Upload tokenizer
Browse files- special_tokens_map.json +57 -0
- tokenizer.json +0 -0
- tokenizer_config.json +267 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,57 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"additional_special_tokens": [
|
3 |
+
"<PAD>",
|
4 |
+
"<quatrain>",
|
5 |
+
"</quatrain>",
|
6 |
+
"[ABCD]",
|
7 |
+
"[AABC]",
|
8 |
+
"[ABAC]",
|
9 |
+
"[ABCC]",
|
10 |
+
"[ABBA]",
|
11 |
+
"[ABAB]",
|
12 |
+
"[ABCB]",
|
13 |
+
"[ABBC]",
|
14 |
+
"[ABBB]",
|
15 |
+
"[AABA]",
|
16 |
+
"[AABB]",
|
17 |
+
"[AAAB]",
|
18 |
+
"[ABCA]",
|
19 |
+
"[AAAA]",
|
20 |
+
"[ABAA]",
|
21 |
+
"<iambus>",
|
22 |
+
"<trochee>",
|
23 |
+
"<anapaest>",
|
24 |
+
"<dactyl>",
|
25 |
+
"<other>",
|
26 |
+
"<amphibrach>",
|
27 |
+
"<alexandrine>"
|
28 |
+
],
|
29 |
+
"bos_token": {
|
30 |
+
"content": "<s>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false
|
35 |
+
},
|
36 |
+
"eos_token": {
|
37 |
+
"content": "</s>",
|
38 |
+
"lstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"rstrip": false,
|
41 |
+
"single_word": false
|
42 |
+
},
|
43 |
+
"pad_token": {
|
44 |
+
"content": "<PAD>",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false
|
49 |
+
},
|
50 |
+
"unk_token": {
|
51 |
+
"content": "<unk>",
|
52 |
+
"lstrip": false,
|
53 |
+
"normalized": false,
|
54 |
+
"rstrip": false,
|
55 |
+
"single_word": false
|
56 |
+
}
|
57 |
+
}
|
tokenizer.json
ADDED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
ADDED
@@ -0,0 +1,267 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"add_bos_token": true,
|
3 |
+
"add_eos_token": false,
|
4 |
+
"added_tokens_decoder": {
|
5 |
+
"0": {
|
6 |
+
"content": "<unk>",
|
7 |
+
"lstrip": false,
|
8 |
+
"normalized": false,
|
9 |
+
"rstrip": false,
|
10 |
+
"single_word": false,
|
11 |
+
"special": true
|
12 |
+
},
|
13 |
+
"1": {
|
14 |
+
"content": "<s>",
|
15 |
+
"lstrip": false,
|
16 |
+
"normalized": false,
|
17 |
+
"rstrip": false,
|
18 |
+
"single_word": false,
|
19 |
+
"special": true
|
20 |
+
},
|
21 |
+
"2": {
|
22 |
+
"content": "</s>",
|
23 |
+
"lstrip": false,
|
24 |
+
"normalized": false,
|
25 |
+
"rstrip": false,
|
26 |
+
"single_word": false,
|
27 |
+
"special": true
|
28 |
+
},
|
29 |
+
"32000": {
|
30 |
+
"content": "<PAD>",
|
31 |
+
"lstrip": false,
|
32 |
+
"normalized": false,
|
33 |
+
"rstrip": false,
|
34 |
+
"single_word": false,
|
35 |
+
"special": true
|
36 |
+
},
|
37 |
+
"32001": {
|
38 |
+
"content": "<quatrain>",
|
39 |
+
"lstrip": false,
|
40 |
+
"normalized": false,
|
41 |
+
"rstrip": false,
|
42 |
+
"single_word": false,
|
43 |
+
"special": true
|
44 |
+
},
|
45 |
+
"32002": {
|
46 |
+
"content": "</quatrain>",
|
47 |
+
"lstrip": false,
|
48 |
+
"normalized": false,
|
49 |
+
"rstrip": false,
|
50 |
+
"single_word": false,
|
51 |
+
"special": true
