ADDED
@@ -0,0 +1,2584 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": true
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": true
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": true
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": true
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": true
180
+ },
181
+ "151665": {
182
+ "content": "<|bos|>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": true
188
+ },
189
+ "151666": {
190
+ "content": "<|eos|>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": true
196
+ },
197
+ "151667": {
198
+ "content": "<|pad|>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": true
204
+ },
205
+ "151668": {
206
+ "content": "<|prompt|>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": true
212
+ },
213
+ "151669": {
214
+ "content": "<|/prompt|>",
215
+ "lstrip": false,
216
+ "normalized": false,
217
+ "rstrip": false,
218
+ "single_word": false,
219
+ "special": true
220
+ },
221
+ "151670": {
222
+ "content": "<|text|>",
223
+ "lstrip": false,
224
+ "normalized": false,
225
+ "rstrip": false,
226
+ "single_word": false,
227
+ "special": true
228
+ },
229
+ "151671": {
230
+ "content": "<|/text|>",
231
+ "lstrip": false,
232
+ "normalized": false,
233
+ "rstrip": false,
234
+ "single_word": false,
235
+ "special": true
236
+ },
237
+ "151672": {
238
+ "content": "<|response|>",
239
+ "lstrip": false,
240
+ "normalized": false,
241
+ "rstrip": false,
242
+ "single_word": false,
243
+ "special": true
244
+ },
245
+ "151673": {
246
+ "content": "<|/response|>",
247
+ "lstrip": false,
248
+ "normalized": false,
249
+ "rstrip": false,
250
+ "single_word": false,
251
+ "special": true
252
+ },
253
+ "151674": {
254
+ "content": "<|system|>",
255
+ "lstrip": false,
256
+ "normalized": false,
257
+ "rstrip": false,
258
+ "single_word": false,
259
+ "special": true
260
+ },
261
+ "151675": {
262
+ "content": "<|/system|>",
263
+ "lstrip": false,
264
+ "normalized": false,
265
+ "rstrip": false,
266
+ "single_word": false,
267
+ "special": true
268
+ },
269
+ "151676": {
270
+ "content": "<|user|>",
271
+ "lstrip": false,
272
+ "normalized": false,
273
+ "rstrip": false,
274
+ "single_word": false,
275
+ "special": true
276
+ },
277
+ "151677": {
278
+ "content": "<|/user|>",
279
+ "lstrip": false,
280
+ "normalized": false,
281
+ "rstrip": false,
282
+ "single_word": false,
283
+ "special": true
284
+ },
285
+ "151678": {
286
+ "content": "<|assistant|>",
287
+ "lstrip": false,
288
+ "normalized": false,
289
+ "rstrip": false,
290
+ "single_word": false,
291
+ "special": true
292
+ },
293
+ "151679": {
294
+ "content": "<|/assistant|>",
295
+ "lstrip": false,
296
+ "normalized": false,
297
+ "rstrip": false,
298
+ "single_word": false,
299
+ "special": true
300
+ },
301
+ "151680": {
302
+ "content": "<|commit_before|>",
303
+ "lstrip": false,
304
+ "normalized": false,
305
+ "rstrip": false,
306
+ "single_word": false,
307
+ "special": true
308
+ },
309
+ "151681": {
310
+ "content": "<|/commit_before|>",
311
+ "lstrip": false,
312
+ "normalized": false,
313
+ "rstrip": false,
314
+ "single_word": false,
315
+ "special": true
316
+ },
317
+ "151682": {
318
+ "content": "<|commit_after|>",
319
+ "lstrip": false,
320
+ "normalized": false,
321
+ "rstrip": false,
322
+ "single_word": false,
323
+ "special": true
324
+ },
325
+ "151683": {
326
+ "content": "<|/commit_after|>",
327
+ "lstrip": false,
328
+ "normalized": false,
329
+ "rstrip": false,
330
+ "single_word": false,
331
+ "special": true
332
+ },
333
+ "151684": {
334
+ "content": "<|commit_msg|>",
335
+ "lstrip": false,
336
+ "normalized": false,
337
+ "rstrip": false,
338
+ "single_word": false,
339
+ "special": true
340
+ },
341
+ "151685": {
342
+ "content": "<|/commit_msg|>",
343
+ "lstrip": false,
344
+ "normalized": false,
345
+ "rstrip": false,
346
+ "single_word": false,
347
+ "special": true
348
+ },
349
+ "151686": {
350
+ "content": "<|diff|>",
351
+ "lstrip": false,
352
+ "normalized": false,
353
+ "rstrip": false,
354
+ "single_word": false,
355
+ "special": true
356
+ },
357
+ "151687": {
358
+ "content": "<|/diff|>",
359
+ "lstrip": false,
360
+ "normalized": false,
361
+ "rstrip": false,
362
+ "single_word": false,
363
+ "special": true
364
+ },
365
+ "151688": {
366
+ "content": "<|diff_add|>",
367
+ "lstrip": false,
368
+ "normalized": false,
369
+ "rstrip": false,
370
+ "single_word": false,
371
+ "special": true
372
+ },
373
+ "151689": {
374
+ "content": "<|diff_del|>",
375
+ "lstrip": false,
376
+ "normalized": false,
377
+ "rstrip": false,
378
+ "single_word": false,
379
+ "special": true
380
+ },
381
+ "151690": {
382
+ "content": "<|diff_ctx|>",
383
+ "lstrip": false,
384
+ "normalized": false,
385
+ "rstrip": false,
386
+ "single_word": false,
387
+ "special": true
388
+ },
389
+ "151691": {
390
+ "content": "<|reponame|>",
391
+ "lstrip": false,
392
+ "normalized": false,
393
+ "rstrip": false,
394
+ "single_word": false,
395
+ "special": true
396
+ },
397
+ "151692": {
398
+ "content": "<|/reponame|>",
399
+ "lstrip": false,
400
+ "normalized": false,
401
+ "rstrip": false,
402
+ "single_word": false,
403
+ "special": true
404
+ },
405
+ "151693": {
406
+ "content": "<|gh_stars|>",
407
+ "lstrip": false,
408
+ "normalized": false,
409
+ "rstrip": false,
410
+ "single_word": false,
411
+ "special": true
412
+ },
413
+ "151694": {
414
+ "content": "<|/gh_stars|>",
415
+ "lstrip": false,
416
+ "normalized": false,
417
+ "rstrip": false,
418
+ "single_word": false,
419
+ "special": true
420
+ },
421
+ "151695": {
422
+ "content": "<|branch|>",
423
+ "lstrip": false,
424
+ "normalized": false,
425
+ "rstrip": false,
426
+ "single_word": false,
427
+ "special": true
428
+ },
429
+ "151696": {
430
+ "content": "<|/branch|>",
431
+ "lstrip": false,
432
+ "normalized": false,
433
+ "rstrip": false,
434
+ "single_word": false,
435
+ "special": true
436
+ },
437
+ "151697": {
438
+ "content": "<|issue|>",
439
+ "lstrip": false,
440
+ "normalized": false,
441
+ "rstrip": false,
442
+ "single_word": false,
443
+ "special": true
444
+ },
445
+ "151698": {
446
+ "content": "<|/issue|>",
447
+ "lstrip": false,
448
+ "normalized": false,
449
+ "rstrip": false,
450
+ "single_word": false,
451
+ "special": true
452
+ },
453
+ "151699": {
454
+ "content": "<|issue_title|>",
455
+ "lstrip": false,
456
+ "normalized": false,
457
+ "rstrip": false,
458
+ "single_word": false,
459
+ "special": true
460
+ },
461
+ "151700": {
462
+ "content": "<|/issue_title|>",
463
+ "lstrip": false,
464
+ "normalized": false,
465
+ "rstrip": false,
466
+ "single_word": false,
467
+ "special": true
468
+ },
469
+ "151701": {
470
+ "content": "<|issue_body|>",
471
+ "lstrip": false,
472
+ "normalized": false,
473
+ "rstrip": false,
474
+ "single_word": false,
475
+ "special": true
476
+ },
477
+ "151702": {
478
+ "content": "<|/issue_body|>",
479
+ "lstrip": false,
480
+ "normalized": false,
481
+ "rstrip": false,
482
+ "single_word": false,
483
+ "special": true
484
+ },
485
+ "151703": {
486
+ "content": "<|issue_closed|>",
487
+ "lstrip": false,
488
+ "normalized": false,
489
+ "rstrip": false,
490
