Upload tokenizer
Browse files- added_tokens.json +4 -0
- merges.txt +1 -0
- special_tokens_map.json +51 -0
- tokenizer.json +714 -0
- tokenizer_config.json +75 -0
- vocab.json +1 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 592,
|
| 3 |
+
"<s>": 591
|
| 4 |
+
}
|
merges.txt
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
#version: 0.2
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,51 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"bos_token": {
|
| 3 |
+
"content": "<s>",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": true,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"eos_token": {
|
| 17 |
+
"content": "</s>",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": true,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
+
"lstrip": true,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"pad_token": {
|
| 31 |
+
"content": "[PAD]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": true,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
},
|
| 37 |
+
"sep_token": {
|
| 38 |
+
"content": "[SEP]",
|
| 39 |
+
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
+
"rstrip": false,
|
| 42 |
+
"single_word": false
|
| 43 |
+
},
|
| 44 |
+
"unk_token": {
|
| 45 |
+
"content": "[UNK]",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false
|
| 50 |
+
}
|
| 51 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,714 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 512,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 512
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "[PAD]"
|
| 18 |
+
},
|
| 19 |
+
"added_tokens": [
|
| 20 |
+
{
|
| 21 |
+
"id": 0,
|
| 22 |
+
"content": "[PAD]",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": true,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"id": 11,
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"normalized": true,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"id": 12,
|
| 40 |
+
"content": "[CLS]",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": true,
|
| 45 |
+
"special": true
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"id": 13,
|
| 49 |
+
"content": "[SEP]",
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"normalized": true,
|
| 54 |
+
"special": true
|
| 55 |
+
},
|
| 56 |
+
{
|
| 57 |
+
"id": 14,
|
| 58 |
+
"content": "[MASK]",
|
| 59 |
+
"single_word": false,
|
| 60 |
+
"lstrip": true,
|
| 61 |
+
"rstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"special": true
|
| 64 |
+
},
|
| 65 |
+
{
|
| 66 |
+
"id": 591,
|
| 67 |
+
"content": "<s>",
|
| 68 |
+
"single_word": false,
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"rstrip": false,
|
| 71 |
+
"normalized": true,
|
| 72 |
+
"special": true
|
| 73 |
+
},
|
| 74 |
+
{
|
| 75 |
+
"id": 592,
|
| 76 |
+
"content": "</s>",
|
| 77 |
+
"single_word": false,
|
| 78 |
+
"lstrip": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"normalized": true,
|
| 81 |
+
"special": true
|
| 82 |
+
}
|
| 83 |
+
],
|
| 84 |
+
"normalizer": null,
|
| 85 |
+
"pre_tokenizer": {
|
| 86 |
+
"type": "ByteLevel",
|
| 87 |
+
"add_prefix_space": false,
|
| 88 |
+
"trim_offsets": true,
|
| 89 |
+
"use_regex": true
|
| 90 |
+
},
|
| 91 |
+
"post_processor": {
|
| 92 |
+
"type": "RobertaProcessing",
|
| 93 |
+
"sep": [
|
| 94 |
+
"[SEP]",
|
| 95 |
+
13
|
| 96 |
+
],
|
| 97 |
+
"cls": [
|
| 98 |
+
"[CLS]",
|
| 99 |
+
12
|
| 100 |
+
],
|
| 101 |
+
"trim_offsets": true,
|
| 102 |
+
"add_prefix_space": false
|
| 103 |
+
},
|
| 104 |
+
"decoder": {
|
| 105 |
+
"type": "ByteLevel",
|
| 106 |
+
"add_prefix_space": true,
