Upload tokenizer
Browse files- special_tokens_map.json +4 -4
- tokenizer_config.json +193 -193
special_tokens_map.json
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
{
|
2 |
-
"eos_token": "</s>",
|
3 |
-
"pad_token": "<pad>"
|
4 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"eos_token": "</s>",
|
3 |
+
"pad_token": "<pad>"
|
4 |
+
}
|
tokenizer_config.json
CHANGED
@@ -1,193 +1,193 @@
|
|
1 |
-
{
|
2 |
-
"added_tokens_decoder": {
|
3 |
-
"0": {
|
4 |
-
"content": "<s>",
|
5 |
-
"lstrip": false,
|
6 |
-
"normalized": false,
|
7 |
-
"rstrip": false,
|
8 |
-
"single_word": false,
|
9 |
-
"special": true
|
10 |
-
},
|
11 |
-
"1": {
|
12 |
-
"content": "<pad>",
|
13 |
-
"lstrip": false,
|
14 |
-
"normalized": false,
|
15 |
-
"rstrip": false,
|
16 |
-
"single_word": false,
|
17 |
-
"special": true
|
18 |
-
},
|
19 |
-
"2": {
|
20 |
-
"content": "</s>",
|
21 |
-
"lstrip": false,
|
22 |
-
"normalized": false,
|
23 |
-
"rstrip": false,
|
24 |
-
"single_word": false,
|
25 |
-
"special": true
|
26 |
-
},
|
27 |
-
"3": {
|
28 |
-
"content": "<unk>",
|
29 |
-
"lstrip": false,
|
30 |
-
"normalized": false,
|
31 |
-
"rstrip": false,
|
32 |
-
"single_word": false,
|
33 |
-
"special": true
|
34 |
-
},
|
35 |
-
"4": {
|
36 |
-
"content": "[START_REF]",
|
37 |
-
"lstrip": false,
|
38 |
-
"normalized": false,
|
39 |
-
"rstrip": false,
|
40 |
-
"single_word": false,
|
41 |
-
"special": true
|
42 |
-
},
|
43 |
-
"5": {
|
44 |
-
"content": "[END_REF]",
|
45 |
-
"lstrip": false,
|
46 |
-
"normalized": false,
|
47 |
-
"rstrip": false,
|
48 |
-
"single_word": false,
|
49 |
-
"special": true
|
50 |
-
},
|
51 |
-
"6": {
|
52 |
-
"content": "[IMAGE]",
|
53 |
-
"lstrip": false,
|
54 |
-
"normalized": false,
|
55 |
-
"rstrip": false,
|
56 |
-
"single_word": false,
|
57 |
-
"special": true
|
58 |
-
},
|
59 |
-
"7": {
|
60 |
-
"content": "<fragments>",
|
61 |
-
"lstrip": false,
|
62 |
-
"normalized": false,
|
63 |
-
"rstrip": false,
|
64 |
-
"single_word": false,
|
65 |
-
"special": true
|
66 |
-
},
|
67 |
-
"8": {
|
68 |
-
"content": "</fragments>",
|
69 |
-
"lstrip": false,
|
70 |
-
"normalized": false,
|
71 |
-
"rstrip": false,
|
72 |
-
"single_word": false,
|
73 |
-
"special": true
|
74 |
-
},
|
75 |
-
"9": {
|
76 |
-
"content": "<work>",
|
77 |
-
"lstrip": false,
|
78 |
-
"normalized": false,
|
79 |
-
"rstrip": false,
|
80 |
-
"single_word": false,
|
81 |
-
"special": true
|
82 |
-
},
|
83 |
-
"10": {
|
84 |
-
"content": "</work>",
|
85 |
-
"lstrip": false,
|
86 |
-
"normalized": false,
|
87 |
-
"rstrip": false,
|
88 |
-
"single_word": false,
|
89 |
-
"special": true
|
90 |
-
},
|
91 |
-
"11": {
|
92 |
-
"content": "[START_SUP]",
|
93 |
-
"lstrip": false,
|
94 |
-
"normalized": false,
|
95 |
-
"rstrip": false,
|
96 |
-
"single_word": false,
|
97 |
-
"special": true
|
98 |
-
},
|
99 |
-
"12": {
|
100 |
-
"content": "[END_SUP]",
|
101 |
-
"lstrip": false,
|
102 |
-
"normalized": false,
|
103 |
-
"rstrip": false,
|
104 |
-
"single_word": false,
|
105 |
-
"special": true
|
106 |
-
},
|
107 |
-
"13": {
|
108 |
-
"content": "[START_SUB]",
|
109 |
-
"lstrip": false,
|
110 |
-
"normalized": false,
|
111 |
-
"rstrip": false,
|
112 |
-
"single_word": false,
|
113 |
-
"special": true
|
114 |
-
},
|
115 |
-
"14": {
|
116 |
-
"content": "[END_SUB]",
|
117 |
-
"lstrip": false,
|
118 |
-
"normalized": false,
|
119 |
-
"rstrip": false,
|
120 |
-
"single_word": false,
|
121 |
-
"special": true
|
122 |
-
},
|
123 |
-
"15": {