+ "single_word": false,
491
+ "special": true
492
+ },
493
+ "151704": {
494
+ "content": "<|issue_open|>",
495
+ "lstrip": false,
496
+ "normalized": false,
497
+ "rstrip": false,
498
+ "single_word": false,
499
+ "special": true
500
+ },
501
+ "151705": {
502
+ "content": "<|pr|>",
503
+ "lstrip": false,
504
+ "normalized": false,
505
+ "rstrip": false,
506
+ "single_word": false,
507
+ "special": true
508
+ },
509
+ "151706": {
510
+ "content": "<|/pr|>",
511
+ "lstrip": false,
512
+ "normalized": false,
513
+ "rstrip": false,
514
+ "single_word": false,
515
+ "special": true
516
+ },
517
+ "151707": {
518
+ "content": "<|pr_title|>",
519
+ "lstrip": false,
520
+ "normalized": false,
521
+ "rstrip": false,
522
+ "single_word": false,
523
+ "special": true
524
+ },
525
+ "151708": {
526
+ "content": "<|/pr_title|>",
527
+ "lstrip": false,
528
+ "normalized": false,
529
+ "rstrip": false,
530
+ "single_word": false,
531
+ "special": true
532
+ },
533
+ "151709": {
534
+ "content": "<|pr_body|>",
535
+ "lstrip": false,
536
+ "normalized": false,
537
+ "rstrip": false,
538
+ "single_word": false,
539
+ "special": true
540
+ },
541
+ "151710": {
542
+ "content": "<|/pr_body|>",
543
+ "lstrip": false,
544
+ "normalized": false,
545
+ "rstrip": false,
546
+ "single_word": false,
547
+ "special": true
548
+ },
549
+ "151711": {
550
+ "content": "<|pr_merged|>",
551
+ "lstrip": false,
552
+ "normalized": false,
553
+ "rstrip": false,
554
+ "single_word": false,
555
+ "special": true
556
+ },
557
+ "151712": {
558
+ "content": "<|pr_closed|>",
559
+ "lstrip": false,
560
+ "normalized": false,
561
+ "rstrip": false,
562
+ "single_word": false,
563
+ "special": true
564
+ },
565
+ "151713": {
566
+ "content": "<|jupyter|>",
567
+ "lstrip": false,
568
+ "normalized": false,
569
+ "rstrip": false,
570
+ "single_word": false,
571
+ "special": true
572
+ },
573
+ "151714": {
574
+ "content": "<|/jupyter|>",
575
+ "lstrip": false,
576
+ "normalized": false,
577
+ "rstrip": false,
578
+ "single_word": false,
579
+ "special": true
580
+ },
581
+ "151715": {
582
+ "content": "<|jupyter_code|>",
583
+ "lstrip": false,
584
+ "normalized": false,
585
+ "rstrip": false,
586
+ "single_word": false,
587
+ "special": true
588
+ },
589
+ "151716": {
590
+ "content": "<|/jupyter_code|>",
591
+ "lstrip": false,
592
+ "normalized": false,
593
+ "rstrip": false,
594
+ "single_word": false,
595
+ "special": true
596
+ },
597
+ "151717": {
598
+ "content": "<|jupyter_output|>",
599
+ "lstrip": false,
600
+ "normalized": false,
601
+ "rstrip": false,
602
+ "single_word": false,
603
+ "special": true
604
+ },
605
+ "151718": {
606
+ "content": "<|/jupyter_output|>",
607
+ "lstrip": false,
608
+ "normalized": false,
609
+ "rstrip": false,
610
+ "single_word": false,
611
+ "special": true
612
+ },
613
+ "151719": {
614
+ "content": "<|jupyter_text|>",
615
+ "lstrip": false,
616
+ "normalized": false,
617
+ "rstrip": false,
618
+ "single_word": false,
619
+ "special": true
620
+ },
621
+ "151720": {
622
+ "content": "<|/jupyter_text|>",
623
+ "lstrip": false,
624
+ "normalized": false,
625
+ "rstrip": false,
626
+ "single_word": false,
627
+ "special": true
628
+ },
629
+ "151721": {
630
+ "content": "<|jupyter_error|>",
631
+ "lstrip": false,
632
+ "normalized": false,
633
+ "rstrip": false,
634
+ "single_word": false,
635
+ "special": true
636
+ },
637
+ "151722": {
638
+ "content": "<|/jupyter_error|>",
639
+ "lstrip": false,
640
+ "normalized": false,
641
+ "rstrip": false,
642
+ "single_word": false,
643
+ "special": true
644
+ },
645
+ "151723": {
646
+ "content": "<|empty_output|>",
647
+ "lstrip": false,
648
+ "normalized": false,
649
+ "rstrip": false,
650
+ "single_word": false,
651
+ "special": true
652
+ },
653
+ "151724": {
654
+ "content": "<|exec|>",
655
+ "lstrip": false,
656
+ "normalized": false,
657
+ "rstrip": false,
658
+ "single_word": false,
659
+ "special": true
660
+ },
661
+ "151725": {
662
+ "content": "<|/exec|>",
663
+ "lstrip": false,
664
+ "normalized": false,
665
+ "rstrip": false,
666
+ "single_word": false,
667
+ "special": true
668
+ },
669
+ "151726": {
670
+ "content": "<|exec_result|>",
671
+ "lstrip": false,
672
+ "normalized": false,
673
+ "rstrip": false,
674
+ "single_word": false,
675
+ "special": true
676
+ },
677
+ "151727": {
678
+ "content": "<|/exec_result|>",
679
+ "lstrip": false,
680
+ "normalized": false,
681
+ "rstrip": false,
682
+ "single_word": false,
683
+ "special": true
684
+ },
685
+ "151728": {
686
+ "content": "<|exec_error|>",
687
+ "lstrip": false,
688
+ "normalized": false,
689
+ "rstrip": false,
690
+ "single_word": false,
691
+ "special": true
692
+ },
693
+ "151729": {
694
+ "content": "<|/exec_error|>",
695
+ "lstrip": false,
696
+ "normalized": false,
697
+ "rstrip": false,
698
+ "single_word": false,
699
+ "special": true
700
+ },
701
+ "151730": {
702
+ "content": "<|exec_timeout|>",
703
+ "lstrip": false,
704
+ "normalized": false,
705
+ "rstrip": false,
706
+ "single_word": false,
707
+ "special": true
708
+ },
709
+ "151731": {
710
+ "content": "<|add_file|>",
711
+ "lstrip": false,
712
+ "normalized": false,
713
+ "rstrip": false,
714
+ "single_word": false,
715
+ "special": true
716
+ },
717
+ "151732": {
718
+ "content": "<|/add_file|>",
719
+ "lstrip": false,
720
+ "normalized": false,
721
+ "rstrip": false,
722
+ "single_word": false,
723
+ "special": true
724
+ },
725
+ "151733": {
726
+ "content": "<|delete_file|>",
727
+ "lstrip": false,
728
+ "normalized": false,
729
+ "rstrip": false,
730
+ "single_word": false,
731
+ "special": true
732
+ },
733
+ "151734": {
734
+ "content": "<|/delete_file|>",
735
+ "lstrip": false,
736
+ "normalized": false,
737
+ "rstrip": false,
738
+ "single_word": false,
739
+ "special": true
740
+ },
741
+ "151735": {
742
+ "content": "<|rename_file|>",
743
+ "lstrip": false,
744
+ "normalized": false,
745
+ "rstrip": false,
746
+ "single_word": false,
747
+ "special": true
748
+ },
749
+ "151736": {
750
+ "content": "<|/rename_file|>",
751
+ "lstrip": false,
752
+ "normalized": false,
753
+ "rstrip": false,
754
+ "single_word": false,
755
+ "special": true
756
+ },
757
+ "151737": {
758
+ "content": "<|edit_file|>",
759
+ "lstrip": false,
760
+ "normalized": false,
761
+ "rstrip": false,
762
+ "single_word": false,
763
+ "special": true
764
+ },
765
+ "151738": {
766
+ "content": "<|/edit_file|>",
767
+ "lstrip": false,
768
+ "normalized": false,
769
+ "rstrip": false,
770
+ "single_word": false,
771
+ "special": true
772
+ },
773
+ "151739": {
774
+ "content": "<|read_file|>",
775
+ "lstrip": false,
776
+ "normalized": false,
777
+ "rstrip": false,
778
+ "single_word": false,
779
+ "special": true
780
+ },
781
+ "151740": {
782
+ "content": "<|/read_file|>",
783
+ "lstrip": false,
784
+ "normalized": false,
785
+ "rstrip": false,
786
+ "single_word": false,
787
+ "special": true
788
+ },
789
+ "151741": {
790
+ "content": "<|file_content|>",
791
+ "lstrip": false,
792
+ "normalized": false,
793
+ "rstrip": false,
794
+ "single_word": false,
795
+ "special": true
796
+ },
797
+ "151742": {
798
+ "content": "<|/file_content|>",
799
+ "lstrip": false,
800
+ "normalized": false,