|
| 107 |
+
"trim_offsets": true,
|
| 108 |
+
"use_regex": true
|
| 109 |
+
},
|
| 110 |
+
"model": {
|
| 111 |
+
"type": "BPE",
|
| 112 |
+
"dropout": null,
|
| 113 |
+
"unk_token": null,
|
| 114 |
+
"continuing_subword_prefix": "",
|
| 115 |
+
"end_of_word_suffix": "",
|
| 116 |
+
"fuse_unk": false,
|
| 117 |
+
"byte_fallback": false,
|
| 118 |
+
"ignore_merges": false,
|
| 119 |
+
"vocab": {
|
| 120 |
+
"[PAD]": 0,
|
| 121 |
+
"[unused1]": 1,
|
| 122 |
+
"[unused2]": 2,
|
| 123 |
+
"[unused3]": 3,
|
| 124 |
+
"[unused4]": 4,
|
| 125 |
+
"[unused5]": 5,
|
| 126 |
+
"[unused6]": 6,
|
| 127 |
+
"[unused7]": 7,
|
| 128 |
+
"[unused8]": 8,
|
| 129 |
+
"[unused9]": 9,
|
| 130 |
+
"[unused10]": 10,
|
| 131 |
+
"[UNK]": 11,
|
| 132 |
+
"[CLS]": 12,
|
| 133 |
+
"[SEP]": 13,
|
| 134 |
+
"[MASK]": 14,
|
| 135 |
+
"c": 15,
|
| 136 |
+
"C": 16,
|
| 137 |
+
"(": 17,
|
| 138 |
+
")": 18,
|
| 139 |
+
"O": 19,
|
| 140 |
+
"1": 20,
|
| 141 |
+
"2": 21,
|
| 142 |
+
"=": 22,
|
| 143 |
+
"N": 23,
|
| 144 |
+
".": 24,
|
| 145 |
+
"n": 25,
|
| 146 |
+
"3": 26,
|
| 147 |
+
"F": 27,
|
| 148 |
+
"Cl": 28,
|
| 149 |
+
">>": 29,
|
| 150 |
+
"~": 30,
|
| 151 |
+
"-": 31,
|
| 152 |
+
"4": 32,
|
| 153 |
+
"[C@H]": 33,
|
| 154 |
+
"S": 34,
|
| 155 |
+
"[C@@H]": 35,
|
| 156 |
+
"[O-]": 36,
|
| 157 |
+
"Br": 37,
|
| 158 |
+
"#": 38,
|
| 159 |
+
"/": 39,
|
| 160 |
+
"[nH]": 40,
|
| 161 |
+
"[N+]": 41,
|
| 162 |
+
"s": 42,
|
| 163 |
+
"5": 43,
|
| 164 |
+
"o": 44,
|
| 165 |
+
"P": 45,
|
| 166 |
+
"[Na+]": 46,
|
| 167 |
+
"[Si]": 47,
|
| 168 |
+
"I": 48,
|
| 169 |
+
"[Na]": 49,
|
| 170 |
+
"[Pd]": 50,
|
| 171 |
+
"[K+]": 51,
|
| 172 |
+
"[K]": 52,
|
| 173 |
+
"[P]": 53,
|
| 174 |
+
"B": 54,
|
| 175 |
+
"[C@]": 55,
|
| 176 |
+
"[C@@]": 56,
|
| 177 |
+
"[Cl-]": 57,
|
| 178 |
+
"6": 58,
|
| 179 |
+
"[OH-]": 59,
|
| 180 |
+
"\\": 60,
|
| 181 |
+
"[N-]": 61,
|
| 182 |
+
"[Li]": 62,
|
| 183 |
+
"[H]": 63,
|
| 184 |
+
"[2H]": 64,
|
| 185 |
+
"[NH4+]": 65,
|
| 186 |
+
"[c-]": 66,
|
| 187 |
+
"[P-]": 67,
|
| 188 |
+
"[Cs+]": 68,
|
| 189 |
+
"[Li+]": 69,
|
| 190 |
+
"[Cs]": 70,
|
| 191 |
+
"[NaH]": 71,
|
| 192 |
+
"[H-]": 72,
|
| 193 |
+
"[O+]": 73,
|
| 194 |
+
"[BH4-]": 74,
|
| 195 |
+
"[Cu]": 75,
|
| 196 |
+
"7": 76,
|
| 197 |
+
"[Mg]": 77,
|
| 198 |
+
"[Fe+2]": 78,
|
| 199 |
+
"[n+]": 79,
|
| 200 |
+
"[Sn]": 80,
|
| 201 |
+
"[BH-]": 81,
|
| 202 |
+
"[Pd+2]": 82,
|
| 203 |
+
"[CH]": 83,
|
| 204 |
+
"[I-]": 84,
|
| 205 |
+
"[Br-]": 85,
|
| 206 |
+
"[C-]": 86,
|
| 207 |
+
"[Zn]": 87,
|
| 208 |
+
"[B-]": 88,
|
| 209 |
+
"[F-]": 89,
|
| 210 |
+
"[Al]": 90,
|
| 211 |
+
"[P+]": 91,
|
| 212 |
+
"[BH3-]": 92,
|
| 213 |
+
"[Fe]": 93,
|
| 214 |
+
"[C]": 94,
|
| 215 |
+
"[AlH4]": 95,
|
| 216 |
+
"[Ni]": 96,
|
| 217 |
+
"[SiH]": 97,
|
| 218 |
+
"8": 98,
|
| 219 |
+
"[Cu+2]": 99,
|
| 220 |
+
"[Mn]": 100,
|
| 221 |
+
"[AlH]": 101,
|
| 222 |
+
"[nH+]": 102,
|
| 223 |
+
"[AlH4-]": 103,
|
| 224 |
+
"[O-2]": 104,
|
| 225 |
+
"[Cr]": 105,
|
| 226 |
+
"[Mg+2]": 106,
|
| 227 |
+
"[NH3+]": 107,
|
| 228 |
+
"[S@]": 108,
|
| 229 |
+
"[Pt]": 109,
|
| 230 |
+
"[Al+3]": 110,
|
| 231 |
+
"[S@@]": 111,
|
| 232 |
+
"[S-]": 112,
|
| 233 |
+
"[Ti]": 113,
|
| 234 |
+
"[Zn+2]": 114,
|
| 235 |
+
"[PH]": 115,
|
| 236 |
+
"[NH2+]": 116,
|
| 237 |
+
"[Ru]": 117,
|
| 238 |
+
"[Ag+]": 118,
|
| 239 |
+
"[S+]": 119,
|
| 240 |
+
"[I+3]": 120,
|
| 241 |
+
"[NH+]": 121,
|
| 242 |
+
"[Ca+2]": 122,
|
| 243 |
+
"[Ag]": 123,
|
| 244 |
+
"9": 124,
|
| 245 |
+
"[Os]": 125,
|
| 246 |
+
"[Se]": 126,
|
| 247 |
+
"[SiH2]": 127,
|
| 248 |
+
"[Ca]": 128,
|
| 249 |
+
"[Ti+4]": 129,
|
| 250 |
+
