lei-HuggingFace
commited on
Commit
•
baa7e96
1
Parent(s):
58e1044
Delete tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +0 -235
tokenizer_config.json
DELETED
@@ -1,235 +0,0 @@
|
|
1 |
-
{
|
2 |
-
"add_prefix_space": false,
|
3 |
-
"added_tokens_decoder": {
|
4 |
-
"128244": {
|
5 |
-
"content": "<unk>",
|
6 |
-
"lstrip": false,
|
7 |
-
"normalized": false,
|
8 |
-
"rstrip": false,
|
9 |
-
"single_word": false,
|
10 |
-
"special": true
|
11 |
-
},
|
12 |
-
"151643": {
|
13 |
-
"content": "<|endoftext|>",
|
14 |
-
"lstrip": false,
|
15 |
-
"normalized": false,
|
16 |
-
"rstrip": false,
|
17 |
-
"single_word": false,
|
18 |
-
"special": true
|
19 |
-
},
|
20 |
-
"151644": {
|
21 |
-
"content": "<|im_start|>",
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": false,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": true
|
27 |
-
},
|
28 |
-
"151645": {
|
29 |
-
"content": "<|im_end|>",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": false,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": true
|
35 |
-
},
|
36 |
-
"151646": {
|
37 |
-
"content": "<image>",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": false,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": true
|
43 |
-
},
|
44 |
-
"151647": {
|
45 |
-
"content": "</image>",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": false,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": true
|
51 |
-
},
|
52 |
-
"151648": {
|
53 |
-
"content": "<ref>",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": false,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": true
|
59 |
-
},
|
60 |
-
"151649": {
|
61 |
-
"content": "</ref>",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": false,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": true
|
67 |
-
},
|
68 |
-
"151650": {
|
69 |
-
"content": "<box>",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": false,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": true
|
75 |
-
},
|
76 |
-
"151651": {
|
77 |
-
"content": "</box>",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": false,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": true
|
83 |
-
},
|
84 |
-
"151652": {
|
85 |
-
"content": "<quad>",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": false,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": true
|
91 |
-
},
|
92 |
-
"151653": {
|
93 |
-
"content": "</quad>",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": false,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": true
|
99 |
-
},
|
100 |
-
"151654": {
|
101 |
-
"content": "<point>",
|
102 |
-
"lstrip": false,
|
103 |
-
"normalized": false,
|
104 |
-
"rstrip": false,
|
105 |
-
"single_word": false,
|
106 |
-
"special": true
|
107 |
-
},
|
108 |
-
"151655": {
|
109 |
-
"content": "</point>",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": false,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false,
|
114 |
-
"special": true
|
115 |
-
},
|
116 |
-
"151656": {
|
117 |
-
"content": "<slice>",
|
118 |
-
"lstrip": false,
|
119 |
-
"normalized": false,
|
120 |
-
"rstrip": false,
|
121 |
-
"single_word": false,
|
122 |
-
"special": true
|
123 |
-
},
|
124 |
-
"151657": {
|
125 |
-
"content": "</slice>",
|
126 |
-
"lstrip": false,
|
127 |
-
"normalized": false,
|
128 |
-
"rstrip": false,
|
129 |
-
"single_word": false,
|
130 |
-
"special": true
|
131 |
-
},
|
132 |
-
"151658": {