801
+ "rstrip": false,
802
+ "single_word": false,
803
+ "special": true
804
+ },
805
+ "151743": {
806
+ "content": "<|edit_range|>",
807
+ "lstrip": false,
808
+ "normalized": false,
809
+ "rstrip": false,
810
+ "single_word": false,
811
+ "special": true
812
+ },
813
+ "151744": {
814
+ "content": "<|/edit_range|>",
815
+ "lstrip": false,
816
+ "normalized": false,
817
+ "rstrip": false,
818
+ "single_word": false,
819
+ "special": true
820
+ },
821
+ "151745": {
822
+ "content": "<|line|>",
823
+ "lstrip": false,
824
+ "normalized": false,
825
+ "rstrip": false,
826
+ "single_word": false,
827
+ "special": true
828
+ },
829
+ "151746": {
830
+ "content": "<|/line|>",
831
+ "lstrip": false,
832
+ "normalized": false,
833
+ "rstrip": false,
834
+ "single_word": false,
835
+ "special": true
836
+ },
837
+ "151747": {
838
+ "content": "<|insert_before|>",
839
+ "lstrip": false,
840
+ "normalized": false,
841
+ "rstrip": false,
842
+ "single_word": false,
843
+ "special": true
844
+ },
845
+ "151748": {
846
+ "content": "<|insert_after|>",
847
+ "lstrip": false,
848
+ "normalized": false,
849
+ "rstrip": false,
850
+ "single_word": false,
851
+ "special": true
852
+ },
853
+ "151749": {
854
+ "content": "<|replace|>",
855
+ "lstrip": false,
856
+ "normalized": false,
857
+ "rstrip": false,
858
+ "single_word": false,
859
+ "special": true
860
+ },
861
+ "151750": {
862
+ "content": "<|/replace|>",
863
+ "lstrip": false,
864
+ "normalized": false,
865
+ "rstrip": false,
866
+ "single_word": false,
867
+ "special": true
868
+ },
869
+ "151751": {
870
+ "content": "[e~[",
871
+ "lstrip": false,
872
+ "normalized": false,
873
+ "rstrip": false,
874
+ "single_word": false,
875
+ "special": true
876
+ },
877
+ "151752": {
878
+ "content": "]~e]",
879
+ "lstrip": false,
880
+ "normalized": false,
881
+ "rstrip": false,
882
+ "single_word": false,
883
+ "special": true
884
+ },
885
+ "151753": {
886
+ "content": "[d~[",
887
+ "lstrip": false,
888
+ "normalized": false,
889
+ "rstrip": false,
890
+ "single_word": false,
891
+ "special": true
892
+ },
893
+ "151754": {
894
+ "content": "]~d]",
895
+ "lstrip": false,
896
+ "normalized": false,
897
+ "rstrip": false,
898
+ "single_word": false,
899
+ "special": true
900
+ },
901
+ "151755": {
902
+ "content": "[p~[",
903
+ "lstrip": false,
904
+ "normalized": false,
905
+ "rstrip": false,
906
+ "single_word": false,
907
+ "special": true
908
+ },
909
+ "151756": {
910
+ "content": "]~p]",
911
+ "lstrip": false,
912
+ "normalized": false,
913
+ "rstrip": false,
914
+ "single_word": false,
915
+ "special": true
916
+ },
917
+ "151757": {
918
+ "content": "]~b]",
919
+ "lstrip": false,
920
+ "normalized": false,
921
+ "rstrip": false,
922
+ "single_word": false,
923
+ "special": true
924
+ },
925
+ "151758": {
926
+ "content": "]~!b[",
927
+ "lstrip": false,
928
+ "normalized": false,
929
+ "rstrip": false,
930
+ "single_word": false,
931
+ "special": true
932
+ },
933
+ "151759": {
934
+ "content": "[m~[",
935
+ "lstrip": false,
936
+ "normalized": false,
937
+ "rstrip": false,
938
+ "single_word": false,
939
+ "special": true
940
+ },
941
+ "151760": {
942
+ "content": "]~m]",
943
+ "lstrip": false,
944
+ "normalized": false,
945
+ "rstrip": false,
946
+ "single_word": false,
947
+ "special": true
948
+ },
949
+ "151761": {
950
+ "content": "<|doc|>",
951
+ "lstrip": false,
952
+ "normalized": false,
953
+ "rstrip": false,
954
+ "single_word": false,
955
+ "special": true
956
+ },
957
+ "151762": {
958
+ "content": "<|/doc|>",
959
+ "lstrip": false,
960
+ "normalized": false,
961
+ "rstrip": false,
962
+ "single_word": false,
963
+ "special": true
964
+ },
965
+ "151763": {
966
+ "content": "<|eod|>",
967
+ "lstrip": false,
968
+ "normalized": false,
969
+ "rstrip": false,
970
+ "single_word": false,
971
+ "special": true
972
+ },
973
+ "151764": {
974
+ "content": "<|file:txt|>",
975
+ "lstrip": false,
976
+ "normalized": false,
977
+ "rstrip": false,
978
+ "single_word": false,
979
+ "special": true
980
+ },
981
+ "151765": {
982
+ "content": "<|/file:txt|>",
983
+ "lstrip": false,
984
+ "normalized": false,
985
+ "rstrip": false,
986
+ "single_word": false,
987
+ "special": true
988
+ },
989
+ "151766": {
990
+ "content": "<|file:md|>",
991
+ "lstrip": false,
992
+ "normalized": false,
993
+ "rstrip": false,
994
+ "single_word": false,
995
+ "special": true
996
+ },
997
+ "151767": {
998
+ "content": "<|/file:md|>",
999
+ "lstrip": false,
1000
+ "normalized": false,
1001
+ "rstrip": false,
1002
+ "single_word": false,
1003
+ "special": true
1004
+ },
1005
+ "151768": {
1006
+ "content": "<|file:json|>",
1007
+ "lstrip": false,
1008
+ "normalized": false,
1009
+ "rstrip": false,
1010
+ "single_word": false,
1011
+ "special": true
1012
+ },
1013
+ "151769": {
1014
+ "content": "<|/file:json|>",
1015
+ "lstrip": false,
1016
+ "normalized": false,
1017
+ "rstrip": false,
1018
+ "single_word": false,
1019
+ "special": true
1020
+ },
1021
+ "151770": {
1022
+ "content": "<|file:xml|>",
1023
+ "lstrip": false,
1024
+ "normalized": false,
1025
+ "rstrip": false,
1026
+ "single_word": false,
1027
+ "special": true
1028
+ },
1029
+ "151771": {
1030
+ "content": "<|/file:xml|>",
1031
+ "lstrip": false,
1032
+ "normalized": false,
1033
+ "rstrip": false,
1034
+ "single_word": false,
1035
+ "special": true
1036
+ },
1037
+ "151772": {
1038
+ "content": "<|file:yaml|>",
1039
+ "lstrip": false,
1040
+ "normalized": false,
1041
+ "rstrip": false,
1042
+ "single_word": false,
1043
+ "special": true
1044
+ },
1045
+ "151773": {
1046
+ "content": "<|/file:yaml|>",
1047
+ "lstrip": false,
1048
+ "normalized": false,
1049
+ "rstrip": false,
1050
+ "single_word": false,
1051
+ "special": true
1052
+ },
1053
+ "151774": {
1054
+ "content": "<|file:html|>",
1055
+ "lstrip": false,
1056
+ "normalized": false,
1057
+ "rstrip": false,
1058
+ "single_word": false,
1059
+ "special": true
1060
+ },
1061
+ "151775": {
1062
+ "content": "<|/file:html|>",
1063
+ "lstrip": false,
1064
+ "normalized": false,
1065
+ "rstrip": false,
1066
+ "single_word": false,
1067
+ "special": true
1068
+ },
1069
+ "151776": {
1070
+ "content": "<|file:css|>",
1071
+ "lstrip": false,
1072
+ "normalized": false,
1073
+ "rstrip": false,
1074
+ "single_word": false,
1075
+ "special": true
1076
+ },
1077
+ "151777": {
1078
+ "content": "<|/file:css|>",
1079
+ "lstrip": false,
1080
+ "normalized": false,
1081
+ "rstrip": false,
1082
+ "single_word": false,
1083
+ "special": true
1084
+ },
1085
+ "151778": {
1086
+ "content": "<|file:csv|>",
1087
+ "lstrip": false,
1088
+ "normalized": false,
1089
+ "rstrip": false,
1090
+ "single_word": false,
1091
+ "special": true
1092
+ },
1093
+ "151779": {
1094
+ "content": "<|/file:csv|>",
1095
+ "lstrip": false,
1096
+ "normalized": false,
1097
+ "rstrip": false,
1098
+ "single_word": false,
1099
+ "special": true
1100
+ },
1101
+ "151780": {
1102
+ "content": "<|file:toml|>",
1103
+ "lstrip": false,
1104
+ "normalized": false,
1105
+ "rstrip": false,
1106
+ "single_word": false,
1107
+ "special": true
1108
+ },
1109
+ "151781": {
1110
+ "content": "<|/file:toml|>",
1111
+ "lstrip": false,
1112