"[Ac]": 130,
|
| 251 |
+
"[Cu+]": 131,
|
| 252 |
+
"[S]": 132,
|
| 253 |
+
"[Rh]": 133,
|
| 254 |
+
"[Cl+3]": 134,
|
| 255 |
+
"[cH-]": 135,
|
| 256 |
+
"[Zn+]": 136,
|
| 257 |
+
"[O]": 137,
|
| 258 |
+
"[Cl+]": 138,
|
| 259 |
+
"[SH]": 139,
|
| 260 |
+
"[H+]": 140,
|
| 261 |
+
"[Pd+]": 141,
|
| 262 |
+
"[se]": 142,
|
| 263 |
+
"[PH+]": 143,
|
| 264 |
+
"[I]": 144,
|
| 265 |
+
"[Pt+2]": 145,
|
| 266 |
+
"[C+]": 146,
|
| 267 |
+
"[Mg+]": 147,
|
| 268 |
+
"[Hg]": 148,
|
| 269 |
+
"[W]": 149,
|
| 270 |
+
"[SnH]": 150,
|
| 271 |
+
"[SiH3]": 151,
|
| 272 |
+
"[Fe+3]": 152,
|
| 273 |
+
"[NH]": 153,
|
| 274 |
+
"[Mo]": 154,
|
| 275 |
+
"[CH2+]": 155,
|
| 276 |
+
"%10": 156,
|
| 277 |
+
"[CH2-]": 157,
|
| 278 |
+
"[CH2]": 158,
|
| 279 |
+
"[n-]": 159,
|
| 280 |
+
"[Ce+4]": 160,
|
| 281 |
+
"[NH-]": 161,
|
| 282 |
+
"[Co]": 162,
|
| 283 |
+
"[I+]": 163,
|
| 284 |
+
"[PH2]": 164,
|
| 285 |
+
"[Pt+4]": 165,
|
| 286 |
+
"[Ce]": 166,
|
| 287 |
+
"[B]": 167,
|
| 288 |
+
"[Sn+2]": 168,
|
| 289 |
+
"[Ba+2]": 169,
|
| 290 |
+
"%11": 170,
|
| 291 |
+
"[Fe-3]": 171,
|
| 292 |
+
"[18F]": 172,
|
| 293 |
+
"[SH-]": 173,
|
| 294 |
+
"[Pb+2]": 174,
|
| 295 |
+
"[Os-2]": 175,
|
| 296 |
+
"[Zr+4]": 176,
|
| 297 |
+
"[N]": 177,
|
| 298 |
+
"[Ir]": 178,
|
| 299 |
+
"[Bi]": 179,
|
| 300 |
+
"[Ni+2]": 180,
|
| 301 |
+
"[P@]": 181,
|
| 302 |
+
"[Co+2]": 182,
|
| 303 |
+
"[s+]": 183,
|
| 304 |
+
"[As]": 184,
|
| 305 |
+
"[P+3]": 185,
|
| 306 |
+
"[Hg+2]": 186,
|
| 307 |
+
"[Yb+3]": 187,
|
| 308 |
+
"[CH-]": 188,
|
| 309 |
+
"[Zr+2]": 189,
|
| 310 |
+
"[Mn+2]": 190,
|
| 311 |
+
"[CH+]": 191,
|
| 312 |
+
"[In]": 192,
|
| 313 |
+
"[KH]": 193,
|
| 314 |
+
"[Ce+3]": 194,
|
| 315 |
+
"[Zr]": 195,
|
| 316 |
+
"[AlH2-]": 196,
|
| 317 |
+
"[OH2+]": 197,
|
| 318 |
+
"[Ti+3]": 198,
|
| 319 |
+
"[Rh+2]": 199,
|
| 320 |
+
"[Sb]": 200,
|
| 321 |
+
"[S-2]": 201,
|
| 322 |
+
"%12": 202,
|
| 323 |
+
"[P@@]": 203,
|
| 324 |
+
"[Si@H]": 204,
|
| 325 |
+
"[Mn+4]": 205,
|
| 326 |
+
"p": 206,
|
| 327 |
+
"[Ba]": 207,
|
| 328 |
+
"[NH2-]": 208,
|
| 329 |
+
"[Ge]": 209,
|
| 330 |
+
"[Pb+4]": 210,
|
| 331 |
+
"[Cr+3]": 211,
|
| 332 |
+
"[Au]": 212,
|
| 333 |
+
"[LiH]": 213,
|
| 334 |
+
"[Sc+3]": 214,
|
| 335 |
+
"[o+]": 215,
|
| 336 |
+
"[Rh-3]": 216,
|
| 337 |
+
"%13": 217,
|
| 338 |
+
"[Br]": 218,
|
| 339 |
+
"[Sb-]": 219,
|
| 340 |
+
"[S@+]": 220,
|
| 341 |
+
"[I+2]": 221,
|
| 342 |
+
"[Ar]": 222,
|
| 343 |
+
"[V]": 223,
|
| 344 |
+
"[Cu-]": 224,
|
| 345 |
+
"[Al-]": 225,
|
| 346 |
+
"[Te]": 226,
|
| 347 |
+
"[13c]": 227,
|
| 348 |
+
"[13C]": 228,
|
| 349 |
+
"[Cl]": 229,
|
| 350 |
+
"[PH4+]": 230,
|
| 351 |
+
"[SiH4]": 231,
|
| 352 |
+
"[te]": 232,
|
| 353 |
+
"[CH3-]": 233,
|
| 354 |
+
"[S@@+]": 234,
|
| 355 |
+
"[Rh+3]": 235,
|
| 356 |
+
"[SH+]": 236,
|
| 357 |
+
"[Bi+3]": 237,
|
| 358 |
+
"[Br+2]": 238,
|
| 359 |
+
"[La]": 239,
|
| 360 |
+
"[La+3]": 240,
|
| 361 |
+
"[Pt-2]": 241,
|
| 362 |
+
"[N@@]": 242,
|
| 363 |
+
"[PH3+]": 243,
|
| 364 |
+
"[N@]": 244,
|
| 365 |
+
"[Si+4]": 245,
|
| 366 |
+
"[Sr+2]": 246,
|
| 367 |
+
"[Al+]": 247,
|
| 368 |
+
"[Pb]": 248,
|
| 369 |
+
"[SeH]": 249,
|
| 370 |
+
"[Si-]": 250,
|
| 371 |
+
"[V+5]": 251,
|
| 372 |
+
"[Y+3]": 252,
|
| 373 |
+
"[Re]": 253,
|
| 374 |
+
"[Ru+]": 254,
|
| 375 |
+
"[Sm]": 255,
|
| 376 |
+
"*": 256,
|
| 377 |
+
"[3H]": 257,
|
| 378 |
+
"[NH2]": 258,
|
| 379 |
+
"[Ag-]": 259,
|
| 380 |
+
"[13CH3]": 260,
|
| 381 |
+
"[OH+]": 261,
|
| 382 |
+
"[Ru+3]": 262,
|
| 383 |
+
"[OH]": 263,
|
| 384 |
+
"[Gd+3]": 264,
|
| 385 |
+
"[13CH2]": 265,
|
| 386 |
+
"[In+3]": 266,
|
| 387 |
+
"[Si@@]": 267,
