Upload tokenizer
Browse files- added_tokens.json +1 -0
- tokenizer.json +9 -0
- tokenizer_config.json +8 -0
added_tokens.json
CHANGED
|
@@ -1,3 +1,4 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"<ts>": 32100
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"<0>": 32101,
|
| 3 |
"<ts>": 32100
|
| 4 |
}
|
tokenizer.json
CHANGED
|
@@ -938,6 +938,15 @@
|
|
| 938 |
"rstrip": false,
|
| 939 |
"normalized": true,
|
| 940 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 941 |
}
|
| 942 |
],
|
| 943 |
"normalizer": {
|
|
|
|
| 938 |
"rstrip": false,
|
| 939 |
"normalized": true,
|
| 940 |
"special": false
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"id": 32101,
|
| 944 |
+
"content": "<0>",
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"lstrip": false,
|
| 947 |
+
"rstrip": false,
|
| 948 |
+
"normalized": true,
|
| 949 |
+
"special": false
|
| 950 |
}
|
| 951 |
],
|
| 952 |
"normalizer": {
|
tokenizer_config.json
CHANGED
|
@@ -831,6 +831,14 @@
|
|
| 831 |
"rstrip": false,
|
| 832 |
"single_word": false,
|
| 833 |
"special": false
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 834 |
}
|
| 835 |
},
|
| 836 |
"additional_special_tokens": [
|
|
|
|
| 831 |
"rstrip": false,
|
| 832 |
"single_word": false,
|
| 833 |
"special": false
|
| 834 |
+
},
|
| 835 |
+
"32101": {
|
| 836 |
+
"content": "<0>",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": true,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": false
|
| 842 |
}
|
| 843 |
},
|
| 844 |
"additional_special_tokens": [
|