+ "normalized": false,
1113
+ "rstrip": false,
1114
+ "single_word": false,
1115
+ "special": true
1116
+ },
1117
+ "151782": {
1118
+ "content": "<|file:ini|>",
1119
+ "lstrip": false,
1120
+ "normalized": false,
1121
+ "rstrip": false,
1122
+ "single_word": false,
1123
+ "special": true
1124
+ },
1125
+ "151783": {
1126
+ "content": "<|/file:ini|>",
1127
+ "lstrip": false,
1128
+ "normalized": false,
1129
+ "rstrip": false,
1130
+ "single_word": false,
1131
+ "special": true
1132
+ },
1133
+ "151784": {
1134
+ "content": "<|file:log|>",
1135
+ "lstrip": false,
1136
+ "normalized": false,
1137
+ "rstrip": false,
1138
+ "single_word": false,
1139
+ "special": true
1140
+ },
1141
+ "151785": {
1142
+ "content": "<|/file:log|>",
1143
+ "lstrip": false,
1144
+ "normalized": false,
1145
+ "rstrip": false,
1146
+ "single_word": false,
1147
+ "special": true
1148
+ },
1149
+ "151786": {
1150
+ "content": "<|filename|>",
1151
+ "lstrip": false,
1152
+ "normalized": false,
1153
+ "rstrip": false,
1154
+ "single_word": false,
1155
+ "special": true
1156
+ },
1157
+ "151787": {
1158
+ "content": "<|/filename|>",
1159
+ "lstrip": false,
1160
+ "normalized": false,
1161
+ "rstrip": false,
1162
+ "single_word": false,
1163
+ "special": true
1164
+ },
1165
+ "151788": {
1166
+ "content": "<|filepath|>",
1167
+ "lstrip": false,
1168
+ "normalized": false,
1169
+ "rstrip": false,
1170
+ "single_word": false,
1171
+ "special": true
1172
+ },
1173
+ "151789": {
1174
+ "content": "<|/filepath|>",
1175
+ "lstrip": false,
1176
+ "normalized": false,
1177
+ "rstrip": false,
1178
+ "single_word": false,
1179
+ "special": true
1180
+ },
1181
+ "151790": {
1182
+ "content": "<|image|>",
1183
+ "lstrip": false,
1184
+ "normalized": false,
1185
+ "rstrip": false,
1186
+ "single_word": false,
1187
+ "special": true
1188
+ },
1189
+ "151791": {
1190
+ "content": "<|/image|>",
1191
+ "lstrip": false,
1192
+ "normalized": false,
1193
+ "rstrip": false,
1194
+ "single_word": false,
1195
+ "special": true
1196
+ },
1197
+ "151792": {
1198
+ "content": "<|video|>",
1199
+ "lstrip": false,
1200
+ "normalized": false,
1201
+ "rstrip": false,
1202
+ "single_word": false,
1203
+ "special": true
1204
+ },
1205
+ "151793": {
1206
+ "content": "<|/video|>",
1207
+ "lstrip": false,
1208
+ "normalized": false,
1209
+ "rstrip": false,
1210
+ "single_word": false,
1211
+ "special": true
1212
+ },
1213
+ "151794": {
1214
+ "content": "<|gen_image|>",
1215
+ "lstrip": false,
1216
+ "normalized": false,
1217
+ "rstrip": false,
1218
+ "single_word": false,
1219
+ "special": true
1220
+ },
1221
+ "151795": {
1222
+ "content": "<|/gen_image|>",
1223
+ "lstrip": false,
1224
+ "normalized": false,
1225
+ "rstrip": false,
1226
+ "single_word": false,
1227
+ "special": true
1228
+ },
1229
+ "151796": {
1230
+ "content": "<|gen_video|>",
1231
+ "lstrip": false,
1232
+ "normalized": false,
1233
+ "rstrip": false,
1234
+ "single_word": false,
1235
+ "special": true
1236
+ },
1237
+ "151797": {
1238
+ "content": "<|/gen_video|>",
1239
+ "lstrip": false,
1240
+ "normalized": false,
1241
+ "rstrip": false,
1242
+ "single_word": false,
1243
+ "special": true
1244
+ },
1245
+ "151798": {
1246
+ "content": "<|tool_call|>",
1247
+ "lstrip": false,
1248
+ "normalized": false,
1249
+ "rstrip": false,
1250
+ "single_word": false,
1251
+ "special": true
1252
+ },
1253
+ "151799": {
1254
+ "content": "<|/tool_call|>",
1255
+ "lstrip": false,
1256
+ "normalized": false,
1257
+ "rstrip": false,
1258
+ "single_word": false,
1259
+ "special": true
1260
+ },
1261
+ "151800": {
1262
+ "content": "<|tool_result|>",
1263
+ "lstrip": false,
1264
+ "normalized": false,
1265
+ "rstrip": false,
1266
+ "single_word": false,
1267
+ "special": true
1268
+ },
1269
+ "151801": {
1270
+ "content": "<|/tool_result|>",
1271
+ "lstrip": false,
1272
+ "normalized": false,
1273
+ "rstrip": false,
1274
+ "single_word": false,
1275
+ "special": true
1276
+ },
1277
+ "151802": {
1278
+ "content": "<|function_name|>",
1279
+ "lstrip": false,
1280
+ "normalized": false,
1281
+ "rstrip": false,
1282
+ "single_word": false,
1283
+ "special": true
1284
+ },
1285
+ "151803": {
1286
+ "content": "<|/function_name|>",
1287
+ "lstrip": false,
1288
+ "normalized": false,
1289
+ "rstrip": false,
1290
+ "single_word": false,
1291
+ "special": true
1292
+ },
1293
+ "151804": {
1294
+ "content": "<|function_args|>",
1295
+ "lstrip": false,
1296
+ "normalized": false,
1297
+ "rstrip": false,
1298
+ "single_word": false,
1299
+ "special": true
1300
+ },
1301
+ "151805": {
1302
+ "content": "<|/function_args|>",
1303
+ "lstrip": false,
1304
+ "normalized": false,
1305
+ "rstrip": false,
1306
+ "single_word": false,
1307
+ "special": true
1308
+ },
1309
+ "151806": {
1310
+ "content": "<|arg_name|>",
1311
+ "lstrip": false,
1312
+ "normalized": false,
1313
+ "rstrip": false,
1314
+ "single_word": false,
1315
+ "special": true
1316
+ },
1317
+ "151807": {
1318
+ "content": "<|/arg_name|>",
1319
+ "lstrip": false,
1320
+ "normalized": false,
1321
+ "rstrip": false,
1322
+ "single_word": false,
1323
+ "special": true
1324
+ },
1325
+ "151808": {
1326
+ "content": "<|arg_value|>",
1327
+ "lstrip": false,
1328
+ "normalized": false,
1329
+ "rstrip": false,
1330
+ "single_word": false,
1331
+ "special": true
1332
+ },
1333
+ "151809": {
1334
+ "content": "<|/arg_value|>",
1335
+ "lstrip": false,
1336
+ "normalized": false,
1337
+ "rstrip": false,
1338
+ "single_word": false,
1339
+ "special": true
1340
+ },
1341
+ "151810": {
1342
+ "content": "<|tools|>",
1343
+ "lstrip": false,
1344
+ "normalized": false,
1345
+ "rstrip": false,
1346
+ "single_word": false,
1347
+ "special": true
1348
+ },
1349
+ "151811": {
1350
+ "content": "<|/tools|>",
1351
+ "lstrip": false,
1352
+ "normalized": false,
1353
+ "rstrip": false,
1354
+ "single_word": false,
1355
+ "special": true
1356
+ },
1357
+ "151812": {
1358
+ "content": "<|function_def|>",
1359
+ "lstrip": false,
1360
+ "normalized": false,
1361
+ "rstrip": false,
1362
+ "single_word": false,
1363
+ "special": true
1364
+ },
1365
+ "151813": {
1366
+ "content": "<|/function_def|>",
1367
+ "lstrip": false,
1368
+ "normalized": false,
1369
+ "rstrip": false,
1370
+ "single_word": false,
1371
+ "special": true
1372
+ },
1373
+ "151814": {
1374
+ "content": "<|tool_error|>",
1375
+ "lstrip": false,
1376
+ "normalized": false,
1377
+ "rstrip": false,
1378
+ "single_word": false,
1379
+ "special": true
1380
+ },
1381
+ "151815": {
1382
+ "content": "<|/tool_error|>",
1383
+ "lstrip": false,
1384
+ "normalized": false,
1385
+ "rstrip": false,
1386
+ "single_word": false,
1387
+ "special": true
1388
+ },
1389
+ "151816": {
1390
+ "content": "<|tool_success|>",
1391
+ "lstrip": false,
1392
+ "normalized": false,
1393
+ "rstrip": false,
1394
+ "single_word": false,
1395
+ "special": true
1396
+ },
1397
+ "151817": {
1398
+ "content": "<|tool_calls|>",
1399
+ "lstrip": false,
1400
+ "normalized": false,
1401
+ "rstrip": false,
1402
+ "single_word": false,
1403
+ "special": true
1404
+ },
1405
+ "151818": {
1406
+ "content": "<|/tool_calls|>",
1407
+ "lstrip": false,
1408
+ "normalized": false,
1409
+ "rstrip": false,
1410
