Upload tokenizer.json with huggingface_hub
Browse files- tokenizer.json +213 -0
tokenizer.json
ADDED
@@ -0,0 +1,213 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
5 |
+
"added_tokens": [
|
6 |
+
{
|
7 |
+
"id": 0,
|
8 |
+
"content": "<unk>",
|
9 |
+
"single_word": false,
|
10 |
+
"lstrip": false,
|
11 |
+
"rstrip": false,
|
12 |
+
"normalized": false,
|
13 |
+
"special": true
|
14 |
+
},
|
15 |
+
{
|
16 |
+
"id": 100,
|
17 |
+
"content": "<s>",
|
18 |
+
"single_word": false,
|
19 |
+
"lstrip": false,
|
20 |
+
"rstrip": false,
|
21 |
+
"normalized": false,
|
22 |
+
"special": true
|
23 |
+
},
|
24 |
+
{
|
25 |
+
"id": 101,
|
26 |
+
"content": "</s>",
|
27 |
+
"single_word": false,
|
28 |
+
"lstrip": false,
|
29 |
+
"rstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"special": true
|
32 |
+
},
|
33 |
+
{
|
34 |
+
"id": 102,
|
35 |
+
"content": "<pad>",
|
36 |
+
"single_word": false,
|
37 |
+
"lstrip": false,
|
38 |
+
"rstrip": false,
|
39 |
+
"normalized": false,
|
40 |
+
"special": true
|
41 |
+
}
|
42 |
+
],
|
43 |
+
"normalizer": null,
|
44 |
+
"pre_tokenizer": {
|
45 |
+
"type": "Split",
|
46 |
+
"pattern": {
|
47 |
+
"String": " "
|
48 |
+
},
|
49 |
+
"behavior": "Isolated",
|
50 |
+
"invert": false
|
51 |
+
},
|
52 |
+
"post_processor": null,
|
53 |
+
"decoder": null,
|
54 |
+
"model": {
|
55 |
+
"type": "BPE",
|
56 |
+
"dropout": null,
|
57 |
+
"unk_token": "<unk>",
|
58 |
+
"continuing_subword_prefix": null,
|
59 |
+
"end_of_word_suffix": null,
|
60 |
+
"fuse_unk": false,
|
61 |
+
"byte_fallback": false,
|
62 |
+
"ignore_merges": false,
|
63 |
+
"vocab": {
|
64 |
+
"<unk>": 0,
|
65 |
+
" ": 1,
|
66 |
+
".": 2,
|
67 |
+
"A": 3,
|
68 |
+
"B": 4,
|
69 |
+
"C": 5,
|
70 |
+
"D": 6,
|
71 |
+
"E": 7,
|
72 |
+
"F": 8,
|
73 |
+
"G": 9,
|
74 |
+
"H": 10,
|
75 |
+
"I": 11,
|
76 |
+
"J": 12,
|
77 |
+
"K": 13,
|
78 |
+
"L": 14,
|
79 |
+
"M": 15,
|
80 |
+
"N": 16,
|
81 |
+
"O": 17,
|
82 |
+
"P": 18,
|
83 |
+
"Q": 19,
|
84 |
+
"R": 20,
|
85 |
+
"S": 21,
|
86 |
+
"T": 22,
|
87 |
+
"U": 23,
|
88 |
+
"V": 24,
|
89 |
+
"W": 25,
|
90 |
+
"X": 26,
|
91 |
+
"Y": 27,
|
92 |
+
"Z": 28,
|
93 |
+
"a": 29,
|
94 |
+
"b": 30,
|
95 |
+
"c": 31,
|
96 |