|
| 388 |
+
"[Si@]": 268,
|
| 389 |
+
"[Ti+2]": 269,
|
| 390 |
+
"[Sn+]": 270,
|
| 391 |
+
"[Cl+2]": 271,
|
| 392 |
+
"[AlH-]": 272,
|
| 393 |
+
"[Pd-2]": 273,
|
| 394 |
+
"[SnH3]": 274,
|
| 395 |
+
"[B+3]": 275,
|
| 396 |
+
"[Cu-2]": 276,
|
| 397 |
+
"[Nd+3]": 277,
|
| 398 |
+
"[Pb+3]": 278,
|
| 399 |
+
"[13cH]": 279,
|
| 400 |
+
"[Fe-4]": 280,
|
| 401 |
+
"[Ga]": 281,
|
| 402 |
+
"[Sn+4]": 282,
|
| 403 |
+
"[Hg+]": 283,
|
| 404 |
+
"[11CH3]": 284,
|
| 405 |
+
"[Hf]": 285,
|
| 406 |
+
"[Pr]": 286,
|
| 407 |
+
"[Y]": 287,
|
| 408 |
+
"[S+2]": 288,
|
| 409 |
+
"[Cd]": 289,
|
| 410 |
+
"[Cr+6]": 290,
|
| 411 |
+
"[Zr+3]": 291,
|
| 412 |
+
"[Rh+]": 292,
|
| 413 |
+
"[CH3]": 293,
|
| 414 |
+
"[N-3]": 294,
|
| 415 |
+
"[Hf+2]": 295,
|
| 416 |
+
"[Th]": 296,
|
| 417 |
+
"[Sb+3]": 297,
|
| 418 |
+
"%14": 298,
|
| 419 |
+
"[Cr+2]": 299,
|
| 420 |
+
"[Ru+2]": 300,
|
| 421 |
+
"[Hf+4]": 301,
|
| 422 |
+
"[14C]": 302,
|
| 423 |
+
"[Ta]": 303,
|
| 424 |
+
"[Tl+]": 304,
|
| 425 |
+
"[B+]": 305,
|
| 426 |
+
"[Os+4]": 306,
|
| 427 |
+
"[PdH2]": 307,
|
| 428 |
+
"[Pd-]": 308,
|
| 429 |
+
"[Cd+2]": 309,
|
| 430 |
+
"[Co+3]": 310,
|
| 431 |
+
"[S+4]": 311,
|
| 432 |
+
"[Nb+5]": 312,
|
| 433 |
+
"[123I]": 313,
|
| 434 |
+
"[c+]": 314,
|
| 435 |
+
"[Rb+]": 315,
|
| 436 |
+
"[V+2]": 316,
|
| 437 |
+
"[CH3+]": 317,
|
| 438 |
+
"[Ag+2]": 318,
|
| 439 |
+
"[cH+]": 319,
|
| 440 |
+
"[Mn+3]": 320,
|
| 441 |
+
"[Se-]": 321,
|
| 442 |
+
"[As-]": 322,
|
| 443 |
+
"[Eu+3]": 323,
|
| 444 |
+
"[SH2]": 324,
|
| 445 |
+
"[Sm+3]": 325,
|
| 446 |
+
"[IH+]": 326,
|
| 447 |
+
"%15": 327,
|
| 448 |
+
"[OH3+]": 328,
|
| 449 |
+
"[PH3]": 329,
|
| 450 |
+
"[IH2+]": 330,
|
| 451 |
+
"[SH2+]": 331,
|
| 452 |
+
"[Ir+3]": 332,
|
| 453 |
+
"[AlH3]": 333,
|
| 454 |
+
"[Sc]": 334,
|
| 455 |
+
"[Yb]": 335,
|
| 456 |
+
"[15NH2]": 336,
|
| 457 |
+
"[Lu]": 337,
|
| 458 |
+
"[sH+]": 338,
|
| 459 |
+
"[Gd]": 339,
|
| 460 |
+
"[18F-]": 340,
|
| 461 |
+
"[SH3+]": 341,
|
| 462 |
+
"[SnH4]": 342,
|
| 463 |
+
"[TeH]": 343,
|
| 464 |
+
"[Si@@H]": 344,
|
| 465 |
+
"[Ga+3]": 345,
|
| 466 |
+
"[CaH2]": 346,
|
| 467 |
+
"[Tl]": 347,
|
| 468 |
+
"[Ta+5]": 348,
|
| 469 |
+
"[GeH]": 349,
|
| 470 |
+
"[Br+]": 350,
|
| 471 |
+
"[Sr]": 351,
|
| 472 |
+
"[Tl+3]": 352,
|
| 473 |
+
"[Sm+2]": 353,
|
| 474 |
+
"[PH5]": 354,
|
| 475 |
+
"%16": 355,
|
| 476 |
+
"[N@@+]": 356,
|
| 477 |
+
"[Au+3]": 357,
|
| 478 |
+
"[C-4]": 358,
|
| 479 |
+
"[Nd]": 359,
|
| 480 |
+
"[Ti+]": 360,
|
| 481 |
+
"[IH]": 361,
|
| 482 |
+
"[N@+]": 362,
|
| 483 |
+
"[125I]": 363,
|
| 484 |
+
"[Eu]": 364,
|
| 485 |
+
"[Sn+3]": 365,
|
| 486 |
+
"[Nb]": 366,
|
| 487 |
+
"[Er+3]": 367,
|
| 488 |
+
"[123I-]": 368,
|
| 489 |
+
"[14c]": 369,
|
| 490 |
+
"%17": 370,
|
| 491 |
+
"[SnH2]": 371,
|
| 492 |
+
"[YH]": 372,
|
| 493 |
+
"[Sb+5]": 373,
|
| 494 |
+
"[Pr+3]": 374,
|
| 495 |
+
"[Ir+]": 375,
|
| 496 |
+
"[N+3]": 376,
|
| 497 |
+
"[AlH2]": 377,
|
| 498 |
+
"[19F]": 378,
|
| 499 |
+
"%18": 379,
|
| 500 |
+
"[Tb]": 380,
|
| 501 |
+
"[14CH]": 381,
|
| 502 |
+
"[Mo+4]": 382,
|
| 503 |
+
"[Si+]": 383,
|
| 504 |
+
"[BH]": 384,
|
| 505 |
+
"[Be]": 385,
|
| 506 |
+
"[Rb]": 386,
|
| 507 |
+
"[pH]": 387,
|
| 508 |
+
"%19": 388,
|
| 509 |
+
"%20": 389,
|
| 510 |
+
"[Xe]": 390,
|
| 511 |
+
"[Ir-]": 391,
|
| 512 |
+
"[Be+2]": 392,
|
| 513 |
+
"[C+4]": 393,
|
| 514 |
+
"[RuH2]": 394,
|
| 515 |
+
"[15NH]": 395,
|
| 516 |
+
"[U+2]": 396,
|
| 517 |
+
"[Au-]": 397,
|
| 518 |
+
"%21": 398,
|
| 519 |
+
"%22": 399,
|
| 520 |
+
"[Au+]": 400,
|
| 521 |
+
"[15n]": 401,
|
| 522 |
+
"[Al+2]": 402,
|
| 523 |
+
"[Tb+3]": 403,
|