+ "single_word": false,
1411
+ "special": true
1412
+ },
1413
+ "151819": {
1414
+ "content": "<|tool_id|>",
1415
+ "lstrip": false,
1416
+ "normalized": false,
1417
+ "rstrip": false,
1418
+ "single_word": false,
1419
+ "special": true
1420
+ },
1421
+ "151820": {
1422
+ "content": "<|/tool_id|>",
1423
+ "lstrip": false,
1424
+ "normalized": false,
1425
+ "rstrip": false,
1426
+ "single_word": false,
1427
+ "special": true
1428
+ },
1429
+ "151821": {
1430
+ "content": "<|code|>",
1431
+ "lstrip": false,
1432
+ "normalized": false,
1433
+ "rstrip": false,
1434
+ "single_word": false,
1435
+ "special": true
1436
+ },
1437
+ "151822": {
1438
+ "content": "<|/code|>",
1439
+ "lstrip": false,
1440
+ "normalized": false,
1441
+ "rstrip": false,
1442
+ "single_word": false,
1443
+ "special": true
1444
+ },
1445
+ "151823": {
1446
+ "content": "<|lang:python|>",
1447
+ "lstrip": false,
1448
+ "normalized": false,
1449
+ "rstrip": false,
1450
+ "single_word": false,
1451
+ "special": true
1452
+ },
1453
+ "151824": {
1454
+ "content": "<|lang:javascript|>",
1455
+ "lstrip": false,
1456
+ "normalized": false,
1457
+ "rstrip": false,
1458
+ "single_word": false,
1459
+ "special": true
1460
+ },
1461
+ "151825": {
1462
+ "content": "<|lang:typescript|>",
1463
+ "lstrip": false,
1464
+ "normalized": false,
1465
+ "rstrip": false,
1466
+ "single_word": false,
1467
+ "special": true
1468
+ },
1469
+ "151826": {
1470
+ "content": "<|lang:java|>",
1471
+ "lstrip": false,
1472
+ "normalized": false,
1473
+ "rstrip": false,
1474
+ "single_word": false,
1475
+ "special": true
1476
+ },
1477
+ "151827": {
1478
+ "content": "<|lang:cpp|>",
1479
+ "lstrip": false,
1480
+ "normalized": false,
1481
+ "rstrip": false,
1482
+ "single_word": false,
1483
+ "special": true
1484
+ },
1485
+ "151828": {
1486
+ "content": "<|lang:c|>",
1487
+ "lstrip": false,
1488
+ "normalized": false,
1489
+ "rstrip": false,
1490
+ "single_word": false,
1491
+ "special": true
1492
+ },
1493
+ "151829": {
1494
+ "content": "<|lang:csharp|>",
1495
+ "lstrip": false,
1496
+ "normalized": false,
1497
+ "rstrip": false,
1498
+ "single_word": false,
1499
+ "special": true
1500
+ },
1501
+ "151830": {
1502
+ "content": "<|lang:go|>",
1503
+ "lstrip": false,
1504
+ "normalized": false,
1505
+ "rstrip": false,
1506
+ "single_word": false,
1507
+ "special": true
1508
+ },
1509
+ "151831": {
1510
+ "content": "<|lang:rust|>",
1511
+ "lstrip": false,
1512
+ "normalized": false,
1513
+ "rstrip": false,
1514
+ "single_word": false,
1515
+ "special": true
1516
+ },
1517
+ "151832": {
1518
+ "content": "<|lang:ruby|>",
1519
+ "lstrip": false,
1520
+ "normalized": false,
1521
+ "rstrip": false,
1522
+ "single_word": false,
1523
+ "special": true
1524
+ },
1525
+ "151833": {
1526
+ "content": "<|lang:php|>",
1527
+ "lstrip": false,
1528
+ "normalized": false,
1529
+ "rstrip": false,
1530
+ "single_word": false,
1531
+ "special": true
1532
+ },
1533
+ "151834": {
1534
+ "content": "<|lang:swift|>",
1535
+ "lstrip": false,
1536
+ "normalized": false,
1537
+ "rstrip": false,
1538
+ "single_word": false,
1539
+ "special": true
1540
+ },
1541
+ "151835": {
1542
+ "content": "<|lang:kotlin|>",
1543
+ "lstrip": false,
1544
+ "normalized": false,
1545
+ "rstrip": false,
1546
+ "single_word": false,
1547
+ "special": true
1548
+ },
1549
+ "151836": {
1550
+ "content": "<|lang:scala|>",
1551
+ "lstrip": false,
1552
+ "normalized": false,
1553
+ "rstrip": false,
1554
+ "single_word": false,
1555
+ "special": true
1556
+ },
1557
+ "151837": {
1558
+ "content": "<|lang:shell|>",
1559
+ "lstrip": false,
1560
+ "normalized": false,
1561
+ "rstrip": false,
1562
+ "single_word": false,
1563
+ "special": true
1564
+ },
1565
+ "151838": {
1566
+ "content": "<|lang:bash|>",
1567
+ "lstrip": false,
1568
+ "normalized": false,
1569
+ "rstrip": false,
1570
+ "single_word": false,
1571
+ "special": true
1572
+ },
1573
+ "151839": {
1574
+ "content": "<|lang:sql|>",
1575
+ "lstrip": false,
1576
+ "normalized": false,
1577
+ "rstrip": false,
1578
+ "single_word": false,
1579
+ "special": true
1580
+ },
1581
+ "151840": {
1582
+ "content": "<|lang:r|>",
1583
+ "lstrip": false,
1584
+ "normalized": false,
1585
+ "rstrip": false,
1586
+ "single_word": false,
1587
+ "special": true
1588
+ },
1589
+ "151841": {
1590
+ "content": "<|lang:matlab|>",
1591
+ "lstrip": false,
1592
+ "normalized": false,
1593
+ "rstrip": false,
1594
+ "single_word": false,
1595
+ "special": true
1596
+ },
1597
+ "151842": {
1598
+ "content": "<|lang:lua|>",
1599
+ "lstrip": false,
1600
+ "normalized": false,
1601
+ "rstrip": false,
1602
+ "single_word": false,
1603
+ "special": true
1604
+ },
1605
+ "151843": {
1606
+ "content": "<|lang:perl|>",
1607
+ "lstrip": false,
1608
+ "normalized": false,
1609
+ "rstrip": false,
1610
+ "single_word": false,
1611
+ "special": true
1612
+ },
1613
+ "151844": {
1614
+ "content": "<|lang:haskell|>",
1615
+ "lstrip": false,
1616
+ "normalized": false,
1617
+ "rstrip": false,
1618
+ "single_word": false,
1619
+ "special": true
1620
+ },
1621
+ "151845": {
1622
+ "content": "<|lang:other|>",
1623
+ "lstrip": false,
1624
+ "normalized": false,
1625
+ "rstrip": false,
1626
+ "single_word": false,
1627
+ "special": true
1628
+ },
1629
+ "151846": {
1630
+ "content": "<|think|>",
1631
+ "lstrip": false,
1632
+ "normalized": false,
1633
+ "rstrip": false,
1634
+ "single_word": false,
1635
+ "special": true
1636
+ },
1637
+ "151847": {
1638
+ "content": "<|/think|>",
1639
+ "lstrip": false,
1640
+ "normalized": false,
1641
+ "rstrip": false,
1642
+ "single_word": false,
1643
+ "special": true
1644
+ },
1645
+ "151848": {
1646
+ "content": "<|observation|>",
1647
+ "lstrip": false,
1648
+ "normalized": false,
1649
+ "rstrip": false,
1650
+ "single_word": false,
1651
+ "special": true
1652
+ },
1653
+ "151849": {
1654
+ "content": "<|/observation|>",
1655
+ "lstrip": false,
1656
+ "normalized": false,
1657
+ "rstrip": false,
1658
+ "single_word": false,
1659
+ "special": true
1660
+ },
1661
+ "151850": {
1662
+ "content": "<|note|>",
1663
+ "lstrip": false,
1664
+ "normalized": false,
1665
+ "rstrip": false,
1666
+ "single_word": false,
1667
+ "special": true
1668
+ },
1669
+ "151851": {
1670
+ "content": "<|/note|>",
1671
+ "lstrip": false,
1672
+ "normalized": false,
1673
+ "rstrip": false,
1674
+ "single_word": false,
1675
+ "special": true
1676
+ },
1677
+ "151852": {
1678
+ "content": "<|step|>",
1679
+ "lstrip": false,
1680
+ "normalized": false,
1681
+ "rstrip": false,
1682
+ "single_word": false,
1683
+ "special": true
1684
+ },
1685
+ "151853": {
1686
+ "content": "<|/step|>",
1687
+ "lstrip": false,
1688
+ "normalized": false,
1689
+ "rstrip": false,
1690
+ "single_word": false,
1691
+ "special": true
1692
+ },
1693
+ "151854": {
1694
+ "content": "<|reflection|>",
1695
+ "lstrip": false,
1696
+ "normalized": false,
1697
+ "rstrip": false,
1698
+ "single_word": false,
1699
+ "special": true
1700
+ },
1701
+ "151855": {
1702
+ "content": "<|/reflection|>",
1703
+ "lstrip": false,
1704
+ "normalized": false,
1705
+ "rstrip": false,
1706
+ "single_word": false,
1707
+ "special": true
1708
+ },
1709
+ "151856": {