+
"d": 32,
|
97 |
+
"e": 33,
|
98 |
+
"f": 34,
|
99 |
+
"g": 35,
|
100 |
+
"h": 36,
|
101 |
+
"i": 37,
|
102 |
+
"j": 38,
|
103 |
+
"k": 39,
|
104 |
+
"l": 40,
|
105 |
+
"m": 41,
|
106 |
+
"n": 42,
|
107 |
+
"o": 43,
|
108 |
+
"p": 44,
|
109 |
+
"q": 45,
|
110 |
+
"r": 46,
|
111 |
+
"s": 47,
|
112 |
+
"t": 48,
|
113 |
+
"u": 49,
|
114 |
+
"v": 50,
|
115 |
+
"w": 51,
|
116 |
+
"x": 52,
|
117 |
+
"y": 53,
|
118 |
+
"z": 54,
|
119 |
+
"ch": 55,
|
120 |
+
"cho": 56,
|
121 |
+
"echo": 57,
|
122 |
+
"up": 58,
|
123 |
+
"pe": 59,
|
124 |
+
"uppe": 60,
|
125 |
+
"upper": 61,
|
126 |
+
"fo": 62,
|
127 |
+
"nc": 63,
|
128 |
+
"b.": 64,
|
129 |
+
"et": 65,
|
130 |
+
"ip": 66,
|
131 |
+
"mk": 67,
|
132 |
+
"qz": 68,
|
133 |
+
"wx": 69,
|
134 |
+
"kx": 70,
|
135 |
+
"qo": 71,
|
136 |
+
"y.": 72,
|
137 |
+
"ej": 73,
|
138 |
+
"k.": 74,
|
139 |
+
"tg": 75,
|
140 |
+
"bt": 76,
|
141 |
+
"iu": 77,
|
142 |
+
"kk": 78,
|
143 |
+
"sx": 79,
|
144 |
+
"B.": 80,
|
145 |
+
"M.": 81,
|
146 |
+
"fy": 82,
|
147 |
+
"mp": 83,
|
148 |
+
"ou": 84,
|
149 |
+
"pf": 85,
|
150 |
+
"v.": 86,
|
151 |
+
"yo": 87,
|
152 |
+
"P.": 88,
|
153 |
+
"jg": 89,
|
154 |
+
"kq": 90,
|
155 |
+
"m.": 91,
|
156 |
+
"mt": 92,
|
157 |
+
"nh": 93,
|
158 |
+
"qr": 94,
|
159 |
+
"wq": 95,
|
160 |
+
"O.": 96,
|
161 |
+
"aj": 97,
|
162 |
+
"ax": 98,
|
163 |
+
"dt": 99
|
164 |
+
},
|
165 |
+
"merges": [
|
166 |
+
"c h",
|
167 |
+
"ch o",
|
168 |
+
"e cho",
|
169 |
+
"u p",
|
170 |
+
"p e",
|
171 |
+
"up pe",
|
172 |
+
"uppe r",
|
173 |
+
"f o",
|
174 |
+
"n c",
|
175 |
+
"b .",
|
176 |
+
"e t",
|
177 |
+
"i p",
|
178 |
+
"m k",
|
179 |
+
"q z",
|
180 |
+
"w x",
|
181 |
+
"k x",
|
182 |
+
"q o",
|
183 |
+
"y .",
|
184 |
+
"e j",
|
185 |
+
"k .",
|
186 |
+
"t g",
|
187 |
+
"b t",
|
188 |
+
"i u",
|
189 |
+
"k k",
|
190 |
+
"s x",
|
191 |
+
"B .",
|
192 |
+
"M .",
|
193 |
+
"f y",
|
194 |
+
"m p",
|
195 |
+
"o u",
|
196 |
+
"p f",
|
197 |
+
"v .",
|
198 |
+
"y o",
|
199 |
+
"P .",
|
200 |
+
"j g",
|
201 |
+
"k q",
|
202 |
+
"m .",
|
203 |
+
"m t",
|
204 |
+
"n h",
|
205 |
+
"q r",
|
206 |
+
"w q",
|
207 |
+
"O .",
|
208 |
+
"a j",
|
209 |
+
"a x",
|
210 |
+
"d t"
|
211 |
+
]
|
212 |
+
}
|
213 |
+
}
|