Update tokenizer_config.json
Browse files- tokenizer_config.json +5 -181
tokenizer_config.json
CHANGED
@@ -10,191 +10,15 @@
|
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
-
"content": "<|
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
-
"
|
21 |
-
"content": "
|
22 |
-
"lstrip": false,
|
23 |
-
"normalized": true,
|
24 |
-
"rstrip": false,
|
25 |
-
"single_word": false,
|
26 |
-
"special": false
|
27 |
-
},
|
28 |
-
"50255": {
|
29 |
-
"content": " ",
|
30 |
-
"lstrip": false,
|
31 |
-
"normalized": true,
|
32 |
-
"rstrip": false,
|
33 |
-
"single_word": false,
|
34 |
-
"special": false
|
35 |
-
},
|
36 |
-
"50256": {
|
37 |
-
"content": " ",
|
38 |
-
"lstrip": false,
|
39 |
-
"normalized": true,
|
40 |
-
"rstrip": false,
|
41 |
-
"single_word": false,
|
42 |
-
"special": false
|
43 |
-
},
|
44 |
-
"50257": {
|
45 |
-
"content": " ",
|
46 |
-
"lstrip": false,
|
47 |
-
"normalized": true,
|
48 |
-
"rstrip": false,
|
49 |
-
"single_word": false,
|
50 |
-
"special": false
|
51 |
-
},
|
52 |
-
"50258": {
|
53 |
-
"content": " ",
|
54 |
-
"lstrip": false,
|
55 |
-
"normalized": true,
|
56 |
-
"rstrip": false,
|
57 |
-
"single_word": false,
|
58 |
-
"special": false
|
59 |
-
},
|
60 |
-
"50259": {
|
61 |
-
"content": " ",
|
62 |
-
"lstrip": false,
|
63 |
-
"normalized": true,
|
64 |
-
"rstrip": false,
|
65 |
-
"single_word": false,
|
66 |
-
"special": false
|
67 |
-
},
|
68 |
-
"50260": {
|
69 |
-
"content": " ",
|
70 |
-
"lstrip": false,
|
71 |
-
"normalized": true,
|
72 |
-
"rstrip": false,
|
73 |
-
"single_word": false,
|
74 |
-
"special": false
|
75 |
-
},
|
76 |
-
"50261": {
|
77 |
-
"content": " ",
|
78 |
-
"lstrip": false,
|
79 |
-
"normalized": true,
|
80 |
-
"rstrip": false,
|
81 |
-
"single_word": false,
|
82 |
-
"special": false
|
83 |
-
},
|
84 |
-
"50262": {
|
85 |
-
"content": " ",
|
86 |
-
"lstrip": false,
|
87 |
-
"normalized": true,
|
88 |
-
"rstrip": false,
|
89 |
-
"single_word": false,
|
90 |
-
"special": false
|
91 |
-
},
|
92 |
-
"50263": {
|
93 |
-
"content": " ",
|
94 |
-
"lstrip": false,
|
95 |
-
"normalized": true,
|
96 |
-
"rstrip": false,
|
97 |
-
"single_word": false,
|
98 |
-
"special": false
|
99 |
-
},
|
100 |
-
"50264": {
|
101 |
-
"content": " ",
|
102 |
-
"lstrip": false,
|
103 |
-
"normalized": true,
|
104 |
-
"rstrip": false,
|
105 |
-
"single_word": false,
|
106 |
-
"special": false
|
107 |
-
},
|
108 |
-
"50265": {
|
109 |
-
"content": " ",
|
110 |
-
"lstrip": false,
|
111 |
-
"normalized": true,
|
112 |
-
"rstrip": false,
|
113 |
-
"single_word": false,
|
114 |
-
"special": false
|
115 |
-
},
|
116 |
-
"50266": {
|
117 |
-
"content": " ",
|
118 |
-
"lstrip": false,
|
119 |
-
"normalized": true,
|
120 |
-
"rstrip": false,
|
121 |
-
"single_word": false,
|
122 |
-
"special": false
|
123 |
-
},
|
124 |
-
"50267": {
|
125 |
-
"content": " ",
|
126 |
-
"lstrip": false,
|
127 |
-
"normalized": true,
|
128 |
-
"rstrip": false,
|
129 |
-