|
124 |
-
"content": "[START_DNA]",
|
125 |
-
"lstrip": false,
|
126 |
-
"normalized": false,
|
127 |
-
"rstrip": false,
|
128 |
-
"single_word": false,
|
129 |
-
"special": true
|
130 |
-
},
|
131 |
-
"16": {
|
132 |
-
"content": "[END_DNA]",
|
133 |
-
"lstrip": false,
|
134 |
-
"normalized": false,
|
135 |
-
"rstrip": false,
|
136 |
-
"single_word": false,
|
137 |
-
"special": true
|
138 |
-
},
|
139 |
-
"17": {
|
140 |
-
"content": "[START_AMINO]",
|
141 |
-
"lstrip": false,
|
142 |
-
"normalized": false,
|
143 |
-
"rstrip": false,
|
144 |
-
"single_word": false,
|
145 |
-
"special": true
|
146 |
-
},
|
147 |
-
"18": {
|
148 |
-
"content": "[END_AMINO]",
|
149 |
-
"lstrip": false,
|
150 |
-
"normalized": false,
|
151 |
-
"rstrip": false,
|
152 |
-
"single_word": false,
|
153 |
-
"special": true
|
154 |
-
},
|
155 |
-
"19": {
|
156 |
-
"content": "[START_SMILES]",
|
157 |
-
"lstrip": false,
|
158 |
-
"normalized": false,
|
159 |
-
"rstrip": false,
|
160 |
-
"single_word": false,
|
161 |
-
"special": true
|
162 |
-
},
|
163 |
-
"20": {
|
164 |
-
"content": "[END_SMILES]",
|
165 |
-
"lstrip": false,
|
166 |
-
"normalized": false,
|
167 |
-
"rstrip": false,
|
168 |
-
"single_word": false,
|
169 |
-
"special": true
|
170 |
-
},
|
171 |
-
"21": {
|
172 |
-
"content": "[START_I_SMILES]",
|
173 |
-
"lstrip": false,
|
174 |
-
"normalized": false,
|
175 |
-
"rstrip": false,
|
176 |
-
"single_word": false,
|
177 |
-
"special": true
|
178 |
-
},
|
179 |
-
"22": {
|
180 |
-
"content": "[END_I_SMILES]",
|
181 |
-
"lstrip": false,
|
182 |
-
"normalized": false,
|
183 |
-
"rstrip": false,
|
184 |
-
"single_word": false,
|
185 |
-
"special": true
|
186 |
-
}
|
187 |
-
},
|
188 |
-
"clean_up_tokenization_spaces": true,
|
189 |
-
"eos_token": "</s>",
|
190 |
-
"model_max_length": 1000000000000000019884624838656,
|
191 |
-
"pad_token": "<pad>",
|
192 |
-
"tokenizer_class": "PreTrainedTokenizerFast"
|
193 |
-
}
|
|
|
1 |
+
{
|
2 |
+
"added_tokens_decoder": {
|
3 |
+
"0": {
|
4 |
+
"content": "<s>",
|
5 |
+
"lstrip": false,
|
6 |
+
"normalized": false,
|
7 |
+
"rstrip": false,
|
8 |
+
"single_word": false,
|
9 |
+
"special": true
|
10 |
+
},
|
11 |
+
"1": {
|
12 |
+
"content": "<pad>",
|
13 |
+
"lstrip": false,
|
14 |
+
"normalized": false,
|
15 |
+
"rstrip": false,
|
16 |
+
"single_word": false,
|
17 |
+
"special": true
|
18 |
+
},
|
19 |
+
"2": {
|
20 |
+
"content": "</s>",
|
21 |
+
"lstrip": false,
|
22 |
+
"normalized": false,
|
23 |
+
"rstrip": false,
|
24 |
+
"single_word": false,
|
25 |
+
"special": true
|
26 |
+
},
|
27 |
+
"3": {
|
28 |
+
"content": "<unk>",
|
29 |
+
"lstrip": false,
|
30 |
+
"normalized": false,
|
31 |
+
"rstrip": false,
|
32 |
+
"single_word": false,
|
33 |
+
"special": true
|
34 |
+
},
|
35 |
+
"4": {
|
36 |
+
"content": "[START_REF]",
|
37 |
+
"lstrip": false,
|
38 |
+
"normalized": false,
|
39 |
+
"rstrip": false,
|
40 |
+
"single_word": false,
|
41 |
+
"special": true
|
42 |
+
},
|
43 |
+
"5": {
|
44 |
+
"content": "[END_REF]",
|
45 |
+
"lstrip": false,
|
46 |
+
"normalized": false,
|
47 |
+
"rstrip": false,
|
48 |
+
"single_word": false,
|
49 |
+
"special": true
|
50 |
+
},
|
51 |
+
"6": {
|
52 |
+
"content": "[IMAGE]",
|
53 |
+
"lstrip": false,
|
54 |
+
"normalized": false,
|
55 |
+
"rstrip": false,
|
56 |
+
"single_word": false,
|
57 |
+
"special": true
|
58 |
+
},
|
59 |
+
"7": {
|
60 |
+
"content": "<fragments>",
|
61 |
+
"lstrip": false,
|
62 |
+
"normalized": false,
|
63 |
+