|
52 |
+
},
|
53 |
+
"32003": {
|
54 |
+
"content": "[ABCD]",
|
55 |
+
"lstrip": false,
|
56 |
+
"normalized": false,
|
57 |
+
"rstrip": false,
|
58 |
+
"single_word": false,
|
59 |
+
"special": true
|
60 |
+
},
|
61 |
+
"32004": {
|
62 |
+
"content": "[AABC]",
|
63 |
+
"lstrip": false,
|
64 |
+
"normalized": false,
|
65 |
+
"rstrip": false,
|
66 |
+
"single_word": false,
|
67 |
+
"special": true
|
68 |
+
},
|
69 |
+
"32005": {
|
70 |
+
"content": "[ABAC]",
|
71 |
+
"lstrip": false,
|
72 |
+
"normalized": false,
|
73 |
+
"rstrip": false,
|
74 |
+
"single_word": false,
|
75 |
+
"special": true
|
76 |
+
},
|
77 |
+
"32006": {
|
78 |
+
"content": "[ABCC]",
|
79 |
+
"lstrip": false,
|
80 |
+
"normalized": false,
|
81 |
+
"rstrip": false,
|
82 |
+
"single_word": false,
|
83 |
+
"special": true
|
84 |
+
},
|
85 |
+
"32007": {
|
86 |
+
"content": "[ABBA]",
|
87 |
+
"lstrip": false,
|
88 |
+
"normalized": false,
|
89 |
+
"rstrip": false,
|
90 |
+
"single_word": false,
|
91 |
+
"special": true
|
92 |
+
},
|
93 |
+
"32008": {
|
94 |
+
"content": "[ABAB]",
|
95 |
+
"lstrip": false,
|
96 |
+
"normalized": false,
|
97 |
+
"rstrip": false,
|
98 |
+
"single_word": false,
|
99 |
+
"special": true
|
100 |
+
},
|
101 |
+
"32009": {
|
102 |
+
"content": "[ABCB]",
|
103 |
+
"lstrip": false,
|
104 |
+
"normalized": false,
|
105 |
+
"rstrip": false,
|
106 |
+
"single_word": false,
|
107 |
+
"special": true
|
108 |
+
},
|
109 |
+
"32010": {
|
110 |
+
"content": "[ABBC]",
|
111 |
+
"lstrip": false,
|
112 |
+
"normalized": false,
|
113 |
+
"rstrip": false,
|
114 |
+
"single_word": false,
|
115 |
+
"special": true
|
116 |
+
},
|
117 |
+
"32011": {
|
118 |
+
"content": "[ABBB]",
|
119 |
+
"lstrip": false,
|
120 |
+
"normalized": false,
|
121 |
+
"rstrip": false,
|
122 |
+
"single_word": false,
|
123 |
+
"special": true
|
124 |
+
},
|
125 |
+
"32012": {
|
126 |
+
"content": "[AABA]",
|
127 |
+
"lstrip": false,
|
128 |
+
"normalized": false,
|
129 |
+
"rstrip": false,
|
130 |
+
"single_word": false,
|
131 |
+
"special": true
|
132 |
+
},
|
133 |
+
"32013": {
|
134 |
+
"content": "[AABB]",
|
135 |
+
"lstrip": false,
|
136 |
+
"normalized": false,
|
137 |
+
"rstrip": false,
|
138 |
+
"single_word": false,
|
139 |
+
"special": true
|
140 |
+
},
|
141 |
+
"32014": {
|
142 |
+
"content": "[AAAB]",
|
143 |
+
"lstrip": false,
|
144 |
+
"normalized": false,
|
145 |
+
"rstrip": false,
|
146 |
+
"single_word": false,
|
147 |
+
"special": true
|
148 |
+
},
|
149 |
+
"32015": {
|
150 |
+
"content": "[ABCA]",
|
151 |
+
"lstrip": false,
|
152 |
+
"normalized": false,
|
153 |
+
"rstrip": false,
|
154 |
+
"single_word": false,
|
155 |
+
"special": true
|
156 |
+
},
|
157 |
+
"32016": {
|
158 |
+
"content": "[AAAA]",
|
159 |
+
"lstrip": false,
|
160 |
+
"normalized": false,
|
161 |
