iamPi commited on
Commit
f47e904
·
verified ·
1 Parent(s): 488871b

Update tokenizer_config.json

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +15 -202
tokenizer_config.json CHANGED
@@ -1,216 +1,29 @@
1
  {
2
- "added_tokens_decoder": {
3
- "163584": {
4
- "content": "[BOS]",
5
- "lstrip": false,
6
- "normalized": false,
7
- "rstrip": false,
8
- "single_word": false,
9
- "special": true
10
- },
11
- "163585": {
12
- "content": "[EOS]",
13
- "lstrip": false,
14
- "normalized": false,
15
- "rstrip": false,
16
- "single_word": false,
17
- "special": true
18
- },
19
- "163586": {
20
- "content": "<|im_end|>",
21
- "lstrip": false,
22
- "normalized": false,
23
- "rstrip": false,
24
- "single_word": false,
25
- "special": true
26
- },
27
- "163587": {
28
- "content": "<|im_user|>",
29
- "lstrip": false,
30
- "normalized": false,
31
- "rstrip": false,
32
- "single_word": false,
33
- "special": true
34
- },
35
- "163588": {
36
- "content": "<|im_assistant|>",
37
- "lstrip": false,
38
- "normalized": false,
39
- "rstrip": false,
40
- "single_word": false,
41
- "special": true
42
- },
43
- "163590": {
44
- "content": "<|start_header_id|>",
45
- "lstrip": false,
46
- "normalized": false,
47
- "rstrip": false,
48
- "single_word": false,
49
- "special": true
50
- },
51
- "163591": {
52
- "content": "<|end_header_id|>",
53
- "lstrip": false,
54
- "normalized": false,
55
- "rstrip": false,
56
- "single_word": false,
57
- "special": true
58
- },
59
- "163593": {
60
- "content": "[EOT]",
61
- "lstrip": false,
62
- "normalized": false,
63
- "rstrip": false,
64
- "single_word": false,
65
- "special": true
66
- },
67
- "163594": {
68
- "content": "<|im_system|>",
69
- "lstrip": false,
70
- "normalized": false,
71
- "rstrip": false,
72
- "single_word": false,
73
- "special": true
74
- },
75
- "163595": {
76
- "content": "<|tool_calls_section_begin|>",
77
- "lstrip": false,
78
- "normalized": false,
79
- "rstrip": false,
80
- "single_word": false,
81
- "special": false
82
- },
83
- "163596": {
84
- "content": "<|tool_calls_section_end|>",
85
- "lstrip": false,
86
- "normalized": false,
87
- "rstrip": false,
88
- "single_word": false,
89
- "special": false
90
- },
91
- "163597": {
92
- "content": "<|tool_call_begin|>",
93
- "lstrip": false,
94
- "normalized": false,
95
- "rstrip": false,
96
- "single_word": false,
97
- "special": false
98
- },
99
- "163598": {
100
- "content": "<|tool_call_argument_begin|>",
101
- "lstrip": false,
102
- "normalized": false,
103
- "rstrip": false,
104
- "single_word": false,
105
- "special": false
106
- },
107
- "163599": {
108
- "content": "<|tool_call_end|>",
109
- "lstrip": false,
110
- "normalized": false,
111
- "rstrip": false,
112
- "single_word": false,
113
- "special": false
114
- },
115
- "163601": {
116
- "content": "<|im_middle|>",
117
- "lstrip": false,
118
- "normalized": false,
119
- "rstrip": false,
120
- "single_word": false,
121
- "special": true
122
- },
123
- "163602": {
124
- "content": "<|media_begin|>",
125
- "lstrip": false,
126
- "normalized": false,
127
- "rstrip": false,
128
- "single_word": false,
129
- "special": true
130
- },
131
- "163603": {
132
- "content": "<|media_content|>",
133
- "lstrip": false,
134
- "normalized": false,
135
- "rstrip": false,
136
- "single_word": false,
137
- "special": true
138
- },
139
- "163604": {
140
- "content": "<|media_end|>",
141
- "lstrip": false,
142
- "normalized": false,
143
- "rstrip": false,
144
- "single_word": false,
145
- "special": true
146
- },
147
- "163605": {
148
- "content": "<|media_pad|>",
149
- "lstrip": false,
150
- "normalized": false,
151
- "rstrip": false,
152
- "single_word": false,
153
- "special": true
154
- },
155
- "163606": {
156
- "content": "<think>",
157
- "lstrip": false,
158
- "normalized": false,
159
- "rstrip": false,
160
- "single_word": false,
161
- "special": false
162
- },
163
- "163607": {
164
- "content": "</think>",
165
- "lstrip": false,
166
- "normalized": false,
167
- "rstrip": false,
168
- "single_word": false,
169
- "special": false
170
- },
171
- "163838": {
172
- "content": "[UNK]",
173
- "lstrip": false,
174
- "normalized": false,
175
- "rstrip": false,
176
- "single_word": false,
177
- "special": true
178
- },
179
- "163839": {
180
- "content": "[PAD]",
181
- "lstrip": false,
182
- "normalized": false,
183
- "rstrip": false,
184
- "single_word": false,
185
- "special": true
186
- }
187
  },
188
- "additional_special_tokens": [
 
 
 
 
189
  "<|im_end|>",
190
  "<|im_user|>",
191
  "<|im_assistant|>",
192
- "<|start_header_id|>",
193
- "<|end_header_id|>",
194
- "[EOT]",
195
  "<|im_system|>",
196
  "<|im_middle|>",
197
- "<|media_begin|>",
198
  "<|media_content|>",
199
  "<|media_end|>",
200
  "<|media_pad|>"
201
  ],
202
- "bos_token": "[BOS]",
203
- "clean_up_tokenization_spaces": false,
204
- "eos_token": "[EOS]",
205
- "extra_special_tokens": {},
206
  "model_max_length": 1000000000000000019884624838656,
207
  "pad_token": "[PAD]",
208
- "tokenizer_class": "TikTokenTokenizer",
209
- "unk_token": "[UNK]",
210
- "auto_map": {
211
- "AutoTokenizer": [
212
- "tokenization_kimi.TikTokenTokenizer",
213
- null
214
- ]
215
- }
216
  }
 
1
  {
2
+ "auto_map": {
3
+ "AutoTokenizer": [
4
+ "tokenization_kimi.TikTokenTokenizer",
5
+ null
6
+ ]
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
7
  },
8
+ "backend": "tokenizers",
9
+ "bos_token": "[BOS]",
10
+ "clean_up_tokenization_spaces": false,
11
+ "eos_token": "[EOS]",
12
+ "extra_special_tokens": [
13
  "<|im_end|>",
14
  "<|im_user|>",
15
  "<|im_assistant|>",
 
 
 
16
  "<|im_system|>",
17
  "<|im_middle|>",
18
+ "<|media_start|>",
19
  "<|media_content|>",
20
  "<|media_end|>",
21
  "<|media_pad|>"
22
  ],
23
+ "is_local": true,
24
+ "local_files_only": false,
 
 
25
  "model_max_length": 1000000000000000019884624838656,
26
  "pad_token": "[PAD]",
27
+ "tokenizer_class": "TokenizersBackend",
28
+ "unk_token": "[UNK]"
 
 
 
 
 
 
29
  }