|
133 |
-
"content": "<image_id>",
|
134 |
-
"lstrip": false,
|
135 |
-
"normalized": false,
|
136 |
-
"rstrip": false,
|
137 |
-
"single_word": false,
|
138 |
-
"special": true
|
139 |
-
},
|
140 |
-
"151659": {
|
141 |
-
"content": "</image_id>",
|
142 |
-
"lstrip": false,
|
143 |
-
"normalized": false,
|
144 |
-
"rstrip": false,
|
145 |
-
"single_word": false,
|
146 |
-
"special": true
|
147 |
-
},
|
148 |
-
"151660": {
|
149 |
-
"content": "<|reserved_special_token_0|>",
|
150 |
-
"lstrip": false,
|
151 |
-
"normalized": false,
|
152 |
-
"rstrip": false,
|
153 |
-
"single_word": false,
|
154 |
-
"special": true
|
155 |
-
},
|
156 |
-
"151661": {
|
157 |
-
"content": "<|reserved_special_token_1|>",
|
158 |
-
"lstrip": false,
|
159 |
-
"normalized": false,
|
160 |
-
"rstrip": false,
|
161 |
-
"single_word": false,
|
162 |
-
"special": true
|
163 |
-
},
|
164 |
-
"151662": {
|
165 |
-
"content": "<|reserved_special_token_2|>",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": false,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false,
|
170 |
-
"special": true
|
171 |
-
},
|
172 |
-
"151663": {
|
173 |
-
"content": "<|reserved_special_token_3|>",
|
174 |
-
"lstrip": false,
|
175 |
-
"normalized": false,
|
176 |
-
"rstrip": false,
|
177 |
-
"single_word": false,
|
178 |
-
"special": true
|
179 |
-
},
|
180 |
-
"151664": {
|
181 |
-
"content": "<|reserved_special_token_4|>",
|
182 |
-
"lstrip": false,
|
183 |
-
"normalized": false,
|
184 |
-
"rstrip": false,
|
185 |
-
"single_word": false,
|
186 |
-
"special": true
|
187 |
-
},
|
188 |
-
"151665": {
|
189 |
-
"content": "<|reserved_special_token_5|>",
|
190 |
-
"lstrip": false,
|
191 |
-
"normalized": false,
|
192 |
-
"rstrip": false,
|
193 |
-
"single_word": false,
|
194 |
-
"special": true
|
195 |
-
}
|
196 |
-
},
|
197 |
-
"additional_special_tokens": [
|
198 |
-
"<image>",
|
199 |
-
"</image>",
|
200 |
-
"<ref>",
|
201 |
-
"</ref>",
|
202 |
-
"<box>",
|
203 |
-
"</box>",
|
204 |
-
"<quad>",
|
205 |
-
"</quad>",
|
206 |
-
"<point>",
|
207 |
-
"</point>",
|
208 |
-
"<slice>",
|
209 |
-
"</slice>",
|
210 |
-
"<image_id>",
|
211 |
-
"</image_id>",
|
212 |
-
"<|reserved_special_token_0|>",
|
213 |
-
"<|reserved_special_token_1|>",
|
214 |
-
"<|reserved_special_token_2|>",
|
215 |
-
"<|reserved_special_token_3|>",
|
216 |
-
"<|reserved_special_token_4|>",
|
217 |
-
"<|reserved_special_token_5|>"
|
218 |
-
],
|
219 |
-
"auto_map": {
|
220 |
-
"AutoTokenizer": [
|
221 |
-
"openbmb/MiniCPM-V-2_6--tokenization_minicpmv_fast.MiniCPMVTokenizerFast",
|
222 |
-
null
|
223 |
-
]
|
224 |
-
},
|
225 |
-
"bos_token": "<|im_start|>",
|
226 |
-
"chat_template": "{% for message in messages %}{% if loop.first and messages[0]['role'] != 'system' %}{{ '<|im_start|>system\nYou are a helpful assistant.<|im_end|>\n' }}{% endif %}{{'<|im_start|>' + message['role'] + '\n' + message['content'] + '<|im_end|>' + '\n'}}{% endfor %}{% if add_generation_prompt %}{{ '<|im_start|>assistant\n' }}{% endif %}",
|
227 |
-
"clean_up_tokenization_spaces": false,
|
228 |
-
"eos_token": "<|im_end|>",
|
229 |
-
"errors": "replace",
|
230 |
-
"model_max_length": 1000000000000000019884624838656,
|
231 |
-
"pad_token": "<|endoftext|>",
|
232 |
-
"split_special_tokens": false,
|
233 |
-
"tokenizer_class": "MiniCPMVTokenizer",
|
234 |
-
"unk_token": "<unk>"
|
235 |
-
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|