+
"rstrip": false,
|
162 |
+
"single_word": false,
|
163 |
+
"special": true
|
164 |
+
},
|
165 |
+
"32017": {
|
166 |
+
"content": "[ABAA]",
|
167 |
+
"lstrip": false,
|
168 |
+
"normalized": false,
|
169 |
+
"rstrip": false,
|
170 |
+
"single_word": false,
|
171 |
+
"special": true
|
172 |
+
},
|
173 |
+
"32018": {
|
174 |
+
"content": "<iambus>",
|
175 |
+
"lstrip": false,
|
176 |
+
"normalized": false,
|
177 |
+
"rstrip": false,
|
178 |
+
"single_word": false,
|
179 |
+
"special": true
|
180 |
+
},
|
181 |
+
"32019": {
|
182 |
+
"content": "<trochee>",
|
183 |
+
"lstrip": false,
|
184 |
+
"normalized": false,
|
185 |
+
"rstrip": false,
|
186 |
+
"single_word": false,
|
187 |
+
"special": true
|
188 |
+
},
|
189 |
+
"32020": {
|
190 |
+
"content": "<anapaest>",
|
191 |
+
"lstrip": false,
|
192 |
+
"normalized": false,
|
193 |
+
"rstrip": false,
|
194 |
+
"single_word": false,
|
195 |
+
"special": true
|
196 |
+
},
|
197 |
+
"32021": {
|
198 |
+
"content": "<dactyl>",
|
199 |
+
"lstrip": false,
|
200 |
+
"normalized": false,
|
201 |
+
"rstrip": false,
|
202 |
+
"single_word": false,
|
203 |
+
"special": true
|
204 |
+
},
|
205 |
+
"32022": {
|
206 |
+
"content": "<other>",
|
207 |
+
"lstrip": false,
|
208 |
+
"normalized": false,
|
209 |
+
"rstrip": false,
|
210 |
+
"single_word": false,
|
211 |
+
"special": true
|
212 |
+
},
|
213 |
+
"32023": {
|
214 |
+
"content": "<amphibrach>",
|
215 |
+
"lstrip": false,
|
216 |
+
"normalized": false,
|
217 |
+
"rstrip": false,
|
218 |
+
"single_word": false,
|
219 |
+
"special": true
|
220 |
+
},
|
221 |
+
"32024": {
|
222 |
+
"content": "<alexandrine>",
|
223 |
+
"lstrip": false,
|
224 |
+
"normalized": false,
|
225 |
+
"rstrip": false,
|
226 |
+
"single_word": false,
|
227 |
+
"special": true
|
228 |
+
}
|
229 |
+
},
|
230 |
+
"additional_special_tokens": [
|
231 |
+
"<PAD>",
|
232 |
+
"<quatrain>",
|
233 |
+
"</quatrain>",
|
234 |
+
"[ABCD]",
|
235 |
+
"[AABC]",
|
236 |
+
"[ABAC]",
|
237 |
+
"[ABCC]",
|
238 |
+
"[ABBA]",
|
239 |
+
"[ABAB]",
|
240 |
+
"[ABCB]",
|
241 |
+
"[ABBC]",
|
242 |
+
"[ABBB]",
|
243 |
+
"[AABA]",
|
244 |
+
"[AABB]",
|
245 |
+
"[AAAB]",
|
246 |
+
"[ABCA]",
|
247 |
+
"[AAAA]",
|
248 |
+
"[ABAA]",
|
249 |
+
"<iambus>",
|
250 |
+
"<trochee>",
|
251 |
+
"<anapaest>",
|
252 |
+
"<dactyl>",
|
253 |
+
"<other>",
|
254 |
+
"<amphibrach>",
|
255 |
+
"<alexandrine>"
|
256 |
+
],
|
257 |
+
"bos_token": "<s>",
|
258 |
+
"clean_up_tokenization_spaces": false,
|
259 |
+
"eos_token": "</s>",
|
260 |
+
"model_max_length": 1000000000000000019884624838656,
|
261 |
+
"pad_token": "<PAD>",
|
262 |
+
"padding_side": "left",
|
263 |
+
"sp_model_kwargs": {},
|
264 |
+
"tokenizer_class": "LlamaTokenizer",
|
265 |
+
"unk_token": "<unk>",
|
266 |
+
"use_default_system_prompt": false
|
267 |
+
}
|