Commit ·
fc3f7f0
1
Parent(s): 672fbda
Upload tokenizer
Browse files- special_tokens_map.json +0 -6
- tokenizer.json +1 -37
special_tokens_map.json
CHANGED
|
@@ -1,10 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"additional_special_tokens": [
|
| 3 |
-
"<y>",
|
| 4 |
-
"</y>",
|
| 5 |
-
"<t>",
|
| 6 |
-
"</t>"
|
| 7 |
-
],
|
| 8 |
"cls_token": "[CLS]",
|
| 9 |
"mask_token": "[MASK]",
|
| 10 |
"pad_token": "[PAD]",
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"mask_token": "[MASK]",
|
| 4 |
"pad_token": "[PAD]",
|
tokenizer.json
CHANGED
|
@@ -2,7 +2,7 @@
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
-
"max_length":
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
|
@@ -59,42 +59,6 @@
|
|
| 59 |
"rstrip": false,
|
| 60 |
"normalized": false,
|
| 61 |
"special": true
|
| 62 |
-
},
|
| 63 |
-
{
|
| 64 |
-
"id": 30522,
|
| 65 |
-
"content": "<y>",
|
| 66 |
-
"single_word": false,
|
| 67 |
-
"lstrip": false,
|
| 68 |
-
"rstrip": false,
|
| 69 |
-
"normalized": false,
|
| 70 |
-
"special": true
|
| 71 |
-
},
|
| 72 |
-
{
|
| 73 |
-
"id": 30523,
|
| 74 |
-
"content": "</y>",
|
| 75 |
-
"single_word": false,
|
| 76 |
-
"lstrip": false,
|
| 77 |
-
"rstrip": false,
|
| 78 |
-
"normalized": false,
|
| 79 |
-
"special": true
|
| 80 |
-
},
|
| 81 |
-
{
|
| 82 |
-
"id": 30524,
|
| 83 |
-
"content": "<t>",
|
| 84 |
-
"single_word": false,
|
| 85 |
-
"lstrip": false,
|
| 86 |
-
"rstrip": false,
|
| 87 |
-
"normalized": false,
|
| 88 |
-
"special": true
|
| 89 |
-
},
|
| 90 |
-
{
|
| 91 |
-
"id": 30525,
|
| 92 |
-
"content": "</t>",
|
| 93 |
-
"single_word": false,
|
| 94 |
-
"lstrip": false,
|
| 95 |
-
"rstrip": false,
|
| 96 |
-
"normalized": false,
|
| 97 |
-
"special": true
|
| 98 |
}
|
| 99 |
],
|
| 100 |
"normalizer": {
|
|
|
|
| 2 |
"version": "1.0",
|
| 3 |
"truncation": {
|
| 4 |
"direction": "Right",
|
| 5 |
+
"max_length": 128,
|
| 6 |
"strategy": "LongestFirst",
|
| 7 |
"stride": 0
|
| 8 |
},
|
|
|
|
| 59 |
"rstrip": false,
|
| 60 |
"normalized": false,
|
| 61 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 62 |
}
|
| 63 |
],
|
| 64 |
"normalizer": {
|