1710
+ "content": "<|hypothesis|>",
1711
+ "lstrip": false,
1712
+ "normalized": false,
1713
+ "rstrip": false,
1714
+ "single_word": false,
1715
+ "special": true
1716
+ },
1717
+ "151857": {
1718
+ "content": "<|/hypothesis|>",
1719
+ "lstrip": false,
1720
+ "normalized": false,
1721
+ "rstrip": false,
1722
+ "single_word": false,
1723
+ "special": true
1724
+ },
1725
+ "151858": {
1726
+ "content": "<|conclusion|>",
1727
+ "lstrip": false,
1728
+ "normalized": false,
1729
+ "rstrip": false,
1730
+ "single_word": false,
1731
+ "special": true
1732
+ },
1733
+ "151859": {
1734
+ "content": "<|/conclusion|>",
1735
+ "lstrip": false,
1736
+ "normalized": false,
1737
+ "rstrip": false,
1738
+ "single_word": false,
1739
+ "special": true
1740
+ },
1741
+ "151860": {
1742
+ "content": "<|confidence:high|>",
1743
+ "lstrip": false,
1744
+ "normalized": false,
1745
+ "rstrip": false,
1746
+ "single_word": false,
1747
+ "special": true
1748
+ },
1749
+ "151861": {
1750
+ "content": "<|confidence:medium|>",
1751
+ "lstrip": false,
1752
+ "normalized": false,
1753
+ "rstrip": false,
1754
+ "single_word": false,
1755
+ "special": true
1756
+ },
1757
+ "151862": {
1758
+ "content": "<|confidence:low|>",
1759
+ "lstrip": false,
1760
+ "normalized": false,
1761
+ "rstrip": false,
1762
+ "single_word": false,
1763
+ "special": true
1764
+ },
1765
+ "151863": {
1766
+ "content": "<|confidence:uncertain|>",
1767
+ "lstrip": false,
1768
+ "normalized": false,
1769
+ "rstrip": false,
1770
+ "single_word": false,
1771
+ "special": true
1772
+ },
1773
+ "151864": {
1774
+ "content": "<|uncertain|>",
1775
+ "lstrip": false,
1776
+ "normalized": false,
1777
+ "rstrip": false,
1778
+ "single_word": false,
1779
+ "special": true
1780
+ },
1781
+ "151865": {
1782
+ "content": "<|/uncertain|>",
1783
+ "lstrip": false,
1784
+ "normalized": false,
1785
+ "rstrip": false,
1786
+ "single_word": false,
1787
+ "special": true
1788
+ },
1789
+ "151866": {
1790
+ "content": "<|unknown|>",
1791
+ "lstrip": false,
1792
+ "normalized": false,
1793
+ "rstrip": false,
1794
+ "single_word": false,
1795
+ "special": true
1796
+ },
1797
+ "151867": {
1798
+ "content": "<|need_verify|>",
1799
+ "lstrip": false,
1800
+ "normalized": false,
1801
+ "rstrip": false,
1802
+ "single_word": false,
1803
+ "special": true
1804
+ },
1805
+ "151868": {
1806
+ "content": "<|may_outdated|>",
1807
+ "lstrip": false,
1808
+ "normalized": false,
1809
+ "rstrip": false,
1810
+ "single_word": false,
1811
+ "special": true
1812
+ },
1813
+ "151869": {
1814
+ "content": "<|verify|>",
1815
+ "lstrip": false,
1816
+ "normalized": false,
1817
+ "rstrip": false,
1818
+ "single_word": false,
1819
+ "special": true
1820
+ },
1821
+ "151870": {
1822
+ "content": "<|/verify|>",
1823
+ "lstrip": false,
1824
+ "normalized": false,
1825
+ "rstrip": false,
1826
+ "single_word": false,
1827
+ "special": true
1828
+ },
1829
+ "151871": {
1830
+ "content": "<|fact_check|>",
1831
+ "lstrip": false,
1832
+ "normalized": false,
1833
+ "rstrip": false,
1834
+ "single_word": false,
1835
+ "special": true
1836
+ },
1837
+ "151872": {
1838
+ "content": "<|self_correct|>",
1839
+ "lstrip": false,
1840
+ "normalized": false,
1841
+ "rstrip": false,
1842
+ "single_word": false,
1843
+ "special": true
1844
+ },
1845
+ "151873": {
1846
+ "content": "<|correction|>",
1847
+ "lstrip": false,
1848
+ "normalized": false,
1849
+ "rstrip": false,
1850
+ "single_word": false,
1851
+ "special": true
1852
+ },
1853
+ "151874": {
1854
+ "content": "<|/correction|>",
1855
+ "lstrip": false,
1856
+ "normalized": false,
1857
+ "rstrip": false,
1858
+ "single_word": false,
1859
+ "special": true
1860
+ },
1861
+ "151875": {
1862
+ "content": "<|cite|>",
1863
+ "lstrip": false,
1864
+ "normalized": false,
1865
+ "rstrip": false,
1866
+ "single_word": false,
1867
+ "special": true
1868
+ },
1869
+ "151876": {
1870
+ "content": "<|/cite|>",
1871
+ "lstrip": false,
1872
+ "normalized": false,
1873
+ "rstrip": false,
1874
+ "single_word": false,
1875
+ "special": true
1876
+ },
1877
+ "151877": {
1878
+ "content": "<|source|>",
1879
+ "lstrip": false,
1880
+ "normalized": false,
1881
+ "rstrip": false,
1882
+ "single_word": false,
1883
+ "special": true
1884
+ },
1885
+ "151878": {
1886
+ "content": "<|/source|>",
1887
+ "lstrip": false,
1888
+ "normalized": false,
1889
+ "rstrip": false,
1890
+ "single_word": false,
1891
+ "special": true
1892
+ },
1893
+ "151879": {
1894
+ "content": "<|ref|>",
1895
+ "lstrip": false,
1896
+ "normalized": false,
1897
+ "rstrip": false,
1898
+ "single_word": false,
1899
+ "special": true
1900
+ },
1901
+ "151880": {
1902
+ "content": "<|/ref|>",
1903
+ "lstrip": false,
1904
+ "normalized": false,
1905
+ "rstrip": false,
1906
+ "single_word": false,
1907
+ "special": true
1908
+ },
1909
+ "151881": {
1910
+ "content": "<|quote|>",
1911
+ "lstrip": false,
1912
+ "normalized": false,
1913
+ "rstrip": false,
1914
+ "single_word": false,
1915
+ "special": true
1916
+ },
1917
+ "151882": {
1918
+ "content": "<|/quote|>",
1919
+ "lstrip": false,
1920
+ "normalized": false,
1921
+ "rstrip": false,
1922
+ "single_word": false,
1923
+ "special": true
1924
+ },
1925
+ "151883": {
1926
+ "content": "<|context|>",
1927
+ "lstrip": false,
1928
+ "normalized": false,
1929
+ "rstrip": false,
1930
+ "single_word": false,
1931
+ "special": true
1932
+ },
1933
+ "151884": {
1934
+ "content": "<|/context|>",
1935
+ "lstrip": false,
1936
+ "normalized": false,
1937
+ "rstrip": false,
1938
+ "single_word": false,
1939
+ "special": true
1940
+ },
1941
+ "151885": {
1942
+ "content": "<|retrieved|>",
1943
+ "lstrip": false,
1944
+ "normalized": false,
1945
+ "rstrip": false,
1946
+ "single_word": false,
1947
+ "special": true
1948
+ },
1949
+ "151886": {
1950
+ "content": "<|/retrieved|>",
1951
+ "lstrip": false,
1952
+ "normalized": false,
1953
+ "rstrip": false,
1954
+ "single_word": false,
1955
+ "special": true
1956
+ },
1957
+ "151887": {
1958
+ "content": "<|grounded|>",
1959
+ "lstrip": false,
1960
+ "normalized": false,
1961
+ "rstrip": false,
1962
+ "single_word": false,
1963
+ "special": true
1964
+ },
1965
+ "151888": {
1966
+ "content": "<|ungrounded|>",
1967
+ "lstrip": false,
1968
+ "normalized": false,
1969
+ "rstrip": false,
1970
+ "single_word": false,
1971
+ "special": true
1972
+ },
1973
+ "151889": {
1974
+ "content": "<|knowledge_cutoff|>",
1975
+ "lstrip": false,
1976
+ "normalized": false,
1977
+ "rstrip": false,
1978
+ "single_word": false,
1979
+ "special": true
1980
+ },
1981
+ "151890": {
1982
+ "content": "<|beyond_knowledge|>",
1983
+ "lstrip": false,
1984
+ "normalized": false,
1985
+ "rstrip": false,
1986
+ "single_word": false,
1987
+ "special": true
1988
+ },
1989
+ "151891": {
1990
+ "content": "<|within_knowledge|>",
1991
+ "lstrip": false,
1992
+ "normalized": false,
1993
+ "rstrip": false,
1994
+ "single_word": false,
1995
+ "special": true
1996
+ },
1997
+ "151892": {
1998
+ "content": "<|listen|>",
1999
+ "lstrip": false,
2000
+ "normalized": false,
2001
+ "rstrip": false,
2002
+ "single_word": false,
2003
+ "special": true
2004
+ },
2005
+ "151893": {
2006
+ "content": "<|/listen|>",
2007