| 524 |
+
"[15N]": 404,
|
| 525 |
+
"[V+3]": 405,
|
| 526 |
+
"[W+6]": 406,
|
| 527 |
+
"[14CH3]": 407,
|
| 528 |
+
"[Cr+4]": 408,
|
| 529 |
+
"[ClH+]": 409,
|
| 530 |
+
"b": 410,
|
| 531 |
+
"[Ti+6]": 411,
|
| 532 |
+
"[Nd+]": 412,
|
| 533 |
+
"[Zr+]": 413,
|
| 534 |
+
"[PH2+]": 414,
|
| 535 |
+
"[Fm]": 415,
|
| 536 |
+
"[N@H+]": 416,
|
| 537 |
+
"[RuH]": 417,
|
| 538 |
+
"[Dy+3]": 418,
|
| 539 |
+
"%23": 419,
|
| 540 |
+
"[Hf+3]": 420,
|
| 541 |
+
"[W+4]": 421,
|
| 542 |
+
"[11C]": 422,
|
| 543 |
+
"[13CH]": 423,
|
| 544 |
+
"[Er]": 424,
|
| 545 |
+
"[124I]": 425,
|
| 546 |
+
"[LaH]": 426,
|
| 547 |
+
"[F]": 427,
|
| 548 |
+
"[siH]": 428,
|
| 549 |
+
"[Ga+]": 429,
|
| 550 |
+
"[Cm]": 430,
|
| 551 |
+
"[GeH3]": 431,
|
| 552 |
+
"[IH-]": 432,
|
| 553 |
+
"[U+6]": 433,
|
| 554 |
+
"[SeH+]": 434,
|
| 555 |
+
"[32P]": 435,
|
| 556 |
+
"[SeH-]": 436,
|
| 557 |
+
"[Pt-]": 437,
|
| 558 |
+
"[Ir+2]": 438,
|
| 559 |
+
"[se+]": 439,
|
| 560 |
+
"[U]": 440,
|
| 561 |
+
"[F+]": 441,
|
| 562 |
+
"[BH2]": 442,
|
| 563 |
+
"[As+]": 443,
|
| 564 |
+
"[Cf]": 444,
|
| 565 |
+
"[ClH2+]": 445,
|
| 566 |
+
"[Ni+]": 446,
|
| 567 |
+
"[TeH3]": 447,
|
| 568 |
+
"[SbH2]": 448,
|
| 569 |
+
"[Ag+3]": 449,
|
| 570 |
+
"%24": 450,
|
| 571 |
+
"[18O]": 451,
|
| 572 |
+
"[PH4]": 452,
|
| 573 |
+
"[Os+2]": 453,
|
| 574 |
+
"[Na-]": 454,
|
| 575 |
+
"[Sb+2]": 455,
|
| 576 |
+
"[V+4]": 456,
|
| 577 |
+
"[Ho+3]": 457,
|
| 578 |
+
"[68Ga]": 458,
|
| 579 |
+
"[PH-]": 459,
|
| 580 |
+
"[Bi+2]": 460,
|
| 581 |
+
"[Ce+2]": 461,
|
| 582 |
+
"[Pd+3]": 462,
|
| 583 |
+
"[99Tc]": 463,
|
| 584 |
+
"[13C@@H]": 464,
|
| 585 |
+
"[Fe+6]": 465,
|
| 586 |
+
"[c]": 466,
|
| 587 |
+
"[GeH2]": 467,
|
| 588 |
+
"[10B]": 468,
|
| 589 |
+
"[Cu+3]": 469,
|
| 590 |
+
"[Mo+2]": 470,
|
| 591 |
+
"[Cr+]": 471,
|
| 592 |
+
"[Pd+4]": 472,
|
| 593 |
+
"[Dy]": 473,
|
| 594 |
+
"[AsH]": 474,
|
| 595 |
+
"[Ba+]": 475,
|
| 596 |
+
"[SeH2]": 476,
|
| 597 |
+
"[In+]": 477,
|
| 598 |
+
"[TeH2]": 478,
|
| 599 |
+
"[BrH+]": 479,
|
| 600 |
+
"[14cH]": 480,
|
| 601 |
+
"[W+]": 481,
|
| 602 |
+
"[13C@H]": 482,
|
| 603 |
+
"[AsH2]": 483,
|
| 604 |
+
"[In+2]": 484,
|
| 605 |
+
"[N+2]": 485,
|
| 606 |
+
"[N@@H+]": 486,
|
| 607 |
+
"[SbH]": 487,
|
| 608 |
+
"[60Co]": 488,
|
| 609 |
+
"[AsH4+]": 489,
|
| 610 |
+
"[AsH3]": 490,
|
| 611 |
+
"[18OH]": 491,
|
| 612 |
+
"[Ru-2]": 492,
|
| 613 |
+
"[Na-2]": 493,
|
| 614 |
+
"[CuH2]": 494,
|
| 615 |
+
"[31P]": 495,
|
| 616 |
+
"[Ti+5]": 496,
|
| 617 |
+
"[35S]": 497,
|
| 618 |
+
"[P@@H]": 498,
|
| 619 |
+
"[ArH]": 499,
|
| 620 |
+
"[Co+]": 500,
|
| 621 |
+
"[Zr-2]": 501,
|
| 622 |
+
"[BH2-]": 502,
|
| 623 |
+
"[131I]": 503,
|
| 624 |
+
"[SH5]": 504,
|
| 625 |
+
"[VH]": 505,
|
| 626 |
+
"[B+2]": 506,
|
| 627 |
+
"[Yb+2]": 507,
|
| 628 |
+
"[14C@H]": 508,
|
| 629 |
+
"[211At]": 509,
|
| 630 |
+
"[NH3+2]": 510,
|
| 631 |
+
"[IrH]": 511,
|
| 632 |
+
"[IrH2]": 512,
|
| 633 |
+
"[Rh-]": 513,
|
| 634 |
+
"[Cr-]": 514,
|
| 635 |
+
"[Sb+]": 515,
|
| 636 |
+
"[Ni+3]": 516,
|
| 637 |
+
"[TaH3]": 517,
|
| 638 |
+
"[Tl+2]": 518,
|
| 639 |
+
"[64Cu]": 519,
|
| 640 |
+
"[Tc]": 520,
|
| 641 |
+
"[Cd+]": 521,
|
| 642 |
+
"[1H]": 522,
|
| 643 |
+
"[15nH]": 523,
|
| 644 |
+
"[AlH2+]": 524,
|
| 645 |
+
"[FH+2]": 525,
|
| 646 |
+
"[BiH3]": 526,
|
| 647 |
+
"[Ru-]": 527,
|
| 648 |
+
"[Mo+6]": 528,
|
| 649 |
+
"[AsH+]": 529,
|
| 650 |
+
"[BaH2]": 530,
|
| 651 |
+
"[BaH]": 531,
|
| 652 |
+
"[Fe+4]": 532,
|
| 653 |
+
"[229Th]": 533,
|
| 654 |
+
"[Th+4]": 534,
|
| 655 |
+
"[As+3]": 535,
|
| 656 |
+
"[NH+3]": 536,
|
| 657 |
+
"[P@H]": 537,
|
| 658 |
+
"[Li-]": 538,