"rstrip": false,
|
64 |
+
"single_word": false,
|
65 |
+
"special": true
|
66 |
+
},
|
67 |
+
"8": {
|
68 |
+
"content": "</fragments>",
|
69 |
+
"lstrip": false,
|
70 |
+
"normalized": false,
|
71 |
+
"rstrip": false,
|
72 |
+
"single_word": false,
|
73 |
+
"special": true
|
74 |
+
},
|
75 |
+
"9": {
|
76 |
+
"content": "<work>",
|
77 |
+
"lstrip": false,
|
78 |
+
"normalized": false,
|
79 |
+
"rstrip": false,
|
80 |
+
"single_word": false,
|
81 |
+
"special": true
|
82 |
+
},
|
83 |
+
"10": {
|
84 |
+
"content": "</work>",
|
85 |
+
"lstrip": false,
|
86 |
+
"normalized": false,
|
87 |
+
"rstrip": false,
|
88 |
+
"single_word": false,
|
89 |
+
"special": true
|
90 |
+
},
|
91 |
+
"11": {
|
92 |
+
"content": "[START_SUP]",
|
93 |
+
"lstrip": false,
|
94 |
+
"normalized": false,
|
95 |
+
"rstrip": false,
|
96 |
+
"single_word": false,
|
97 |
+
"special": true
|
98 |
+
},
|
99 |
+
"12": {
|
100 |
+
"content": "[END_SUP]",
|
101 |
+
"lstrip": false,
|
102 |
+
"normalized": false,
|
103 |
+
"rstrip": false,
|
104 |
+
"single_word": false,
|
105 |
+
"special": true
|
106 |
+
},
|
107 |
+
"13": {
|
108 |
+
"content": "[START_SUB]",
|
109 |
+
"lstrip": false,
|
110 |
+
"normalized": false,
|
111 |
+
"rstrip": false,
|
112 |
+
"single_word": false,
|
113 |
+
"special": true
|
114 |
+
},
|
115 |
+
"14": {
|
116 |
+
"content": "[END_SUB]",
|
117 |
+
"lstrip": false,
|
118 |
+
"normalized": false,
|
119 |
+
"rstrip": false,
|
120 |
+
"single_word": false,
|
121 |
+
"special": true
|
122 |
+
},
|
123 |
+
"15": {
|
124 |
+
"content": "[START_DNA]",
|
125 |
+
"lstrip": false,
|
126 |
+
"normalized": false,
|
127 |
+
"rstrip": false,
|
128 |
+
"single_word": false,
|
129 |
+
"special": true
|
130 |
+
},
|
131 |
+
"16": {
|
132 |
+
"content": "[END_DNA]",
|
133 |
+
"lstrip": false,
|
134 |
+
"normalized": false,
|
135 |
+
"rstrip": false,
|
136 |
+
"single_word": false,
|
137 |
+
"special": true
|
138 |
+
},
|
139 |
+
"17": {
|
140 |
+
"content": "[START_AMINO]",
|
141 |
+
"lstrip": false,
|
142 |
+
"normalized": false,
|
143 |
+
"rstrip": false,
|
144 |
+
"single_word": false,
|
145 |
+
"special": true
|
146 |
+
},
|
147 |
+
"18": {
|
148 |
+
"content": "[END_AMINO]",
|
149 |
+
"lstrip": false,
|
150 |
+
"normalized": false,
|
151 |
+
"rstrip": false,
|
152 |
+
"single_word": false,
|
153 |
+
"special": true
|
154 |
+
},
|
155 |
+
"19": {
|
156 |
+
"content": "[START_SMILES]",
|
157 |
+
"lstrip": false,
|
158 |
+
"normalized": false,
|
159 |
+
"rstrip": false,
|
160 |
+
"single_word": false,
|
161 |
+
"special": true
|
162 |
+
},
|
163 |
+
"20": {
|
164 |
+
"content": "[END_SMILES]",
|
165 |
+
"lstrip": false,
|
166 |
+
"normalized": false,
|
167 |
+
"rstrip": false,
|
168 |
+
"single_word": false,
|
169 |
+
"special": true
|
170 |
+
},
|
171 |
+
"21": {
|
172 |
+
"content": "[START_I_SMILES]",
|
173 |
+
"lstrip": false,
|
174 |
+
"normalized": false,
|
175 |
+
"rstrip": false,
|
176 |
+
"single_word": false,
|
177 |
+
"special": true
|
178 |
+
},
|
179 |
+
"22": {
|
180 |
+
"content": "[END_I_SMILES]",
|
181 |
+
"lstrip": false,
|
182 |
+
"normalized": false,
|
183 |
+
"rstrip": false,
|
184 |
+
"single_word": false,
|
185 |
+
"special": true
|
186 |
+
}
|
187 |
+
},
|
188 |
+
"clean_up_tokenization_spaces": true,
|
189 |
+
"eos_token": "</s>",
|
190 |
+
"model_max_length": 1000000000000000019884624838656,
|
191 |
+
"pad_token": "<pad>",
|
192 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
193 |
+
}
|