Update tokenizer.json
Browse files- tokenizer.json +1 -17
tokenizer.json
CHANGED
|
@@ -3,15 +3,6 @@
|
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
| 6 |
-
{
|
| 7 |
-
"id": 1244,
|
| 8 |
-
"content": "[N][C][=N][C][Branch2][Ring1][=C]",
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"lstrip": false,
|
| 11 |
-
"rstrip": false,
|
| 12 |
-
"normalized": true,
|
| 13 |
-
"special": false
|
| 14 |
-
},
|
| 15 |
{
|
| 16 |
"id": 1800,
|
| 17 |
"content": "[START]",
|
|
@@ -86,14 +77,7 @@
|
|
| 86 |
}
|
| 87 |
],
|
| 88 |
"normalizer": null,
|
| 89 |
-
"pre_tokenizer":
|
| 90 |
-
"type": "Split",
|
| 91 |
-
"pattern": {
|
| 92 |
-
"Regex": ".*?]"
|
| 93 |
-
},
|
| 94 |
-
"behavior": "Isolated",
|
| 95 |
-
"invert": false
|
| 96 |
-
},
|
| 97 |
"post_processor": {
|
| 98 |
"type": "TemplateProcessing",
|
| 99 |
"single": [
|
|
|
|
| 3 |
"truncation": null,
|
| 4 |
"padding": null,
|
| 5 |
"added_tokens": [
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 6 |
{
|
| 7 |
"id": 1800,
|
| 8 |
"content": "[START]",
|
|
|
|
| 77 |
}
|
| 78 |
],
|
| 79 |
"normalizer": null,
|
| 80 |
+
"pre_tokenizer":null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 81 |
"post_processor": {
|
| 82 |
"type": "TemplateProcessing",
|
| 83 |
"single": [
|