|
| 659 |
+
"[7NaH]": 539,
|
| 660 |
+
"[Bi+]": 540,
|
| 661 |
+
"[PtH+2]": 541,
|
| 662 |
+
"[p-]": 542,
|
| 663 |
+
"[Re+5]": 543,
|
| 664 |
+
"[NiH]": 544,
|
| 665 |
+
"[Ni-]": 545,
|
| 666 |
+
"[Xe+]": 546,
|
| 667 |
+
"[Ca+]": 547,
|
| 668 |
+
"[11c]": 548,
|
| 669 |
+
"[Rh+4]": 549,
|
| 670 |
+
"[AcH]": 550,
|
| 671 |
+
"[HeH]": 551,
|
| 672 |
+
"[Sc+2]": 552,
|
| 673 |
+
"[Mn+]": 553,
|
| 674 |
+
"[UH]": 554,
|
| 675 |
+
"[14CH2]": 555,
|
| 676 |
+
"[SiH4+]": 556,
|
| 677 |
+
"[18OH2]": 557,
|
| 678 |
+
"[Ac-]": 558,
|
| 679 |
+
"[Re+4]": 559,
|
| 680 |
+
"[118Sn]": 560,
|
| 681 |
+
"[153Sm]": 561,
|
| 682 |
+
"[P+2]": 562,
|
| 683 |
+
"[9CH]": 563,
|
| 684 |
+
"[9CH3]": 564,
|
| 685 |
+
"[Y-]": 565,
|
| 686 |
+
"[NiH2]": 566,
|
| 687 |
+
"[Si+2]": 567,
|
| 688 |
+
"[Mn+6]": 568,
|
| 689 |
+
"[ZrH2]": 569,
|
| 690 |
+
"[C-2]": 570,
|
| 691 |
+
"[Bi+5]": 571,
|
| 692 |
+
"[24NaH]": 572,
|
| 693 |
+
"[Fr]": 573,
|
| 694 |
+
"[15CH]": 574,
|
| 695 |
+
"[Se+]": 575,
|
| 696 |
+
"[At]": 576,
|
| 697 |
+
"[P-3]": 577,
|
| 698 |
+
"[124I-]": 578,
|
| 699 |
+
"[CuH2-]": 579,
|
| 700 |
+
"[Nb+4]": 580,
|
| 701 |
+
"[Nb+3]": 581,
|
| 702 |
+
"[MgH]": 582,
|
| 703 |
+
"[Ir+4]": 583,
|
| 704 |
+
"[67Ga+3]": 584,
|
| 705 |
+
"[67Ga]": 585,
|
| 706 |
+
"[13N]": 586,
|
| 707 |
+
"[15OH2]": 587,
|
| 708 |
+
"[2NH]": 588,
|
| 709 |
+
"[Ho]": 589,
|
| 710 |
+
"[Cn]": 590
|
| 711 |
+
},
|
| 712 |
+
"merges": []
|
| 713 |
+
}
|
| 714 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,75 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": false,
|
| 3 |
+
"added_tokens_decoder": {
|
| 4 |
+
"0": {
|
| 5 |
+
"content": "[PAD]",
|
| 6 |
+
"lstrip": false,
|
| 7 |
+
"normalized": true,
|
| 8 |
+
"rstrip": false,
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"special": true
|
| 11 |
+
},
|
| 12 |
+
"11": {
|
| 13 |
+
"content": "[UNK]",
|
| 14 |
+
"lstrip": false,
|
| 15 |
+
"normalized": true,
|
| 16 |
+
"rstrip": false,
|
| 17 |
+
"single_word": false,
|
| 18 |
+
"special": true
|
| 19 |
+
},
|
| 20 |
+
"12": {
|
| 21 |
+
"content": "[CLS]",
|
| 22 |
+
"lstrip": false,
|
| 23 |
+
"normalized": true,
|
| 24 |
+
"rstrip": false,
|
| 25 |
+
"single_word": false,
|
| 26 |
+
"special": true
|
| 27 |
+
},
|
| 28 |
+
"13": {
|
| 29 |
+
"content": "[SEP]",
|
| 30 |
+
"lstrip": false,
|
| 31 |
+
"normalized": true,
|
| 32 |
+
"rstrip": false,
|
| 33 |
+
"single_word": false,
|
| 34 |
+
"special": true
|
| 35 |
+
},
|
| 36 |
+
"14": {
|
| 37 |
+
"content": "[MASK]",
|
| 38 |
+
"lstrip": true,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"rstrip": false,
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"special": true
|
| 43 |
+
},
|
| 44 |
+
"591": {
|
| 45 |
+
"content": "<s>",
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"normalized": true,
|
| 48 |
+
"rstrip": false,
|
| 49 |
+
"single_word": false,
|
| 50 |
+
"special": true
|
| 51 |
+
},
|
| 52 |
+
"592": {
|
| 53 |
+
"content": "</s>",
|
| 54 |
+
"lstrip": false,
|
| 55 |
+
"normalized": true,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"single_word": false,
|
| 58 |
+
"special": true
|
| 59 |
+
}
|
| 60 |
+
},
|
| 61 |
+
"bos_token": "<s>",
|
| 62 |
+
"clean_up_tokenization_spaces": true,
|
| 63 |
+
"cls_token": "[CLS]",
|
| 64 |
+
"eos_token": "</s>",
|
| 65 |
+
"errors": "replace",
|
| 66 |
+
"full_tokenizer_file": null,
|
| 67 |
+
"mask_token": "[MASK]",
|
| 68 |
+
"max_len": 514,
|
| 69 |
+
"model_max_length": 514,
|
| 70 |
+
"pad_token": "[PAD]",
|
| 71 |
+
"sep_token": "[SEP]",
|
| 72 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 73 |