"single_word": false,
|
130 |
-
"special": false
|
131 |
-
},
|
132 |
-
"50268": {
|
133 |
-
"content": " ",
|
134 |
-
"lstrip": false,
|
135 |
-
"normalized": true,
|
136 |
-
"rstrip": false,
|
137 |
-
"single_word": false,
|
138 |
-
"special": false
|
139 |
-
},
|
140 |
-
"50269": {
|
141 |
-
"content": " ",
|
142 |
-
"lstrip": false,
|
143 |
-
"normalized": true,
|
144 |
-
"rstrip": false,
|
145 |
-
"single_word": false,
|
146 |
-
"special": false
|
147 |
-
},
|
148 |
-
"50270": {
|
149 |
-
"content": " ",
|
150 |
-
"lstrip": false,
|
151 |
-
"normalized": true,
|
152 |
-
"rstrip": false,
|
153 |
-
"single_word": false,
|
154 |
-
"special": false
|
155 |
-
},
|
156 |
-
"50271": {
|
157 |
-
"content": " ",
|
158 |
-
"lstrip": false,
|
159 |
-
"normalized": true,
|
160 |
-
"rstrip": false,
|
161 |
-
"single_word": false,
|
162 |
-
"special": false
|
163 |
-
},
|
164 |
-
"50272": {
|
165 |
-
"content": " ",
|
166 |
-
"lstrip": false,
|
167 |
-
"normalized": true,
|
168 |
-
"rstrip": false,
|
169 |
-
"single_word": false,
|
170 |
-
"special": false
|
171 |
-
},
|
172 |
-
"50273": {
|
173 |
-
"content": " ",
|
174 |
-
"lstrip": false,
|
175 |
-
"normalized": true,
|
176 |
-
"rstrip": false,
|
177 |
-
"single_word": false,
|
178 |
-
"special": false
|
179 |
-
},
|
180 |
-
"50274": {
|
181 |
-
"content": " ",
|
182 |
-
"lstrip": false,
|
183 |
-
"normalized": true,
|
184 |
-
"rstrip": false,
|
185 |
-
"single_word": false,
|
186 |
-
"special": false
|
187 |
-
},
|
188 |
-
"50275": {
|
189 |
-
"content": " ",
|
190 |
-
"lstrip": false,
|
191 |
-
"normalized": true,
|
192 |
-
"rstrip": false,
|
193 |
-
"single_word": false,
|
194 |
-
"special": false
|
195 |
-
},
|
196 |
-
"50276": {
|
197 |
-
"content": " ",
|
198 |
"lstrip": false,
|
199 |
"normalized": true,
|
200 |
"rstrip": false,
|
@@ -202,11 +26,11 @@
|
|
202 |
"special": false
|
203 |
}
|
204 |
},
|
205 |
-
"bos_token": "<|
|
206 |
"clean_up_tokenization_spaces": true,
|
207 |
"eos_token": "<|endoftext|>",
|
208 |
"model_max_length": 1000000000000000019884624838656,
|
209 |
"pad_token": "<|endoftext|>",
|
210 |
"tokenizer_class": "GPTNeoXTokenizer",
|
211 |
-
"unk_token": "<|
|
212 |
}
|
|
|
10 |
"special": true
|
11 |
},
|
12 |
"1": {
|
13 |
+
"content": "<|unknown|>",
|
14 |
"lstrip": false,
|
15 |
"normalized": false,
|
16 |
"rstrip": false,
|
17 |
"single_word": false,
|
18 |
"special": true
|
19 |
},
|
20 |
+
"2": {
|
21 |
+
"content": "<|beginoftext|>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
22 |
"lstrip": false,
|
23 |
"normalized": true,
|
24 |
"rstrip": false,
|
|
|
26 |
"special": false
|
27 |
}
|
28 |
},
|
29 |
+
"bos_token": "<|beginoftext|>",
|
30 |
"clean_up_tokenization_spaces": true,
|
31 |
"eos_token": "<|endoftext|>",
|
32 |
"model_max_length": 1000000000000000019884624838656,
|
33 |
"pad_token": "<|endoftext|>",
|
34 |
"tokenizer_class": "GPTNeoXTokenizer",
|
35 |
+
"unk_token": "<|unknown|>"
|
36 |
}
|