Kasualdad commited on
Commit
981b57e
·
verified ·
1 Parent(s): 3a2f2a3

migrate: copy tokenizer_config.json from build-small-hackathon

Browse files
Files changed (1) hide show
  1. tokenizer_config.json +202 -0
tokenizer_config.json ADDED
@@ -0,0 +1,202 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_prefix_space": false,
3
+ "backend": "tokenizers",
4
+ "bos_token": null,
5
+ "clean_up_tokenization_spaces": false,
6
+ "eos_token": "<|im_end|>",
7
+ "errors": "replace",
8
+ "extra_special_tokens": [],
9
+ "is_local": false,
10
+ "model_max_length": 32768,
11
+ "pad_token": "<|PAD_TOKEN|>",
12
+ "padding_side": "left",
13
+ "split_special_tokens": false,
14
+ "tokenizer_class": "Qwen2Tokenizer",
15
+ "unk_token": null,
16
+ "added_tokens_decoder": {
17
+ "151643": {
18
+ "content": "<|endoftext|>",
19
+ "single_word": false,
20
+ "lstrip": false,
21
+ "rstrip": false,
22
+ "normalized": false,
23
+ "special": true
24
+ },
25
+ "151644": {
26
+ "content": "<|im_start|>",
27
+ "single_word": false,
28
+ "lstrip": false,
29
+ "rstrip": false,
30
+ "normalized": false,
31
+ "special": true
32
+ },
33
+ "151645": {
34
+ "content": "<|im_end|>",
35
+ "single_word": false,
36
+ "lstrip": false,
37
+ "rstrip": false,
38
+ "normalized": false,
39
+ "special": true
40
+ },
41
+ "151646": {
42
+ "content": "<|object_ref_start|>",
43
+ "single_word": false,
44
+ "lstrip": false,
45
+ "rstrip": false,
46
+ "normalized": false,
47
+ "special": true
48
+ },
49
+ "151647": {
50
+ "content": "<|object_ref_end|>",
51
+ "single_word": false,
52
+ "lstrip": false,
53
+ "rstrip": false,
54
+ "normalized": false,
55
+ "special": true
56
+ },
57
+ "151648": {
58
+ "content": "<|box_start|>",
59
+ "single_word": false,
60
+ "lstrip": false,
61
+ "rstrip": false,
62
+ "normalized": false,
63
+ "special": true
64
+ },
65
+ "151649": {
66
+ "content": "<|box_end|>",
67
+ "single_word": false,
68
+ "lstrip": false,
69
+ "rstrip": false,
70
+ "normalized": false,
71
+ "special": true
72
+ },
73
+ "151650": {
74
+ "content": "<|quad_start|>",
75
+ "single_word": false,
76
+ "lstrip": false,
77
+ "rstrip": false,
78
+ "normalized": false,
79
+ "special": true
80
+ },
81
+ "151651": {
82
+ "content": "<|quad_end|>",
83
+ "single_word": false,
84
+ "lstrip": false,
85
+ "rstrip": false,
86
+ "normalized": false,
87
+ "special": true
88
+ },
89
+ "151652": {
90
+ "content": "<|vision_start|>",
91
+ "single_word": false,
92
+ "lstrip": false,
93
+ "rstrip": false,
94
+ "normalized": false,
95
+ "special": true
96
+ },
97
+ "151653": {
98
+ "content": "<|vision_end|>",
99
+ "single_word": false,
100
+ "lstrip": false,
101
+ "rstrip": false,
102
+ "normalized": false,
103
+ "special": true
104
+ },
105
+ "151654": {
106
+ "content": "<|vision_pad|>",
107
+ "single_word": false,
108
+ "lstrip": false,
109
+ "rstrip": false,
110
+ "normalized": false,
111
+ "special": true
112
+ },
113
+ "151655": {
114
+ "content": "<|image_pad|>",
115
+ "single_word": false,
116
+ "lstrip": false,
117
+ "rstrip": false,
118
+ "normalized": false,
119
+ "special": true
120
+ },
121
+ "151656": {
122
+ "content": "<|video_pad|>",
123
+ "single_word": false,
124
+ "lstrip": false,
125
+ "rstrip": false,
126
+ "normalized": false,
127
+ "special": true
128
+ },
129
+ "151657": {
130
+ "content": "<tool_call>",
131
+ "single_word": false,
132
+ "lstrip": false,
133
+ "rstrip": false,
134
+ "normalized": false,
135
+ "special": false
136
+ },
137
+ "151658": {
138
+ "content": "</tool_call>",
139
+ "single_word": false,
140
+ "lstrip": false,
141
+ "rstrip": false,
142
+ "normalized": false,
143
+ "special": false
144
+ },
145
+ "151659": {
146
+ "content": "<|fim_prefix|>",
147
+ "single_word": false,
148
+ "lstrip": false,
149
+ "rstrip": false,
150
+ "normalized": false,
151
+ "special": false
152
+ },
153
+ "151660": {
154
+ "content": "<|fim_middle|>",
155
+ "single_word": false,
156
+ "lstrip": false,
157
+ "rstrip": false,
158
+ "normalized": false,
159
+ "special": false
160
+ },
161
+ "151661": {
162
+ "content": "<|fim_suffix|>",
163
+ "single_word": false,
164
+ "lstrip": false,
165
+ "rstrip": false,
166
+ "normalized": false,
167
+ "special": false
168
+ },
169
+ "151662": {
170
+ "content": "<|fim_pad|>",
171
+ "single_word": false,
172
+ "lstrip": false,
173
+ "rstrip": false,
174
+ "normalized": false,
175
+ "special": false
176
+ },
177
+ "151663": {
178
+ "content": "<|repo_name|>",
179
+ "single_word": false,
180
+ "lstrip": false,
181
+ "rstrip": false,
182
+ "normalized": false,
183
+ "special": false
184
+ },
185
+ "151664": {
186
+ "content": "<|file_sep|>",
187
+ "single_word": false,
188
+ "lstrip": false,
189
+ "rstrip": false,
190
+ "normalized": false,
191
+ "special": false
192
+ },
193
+ "151665": {
194
+ "content": "<|PAD_TOKEN|>",
195
+ "single_word": false,
196
+ "lstrip": false,
197
+ "rstrip": false,
198
+ "normalized": false,
199
+ "special": true
200
+ }
201
+ }
202
+ }