+
"trim_offsets": true,
|
| 74 |
+
"unk_token": "[UNK]"
|
| 75 |
+
}
|
vocab.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"[PAD]":0,"[unused1]":1,"[unused2]":2,"[unused3]":3,"[unused4]":4,"[unused5]":5,"[unused6]":6,"[unused7]":7,"[unused8]":8,"[unused9]":9,"[unused10]":10,"[UNK]":11,"[CLS]":12,"[SEP]":13,"[MASK]":14,"c":15,"C":16,"(":17,")":18,"O":19,"1":20,"2":21,"=":22,"N":23,".":24,"n":25,"3":26,"F":27,"Cl":28,">>":29,"~":30,"-":31,"4":32,"[C@H]":33,"S":34,"[C@@H]":35,"[O-]":36,"Br":37,"#":38,"/":39,"[nH]":40,"[N+]":41,"s":42,"5":43,"o":44,"P":45,"[Na+]":46,"[Si]":47,"I":48,"[Na]":49,"[Pd]":50,"[K+]":51,"[K]":52,"[P]":53,"B":54,"[C@]":55,"[C@@]":56,"[Cl-]":57,"6":58,"[OH-]":59,"\\":60,"[N-]":61,"[Li]":62,"[H]":63,"[2H]":64,"[NH4+]":65,"[c-]":66,"[P-]":67,"[Cs+]":68,"[Li+]":69,"[Cs]":70,"[NaH]":71,"[H-]":72,"[O+]":73,"[BH4-]":74,"[Cu]":75,"7":76,"[Mg]":77,"[Fe+2]":78,"[n+]":79,"[Sn]":80,"[BH-]":81,"[Pd+2]":82,"[CH]":83,"[I-]":84,"[Br-]":85,"[C-]":86,"[Zn]":87,"[B-]":88,"[F-]":89,"[Al]":90,"[P+]":91,"[BH3-]":92,"[Fe]":93,"[C]":94,"[AlH4]":95,"[Ni]":96,"[SiH]":97,"8":98,"[Cu+2]":99,"[Mn]":100,"[AlH]":101,"[nH+]":102,"[AlH4-]":103,"[O-2]":104,"[Cr]":105,"[Mg+2]":106,"[NH3+]":107,"[S@]":108,"[Pt]":109,"[Al+3]":110,"[S@@]":111,"[S-]":112,"[Ti]":113,"[Zn+2]":114,"[PH]":115,"[NH2+]":116,"[Ru]":117,"[Ag+]":118,"[S+]":119,"[I+3]":120,"[NH+]":121,"[Ca+2]":122,"[Ag]":123,"9":124,"[Os]":125,"[Se]":126,"[SiH2]":127,"[Ca]":128,"[Ti+4]":129,"[Ac]":130,"[Cu+]":131,"[S]":132,"[Rh]":133,"[Cl+3]":134,"[cH-]":135,"[Zn+]":136,"[O]":137,"[Cl+]":138,"[SH]":139,"[H+]":140,"[Pd+]":141,"[se]":142,"[PH+]":143,"[I]":144,"[Pt+2]":145,"[C+]":146,"[Mg+]":147,"[Hg]":148,"[W]":149,"[SnH]":150,"[SiH3]":151,"[Fe+3]":152,"[NH]":153,"[Mo]":154,"[CH2+]":155,"%10":156,"[CH2-]":157,"[CH2]":158,"[n-]":159,"[Ce+4]":160,"[NH-]":161,"[Co]":162,"[I+]":163,"[PH2]":164,"[Pt+4]":165,"[Ce]":166,"[B]":167,"[Sn+2]":168,"[Ba+2]":169,"%11":170,"[Fe-3]":171,"[18F]":172,"[SH-]":173,"[Pb+2]":174,"[Os-2]":175,"[Zr+4]":176,"[N]":177,"[Ir]":178,"[Bi]":179,"[Ni+2]":180,"[P@]":181,"[Co+2]":182,"[s+]":183,"[As]":184,"[P+3]":185,"[Hg+2]":186,"[Yb+3]":187,"[CH-]":188,"[Zr+2]":189,"[Mn+2]":190,"[CH+]":191,"[In]":192,"[KH]":193,"[Ce+3]":194,"[Zr]":195,"[AlH2-]":196,"[OH2+]":197,"[Ti+3]":198,"[Rh+2]":199,"[Sb]":200,"[S-2]":201,"%12":202,"[P@@]":203,"[Si@H]":204,"[Mn+4]":205,"p":206,"[Ba]":207,"[NH2-]":208,"[Ge]":209,"[Pb+4]":210,"[Cr+3]":211,"[Au]":212,"[LiH]":213,"[Sc+3]":214,"[o+]":215,"[Rh-3]":216,"%13":217,"[Br]":218,"[Sb-]":219,"[S@+]":220,"[I+2]":221,"[Ar]":222,"[V]":223,"[Cu-]":224,"[Al-]":225,"[Te]":226,"[13c]":227,"[13C]":228,"[Cl]":229,"[PH4+]":230,"[SiH4]":231,"[te]":232,"[CH3-]":233,"[S@@+]":234,"[Rh+3]":235,"[SH+]":236,"[Bi+3]":237,"[Br+2]":238,"[La]":239,"[La+3]":240,"[Pt-2]":241,"[N@@]":242,"[PH3+]":243,"[N@]":244,"[Si+4]":245,"[Sr+2]":246,"[Al+]":247,"[Pb]":248,"[SeH]":249,"[Si-]":250,"[V+5]":251,"[Y+3]":252,"[Re]":253,"[Ru+]":254,"[Sm]":255,"*":256,"[3H]":257,"[NH2]":258,"[Ag-]":259,"[13CH3]":260,"[OH+]":261,"[Ru+3]":262,"[OH]":263,"[Gd+3]":264,"[13CH2]":265,"[In+3]":266,"[Si@@]":267,"[Si@]":268,"[Ti+2]":269,"[Sn+]":270,"[Cl+2]":271,"[AlH-]":272,"[Pd-2]":273,"[SnH3]":274,"[B+3]":275,"[Cu-2]":276,"[Nd+3]":277,"[Pb+3]":278,"[13cH]":279,"[Fe-4]":280,"[Ga]":281,"[Sn+4]":282,"[Hg+]":283,"[11CH3]":284,"[Hf]":285,"[Pr]":286,"[Y]":287,"[S+2]":288,"[Cd]":289,"[Cr+6]":290,"[Zr+3]":291,"[Rh+]":292,"[CH3]":293,"[N-3]":294,"[Hf+2]":295,"[Th]":296,"[Sb+3]":297,"%14":298,"[Cr+2]":299,"[Ru+2]":300,"[Hf+4]":301,"[14C]":302