+ "lstrip": false,
2008
+ "normalized": false,
2009
+ "rstrip": false,
2010
+ "single_word": false,
2011
+ "special": true
2012
+ },
2013
+ "151894": {
2014
+ "content": "<|speak|>",
2015
+ "lstrip": false,
2016
+ "normalized": false,
2017
+ "rstrip": false,
2018
+ "single_word": false,
2019
+ "special": true
2020
+ },
2021
+ "151895": {
2022
+ "content": "<|/speak|>",
2023
+ "lstrip": false,
2024
+ "normalized": false,
2025
+ "rstrip": false,
2026
+ "single_word": false,
2027
+ "special": true
2028
+ },
2029
+ "151896": {
2030
+ "content": "<|audio|>",
2031
+ "lstrip": false,
2032
+ "normalized": false,
2033
+ "rstrip": false,
2034
+ "single_word": false,
2035
+ "special": true
2036
+ },
2037
+ "151897": {
2038
+ "content": "<|/audio|>",
2039
+ "lstrip": false,
2040
+ "normalized": false,
2041
+ "rstrip": false,
2042
+ "single_word": false,
2043
+ "special": true
2044
+ },
2045
+ "151898": {
2046
+ "content": "<|emotion|>",
2047
+ "lstrip": false,
2048
+ "normalized": false,
2049
+ "rstrip": false,
2050
+ "single_word": false,
2051
+ "special": true
2052
+ },
2053
+ "151899": {
2054
+ "content": "<|/emotion|>",
2055
+ "lstrip": false,
2056
+ "normalized": false,
2057
+ "rstrip": false,
2058
+ "single_word": false,
2059
+ "special": true
2060
+ },
2061
+ "151900": {
2062
+ "content": "<|emotion:neutral|>",
2063
+ "lstrip": false,
2064
+ "normalized": false,
2065
+ "rstrip": false,
2066
+ "single_word": false,
2067
+ "special": true
2068
+ },
2069
+ "151901": {
2070
+ "content": "<|emotion:happy|>",
2071
+ "lstrip": false,
2072
+ "normalized": false,
2073
+ "rstrip": false,
2074
+ "single_word": false,
2075
+ "special": true
2076
+ },
2077
+ "151902": {
2078
+ "content": "<|emotion:sad|>",
2079
+ "lstrip": false,
2080
+ "normalized": false,
2081
+ "rstrip": false,
2082
+ "single_word": false,
2083
+ "special": true
2084
+ },
2085
+ "151903": {
2086
+ "content": "<|emotion:angry|>",
2087
+ "lstrip": false,
2088
+ "normalized": false,
2089
+ "rstrip": false,
2090
+ "single_word": false,
2091
+ "special": true
2092
+ },
2093
+ "151904": {
2094
+ "content": "<|emotion:surprised|>",
2095
+ "lstrip": false,
2096
+ "normalized": false,
2097
+ "rstrip": false,
2098
+ "single_word": false,
2099
+ "special": true
2100
+ },
2101
+ "151905": {
2102
+ "content": "<|emotion:fearful|>",
2103
+ "lstrip": false,
2104
+ "normalized": false,
2105
+ "rstrip": false,
2106
+ "single_word": false,
2107
+ "special": true
2108
+ },
2109
+ "151906": {
2110
+ "content": "<|emotion:disgusted|>",
2111
+ "lstrip": false,
2112
+ "normalized": false,
2113
+ "rstrip": false,
2114
+ "single_word": false,
2115
+ "special": true
2116
+ },
2117
+ "151907": {
2118
+ "content": "<|emotion:calm|>",
2119
+ "lstrip": false,
2120
+ "normalized": false,
2121
+ "rstrip": false,
2122
+ "single_word": false,
2123
+ "special": true
2124
+ },
2125
+ "151908": {
2126
+ "content": "<|emotion:excited|>",
2127
+ "lstrip": false,
2128
+ "normalized": false,
2129
+ "rstrip": false,
2130
+ "single_word": false,
2131
+ "special": true
2132
+ },
2133
+ "151909": {
2134
+ "content": "<|emotion:curious|>",
2135
+ "lstrip": false,
2136
+ "normalized": false,
2137
+ "rstrip": false,
2138
+ "single_word": false,
2139
+ "special": true
2140
+ },
2141
+ "151910": {
2142
+ "content": "<|emotion:sympathetic|>",
2143
+ "lstrip": false,
2144
+ "normalized": false,
2145
+ "rstrip": false,
2146
+ "single_word": false,
2147
+ "special": true
2148
+ },
2149
+ "151911": {
2150
+ "content": "<|emotion:confident|>",
2151
+ "lstrip": false,
2152
+ "normalized": false,
2153
+ "rstrip": false,
2154
+ "single_word": false,
2155
+ "special": true
2156
+ },
2157
+ "151912": {
2158
+ "content": "<|prosody|>",
2159
+ "lstrip": false,
2160
+ "normalized": false,
2161
+ "rstrip": false,
2162
+ "single_word": false,
2163
+ "special": true
2164
+ },
2165
+ "151913": {
2166
+ "content": "<|/prosody|>",
2167
+ "lstrip": false,
2168
+ "normalized": false,
2169
+ "rstrip": false,
2170
+ "single_word": false,
2171
+ "special": true
2172
+ },
2173
+ "151914": {
2174
+ "content": "<|prosody:fast|>",
2175
+ "lstrip": false,
2176
+ "normalized": false,
2177
+ "rstrip": false,
2178
+ "single_word": false,
2179
+ "special": true
2180
+ },
2181
+ "151915": {
2182
+ "content": "<|prosody:slow|>",
2183
+ "lstrip": false,
2184
+ "normalized": false,
2185
+ "rstrip": false,
2186
+ "single_word": false,
2187
+ "special": true
2188
+ },
2189
+ "151916": {
2190
+ "content": "<|prosody:normal_speed|>",
2191
+ "lstrip": false,
2192
+ "normalized": false,
2193
+ "rstrip": false,
2194
+ "single_word": false,
2195
+ "special": true
2196
+ },
2197
+ "151917": {
2198
+ "content": "<|prosody:loud|>",
2199
+ "lstrip": false,
2200
+ "normalized": false,
2201
+ "rstrip": false,
2202
+ "single_word": false,
2203
+ "special": true
2204
+ },
2205
+ "151918": {
2206
+ "content": "<|prosody:soft|>",
2207
+ "lstrip": false,
2208
+ "normalized": false,
2209
+ "rstrip": false,
2210
+ "single_word": false,
2211
+ "special": true
2212
+ },
2213
+ "151919": {
2214
+ "content": "<|prosody:whisper|>",
2215
+ "lstrip": false,
2216
+ "normalized": false,
2217
+ "rstrip": false,
2218
+ "single_word": false,
2219
+ "special": true
2220
+ },
2221
+ "151920": {
2222
+ "content": "<|prosody:normal_volume|>",
2223
+ "lstrip": false,
2224
+ "normalized": false,
2225
+ "rstrip": false,
2226
+ "single_word": false,
2227
+ "special": true
2228
+ },
2229
+ "151921": {
2230
+ "content": "<|prosody:high_pitch|>",
2231
+ "lstrip": false,
2232
+ "normalized": false,
2233
+ "rstrip": false,
2234
+ "single_word": false,
2235
+ "special": true
2236
+ },
2237
+ "151922": {
2238
+ "content": "<|prosody:low_pitch|>",
2239
+ "lstrip": false,
2240
+ "normalized": false,
2241
+ "rstrip": false,
2242
+ "single_word": false,
2243
+ "special": true
2244
+ },
2245
+ "151923": {
2246
+ "content": "<|prosody:normal_pitch|>",
2247
+ "lstrip": false,
2248
+ "normalized": false,
2249
+ "rstrip": false,
2250
+ "single_word": false,
2251
+ "special": true
2252
+ },
2253
+ "151924": {
2254
+ "content": "<|prosody:emphasis|>",
2255
+ "lstrip": false,
2256
+ "normalized": false,
2257
+ "rstrip": false,
2258
+ "single_word": false,
2259
+ "special": true
2260
+ },
2261
+ "151925": {
2262
+ "content": "<|prosody:pause_short|>",
2263
+ "lstrip": false,
2264
+ "normalized": false,
2265
+ "rstrip": false,
2266
+ "single_word": false,
2267
+ "special": true
2268
+ },
2269
+ "151926": {
2270
+ "content": "<|prosody:pause_long|>",
2271
+ "lstrip": false,
2272
+ "normalized": false,
2273
+ "rstrip": false,
2274
+ "single_word": false,
2275
+ "special": true
2276
+ },
2277
+ "151927": {
2278
+ "content": "<|sep|>",
2279
+ "lstrip": false,
2280
+ "normalized": false,
2281
+ "rstrip": false,
2282
+ "single_word": false,
2283
+ "special": true
2284
+ },
2285
+ "151928": {
2286
+ "content": "<|nl|>",
2287
+ "lstrip": false,
2288
+ "normalized": false,
2289
+ "rstrip": false,
2290
+ "single_word": false,
2291
+ "special": true
2292
+ },
2293
+ "151929": {
2294
+ "content": "<|mask|>",
2295
+ "lstrip": false,
2296
+ "normalized": false,
2297
+ "rstrip": false,
2298
+ "single_word": false,
2299
+ "special": true
2300
+ }
2301
+ },
2302
+ "additional_special_tokens": [
2303
+ "<|bos|>",
2304
+ "<|eos|>",
2305
+ "<|pad|>",
2306
+ "<|prompt|>",
2307
+ "<|/prompt|>",
2308
+ "<|text|>",
2309
+ "<|/text|>",
2310
+ "<|response|>",
2311
+ "<|/response|>",
2312
+ "<|system|>",
2313
+ "<|/system|>",
2314
+ "<|user|>",
2315
+ "<|/user|>",
2316
+ "<|assistant|>",
2317
+ "<|/assistant|>",
2318
+ "<|fim_prefix|>",
2319
+ "<|fim_middle|>",
2320
+ "<|fim_suffix|>",
2321
+ "<|fim_pad|>",
2322
+ "<|commit_before|>",
2323
+ "<|/commit_before|>",
2324
+ "<|commit_after|>",
2325
+ "<|/commit_after|>",
2326
+ "<|commit_msg|>",
2327
+ "<|/commit_msg|>",
2328
+ "<|diff|>",
2329
+ "<|/diff|>",
2330
+ "<|diff_add|>",
2331
+ "<|diff_del|>",
2332
+ "<|diff_ctx|>",
2333
+ "<|reponame|>",
2334
+ "<|/reponame|>",
2335
+ "<|gh_stars|>",
2336
+ "<|/gh_stars|>",
2337
+ "<|branch|>",
2338
+ "<|/branch|>",
2339
+ "<|issue|>",
2340
+ "<|/issue|>",
2341
+ "<|issue_title|>",
2342
+ "<|/issue_title|>",
2343
+ "<|issue_body|>",
2344
+ "<|/issue_body|>",
2345
+ "<|issue_closed|>",
2346
+ "<|issue_open|>",
2347
+ "<|pr|>",
2348
+ "<|/pr|>",
2349
+ "<|pr_title|>",
2350
+ "<|/pr_title|>",
2351
+ "<|pr_body|>",
2352
+ "<|/pr_body|>",
2353
+ "<|pr_merged|>",
2354
+ "<|pr_closed|>",
2355
+ "<|jupyter|>",
2356
+ "<|/jupyter|>",
2357
+ "<|jupyter_code|>",
2358
+ "<|/jupyter_code|>",
2359
+ "<|jupyter_output|>",
2360
+ "<|/jupyter_output|>",
2361
+ "<|jupyter_text|>",
2362
+ "<|/jupyter_text|>",
2363
+ "<|jupyter_error|>",
2364
+ "<|/jupyter_error|>",
2365
+ "<|empty_output|>",
2366
+ "<|exec|>",
2367
+ "<|/exec|>",
2368
+ "<|exec_result|>",
2369
+ "<|/exec_result|>",
2370
+ "<|exec_error|>",
2371
+ "<|/exec_error|>",
2372
+ "<|exec_timeout|>",
2373
+ "<|add_file|>",
2374
+ "<|/add_file|>",
2375
+ "<|delete_file|>",
2376
+ "<|/delete_file|>",
2377
+ "<|rename_file|>",
2378
+ "<|/rename_file|>",
2379
+ "<|edit_file|>",
2380
+ "<|/edit_file|>",
2381
+ "<|read_file|>",
2382
+ "<|/read_file|>",
2383
+ "<|file_sep|>",
2384
+ "<|file_content|>",
2385
+ "<|/file_content|>",
2386
+ "<|edit_range|>",
2387
+ "<|/edit_range|>",
2388
+ "<|line|>",
2389
+ "<|/line|>",
2390
+ "<|insert_before|>",
2391
+ "<|insert_after|>",
2392
+ "<|replace|>",
2393
+ "<|/replace|>",
2394
+ "[e~[",
2395
+ "]~e]",
2396
+ "[d~[",
2397
+ "]~d]",
2398
+ "[p~[",
2399
+ "]~p]",
2400
+ "]~b]",
2401
+ "]~!b[",
2402
+ "[m~[",
2403
+ "]~m]",
2404
+ "<|doc|>",
2405
+ "<|/doc|>",
2406
+ "<|eod|>",
2407
+ "<|file:txt|>",
2408
+ "<|/file:txt|>",
2409
+ "<|file:md|>",
2410
+ "<|/file:md|>",
2411
+ "<|file:json|>",
2412
+ "<|/file:json|>",
2413
+ "<|file:xml|>",
2414
+ "<|/file:xml|>",
2415
+ "<|file:yaml|>",
2416
+ "<|/file:yaml|>",
2417
+ "<|file:html|>",
2418
+ "<|/file:html|>",
2419
+ "<|file:css|>",
2420
+ "<|/file:css|>",
2421
+ "<|file:csv|>",
2422
+ "<|/file:csv|>",
2423
+ "<|file:toml|>",
2424
+ "<|/file:toml|>",
2425
+ "<|file:ini|>",
2426
+ "<|/file:ini|>",
2427
+ "<|file:log|>",
2428
+ "<|/file:log|>",
2429
+ "<|filename|>",
2430
+ "<|/filename|>",
2431
+ "<|filepath|>",
2432
+ "<|/filepath|>",
2433
+ "<|image|>",
2434
+ "<|/image|>",
2435
+ "<|video|>",
2436
+ "<|/video|>",
2437
+ "<|gen_image|>",
2438
+ "<|/gen_image|>",
2439
+ "<|gen_video|>",
2440
+ "<|/gen_video|>",
2441
+ "<|tool_call|>",
2442
+ "<|/tool_call|>",
2443
+ "<|tool_result|>",
2444
+ "<|/tool_result|>",
2445
+ "<|function_name|>",
2446
+ "<|/function_name|>",
2447
+ "<|function_args|>",
2448
+ "<|/function_args|>",
2449
+ "<|arg_name|>",
2450
+ "<|/arg_name|>",
2451
+ "<|arg_value|>",
2452
+ "<|/arg_value|>",
2453
+ "<|tools|>",
2454
+ "<|/tools|>",
2455
+ "<|function_def|>",
2456
+ "<|/function_def|>",
2457
+ "<|tool_error|>",
2458
+ "<|/tool_error|>",
2459
+ "<|tool_success|>",
2460
+ "<|tool_calls|>",
2461
+ "<|/tool_calls|>",
2462
+ "<|tool_id|>",
2463
+ "<|/tool_id|>",
2464
+ "<|code|>",
2465
+ "<|/code|>",
2466
+ "<|lang:python|>",
2467
+ "<|lang:javascript|>",
2468
+ "<|lang:typescript|>",
2469
+ "<|lang:java|>",
2470
+ "<|lang:cpp|>",
2471
+ "<|lang:c|>",
2472
+ "<|lang:csharp|>",
2473
+ "<|lang:go|>",
2474
+ "<|lang:rust|>",
2475
+ "<|lang:ruby|>",
2476
+ "<|lang:php|>",
2477
+ "<|lang:swift|>",
2478
+ "<|lang:kotlin|>",
2479
+ "<|lang:scala|>",
2480
+ "<|lang:shell|>",
2481
+ "<|lang:bash|>",
2482
+ "<|lang:sql|>",
2483
+ "<|lang:r|>",
2484
+ "<|lang:matlab|>",
2485
+ "<|lang:lua|>",
2486
+ "<|lang:perl|>",
2487
+ "<|lang:haskell|>",
2488
+ "<|lang:other|>",
2489
+ "<|think|>",
2490
+ "<|/think|>",
2491
+ "<|observation|>",
2492
+ "<|/observation|>",
2493
+ "<|note|>",
2494
+ "<|/note|>",
2495
+ "<|step|>",
2496
+ "<|/step|>",
2497
+ "<|reflection|>",
2498
+ "<|/reflection|>",
2499
+ "<|hypothesis|>",
2500
+ "<|/hypothesis|>",
2501
+ "<|conclusion|>",
2502
+ "<|/conclusion|>",
2503
+ "<|confidence:high|>",
2504
+ "<|confidence:medium|>",
2505
+ "<|confidence:low|>",
2506
+ "<|confidence:uncertain|>",
2507
+ "<|uncertain|>",
2508
+ "<|/uncertain|>",
2509
+ "<|unknown|>",
2510
+ "<|need_verify|>",
2511
+ "<|may_outdated|>",
2512
+ "<|verify|>",
2513
+ "<|/verify|>",
2514
+ "<|fact_check|>",
2515
+ "<|self_correct|>",
2516
+ "<|correction|>",
2517
+ "<|/correction|>",
2518
+ "<|cite|>",
2519
+ "<|/cite|>",
2520
+ "<|source|>",
2521
+ "<|/source|>",
2522
+ "<|ref|>",
2523
+ "<|/ref|>",
2524
+ "<|quote|>",
2525
+ "<|/quote|>",
2526
+ "<|context|>",
2527
+ "<|/context|>",
2528
+ "<|retrieved|>",
2529
+ "<|/retrieved|>",
2530
+ "<|grounded|>",
2531
+ "<|ungrounded|>",
2532
+ "<|knowledge_cutoff|>",
2533
+ "<|beyond_knowledge|>",
2534
+ "<|within_knowledge|>",
2535
+ "<|listen|>",
2536
+ "<|/listen|>",
2537
+ "<|speak|>",
2538
+ "<|/speak|>",
2539
+ "<|audio|>",
2540
+ "<|/audio|>",
2541
+ "<|emotion|>",
2542
+ "<|/emotion|>",
2543
+ "<|emotion:neutral|>",
2544
+ "<|emotion:happy|>",
2545
+ "<|emotion:sad|>",
2546
+ "<|emotion:angry|>",
2547
+ "<|emotion:surprised|>",
2548
+ "<|emotion:fearful|>",
2549
+ "<|emotion:disgusted|>",
2550
+ "<|emotion:calm|>",
2551
+ "<|emotion:excited|>",
2552
+ "<|emotion:curious|>",
2553
+ "<|emotion:sympathetic|>",
2554
+ "<|emotion:confident|>",
2555
+ "<|prosody|>",
2556
+ "<|/prosody|>",
2557
+ "<|prosody:fast|>",
2558
+ "<|prosody:slow|>",
2559
+ "<|prosody:normal_speed|>",
2560
+ "<|prosody:loud|>",
2561
+ "<|prosody:soft|>",
2562
+ "<|prosody:whisper|>",
2563
+ "<|prosody:normal_volume|>",
2564
+ "<|prosody:high_pitch|>",
2565
+ "<|prosody:low_pitch|>",
2566
+ "<|prosody:normal_pitch|>",
2567
+ "<|prosody:emphasis|>",
2568
+ "<|prosody:pause_short|>",
2569
+ "<|prosody:pause_long|>",
2570
+ "<|sep|>",
2571
+ "<|nl|>",
2572
+ "<|mask|>"
2573
+ ],
2574
+ "bos_token": "<|bos|>",
2575
+ "clean_up_tokenization_spaces": false,
2576
+ "eos_token": "<|eos|>",
2577
+ "errors": "replace",
2578
+ "extra_special_tokens": {},
2579
+ "model_max_length": 131072,
2580
+ "pad_token": "<|pad|>",
2581
+ "split_special_tokens": false,
2582
+ "tokenizer_class": "Qwen2Tokenizer",
2583
+ "unk_token": null
2584
+ }
training_state.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:34c91c0a4284added2a08b09013db6e8311c2ab38296db54892b0c48f6a745b6
3
+ size 3877508893
vocab.json ADDED
The diff for this file is too large to render. See raw diff