,"[Ta]":303,"[Tl+]":304,"[B+]":305,"[Os+4]":306,"[PdH2]":307,"[Pd-]":308,"[Cd+2]":309,"[Co+3]":310,"[S+4]":311,"[Nb+5]":312,"[123I]":313,"[c+]":314,"[Rb+]":315,"[V+2]":316,"[CH3+]":317,"[Ag+2]":318,"[cH+]":319,"[Mn+3]":320,"[Se-]":321,"[As-]":322,"[Eu+3]":323,"[SH2]":324,"[Sm+3]":325,"[IH+]":326,"%15":327,"[OH3+]":328,"[PH3]":329,"[IH2+]":330,"[SH2+]":331,"[Ir+3]":332,"[AlH3]":333,"[Sc]":334,"[Yb]":335,"[15NH2]":336,"[Lu]":337,"[sH+]":338,"[Gd]":339,"[18F-]":340,"[SH3+]":341,"[SnH4]":342,"[TeH]":343,"[Si@@H]":344,"[Ga+3]":345,"[CaH2]":346,"[Tl]":347,"[Ta+5]":348,"[GeH]":349,"[Br+]":350,"[Sr]":351,"[Tl+3]":352,"[Sm+2]":353,"[PH5]":354,"%16":355,"[N@@+]":356,"[Au+3]":357,"[C-4]":358,"[Nd]":359,"[Ti+]":360,"[IH]":361,"[N@+]":362,"[125I]":363,"[Eu]":364,"[Sn+3]":365,"[Nb]":366,"[Er+3]":367,"[123I-]":368,"[14c]":369,"%17":370,"[SnH2]":371,"[YH]":372,"[Sb+5]":373,"[Pr+3]":374,"[Ir+]":375,"[N+3]":376,"[AlH2]":377,"[19F]":378,"%18":379,"[Tb]":380,"[14CH]":381,"[Mo+4]":382,"[Si+]":383,"[BH]":384,"[Be]":385,"[Rb]":386,"[pH]":387,"%19":388,"%20":389,"[Xe]":390,"[Ir-]":391,"[Be+2]":392,"[C+4]":393,"[RuH2]":394,"[15NH]":395,"[U+2]":396,"[Au-]":397,"%21":398,"%22":399,"[Au+]":400,"[15n]":401,"[Al+2]":402,"[Tb+3]":403,"[15N]":404,"[V+3]":405,"[W+6]":406,"[14CH3]":407,"[Cr+4]":408,"[ClH+]":409,"b":410,"[Ti+6]":411,"[Nd+]":412,"[Zr+]":413,"[PH2+]":414,"[Fm]":415,"[N@H+]":416,"[RuH]":417,"[Dy+3]":418,"%23":419,"[Hf+3]":420,"[W+4]":421,"[11C]":422,"[13CH]":423,"[Er]":424,"[124I]":425,"[LaH]":426,"[F]":427,"[siH]":428,"[Ga+]":429,"[Cm]":430,"[GeH3]":431,"[IH-]":432,"[U+6]":433,"[SeH+]":434,"[32P]":435,"[SeH-]":436,"[Pt-]":437,"[Ir+2]":438,"[se+]":439,"[U]":440,"[F+]":441,"[BH2]":442,"[As+]":443,"[Cf]":444,"[ClH2+]":445,"[Ni+]":446,"[TeH3]":447,"[SbH2]":448,"[Ag+3]":449,"%24":450,"[18O]":451,"[PH4]":452,"[Os+2]":453,"[Na-]":454,"[Sb+2]":455,"[V+4]":456,"[Ho+3]":457,"[68Ga]":458,"[PH-]":459,"[Bi+2]":460,"[Ce+2]":461,"[Pd+3]":462,"[99Tc]":463,"[13C@@H]":464,"[Fe+6]":465,"[c]":466,"[GeH2]":467,"[10B]":468,"[Cu+3]":469,"[Mo+2]":470,"[Cr+]":471,"[Pd+4]":472,"[Dy]":473,"[AsH]":474,"[Ba+]":475,"[SeH2]":476,"[In+]":477,"[TeH2]":478,"[BrH+]":479,"[14cH]":480,"[W+]":481,"[13C@H]":482,"[AsH2]":483,"[In+2]":484,"[N+2]":485,"[N@@H+]":486,"[SbH]":487,"[60Co]":488,"[AsH4+]":489,"[AsH3]":490,"[18OH]":491,"[Ru-2]":492,"[Na-2]":493,"[CuH2]":494,"[31P]":495,"[Ti+5]":496,"[35S]":497,"[P@@H]":498,"[ArH]":499,"[Co+]":500,"[Zr-2]":501,"[BH2-]":502,"[131I]":503,"[SH5]":504,"[VH]":505,"[B+2]":506,"[Yb+2]":507,"[14C@H]":508,"[211At]":509,"[NH3+2]":510,"[IrH]":511,"[IrH2]":512,"[Rh-]":513,"[Cr-]":514,"[Sb+]":515,"[Ni+3]":516,"[TaH3]":517,"[Tl+2]":518,"[64Cu]":519,"[Tc]":520,"[Cd+]":521,"[1H]":522,"[15nH]":523,"[AlH2+]":524,"[FH+2]":525,"[BiH3]":526,"[Ru-]":527,"[Mo+6]":528,"[AsH+]":529,"[BaH2]":530,"[BaH]":531,"[Fe+4]":532,"[229Th]":533,"[Th+4]":534,"[As+3]":535,"[NH+3]":536,"[P@H]":537,"[Li-]":538,"[7NaH]":539,"[Bi+]":540,"[PtH+2]":541,"[p-]":542,"[Re+5]":543,"[NiH]":544,"[Ni-]":545,"[Xe+]":546,"[Ca+]":547,"[11c]":548,"[Rh+4]":549,"[AcH]":550,"[HeH]":551,"[Sc+2]":552,"[Mn+]":553,"[UH]":554,"[14CH2]":555,"[SiH4+]":556,"[18OH2]":557,"[Ac-]":558,"[Re+4]":559,"[118Sn]":560,"[153Sm]":561,"[P+2]":562,"[9CH]":563,"[9CH3]":564,"[Y-]":565,"[NiH2]":566,"[Si+2]":567,"[Mn+6]":568,"[ZrH2]":569,"[C-2]":570,"[Bi+5]":571,"[24NaH]":572,"[Fr]":573,"[15CH]":574,"[Se+]":575,"[At]":576,"[P-3]":577,"[124I-]":578,"[CuH2-]":579,"[Nb+4]":580,"[Nb+3]":581,"[MgH]":582,"[Ir+4]":583,"[67Ga+3]":584,"[67Ga]":585,"[13N]":586,"[15OH2]":587,"[2NH]":588,"[Ho]":589,"[Cn]":590}
|