Commit
•
bb46145
1
Parent(s):
a6fcd92
update
Browse files- special_tokens_map.json +4 -4
- tokenizer.json +9 -5
- tokenizer_config.json +4 -4
special_tokens_map.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<cls>",
|
| 11 |
"lstrip": false,
|
| 12 |
-
"normalized":
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
@@ -23,21 +23,21 @@
|
|
| 23 |
"mask_token": {
|
| 24 |
"content": "<mask>",
|
| 25 |
"lstrip": false,
|
| 26 |
-
"normalized":
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"pad_token": {
|
| 31 |
"content": "<pad>",
|
| 32 |
"lstrip": false,
|
| 33 |
-
"normalized":
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
"content": "<sep>",
|
| 39 |
"lstrip": false,
|
| 40 |
-
"normalized":
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false
|
| 43 |
},
|
|
|
|
| 9 |
"cls_token": {
|
| 10 |
"content": "<cls>",
|
| 11 |
"lstrip": false,
|
| 12 |
+
"normalized": true,
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
|
|
|
| 23 |
"mask_token": {
|
| 24 |
"content": "<mask>",
|
| 25 |
"lstrip": false,
|
| 26 |
+
"normalized": true,
|
| 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 |
},
|
tokenizer.json
CHANGED
|
@@ -36,7 +36,7 @@
|
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
-
"normalized":
|
| 40 |
"special": true
|
| 41 |
},
|
| 42 |
{
|
|
@@ -45,7 +45,7 @@
|
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
-
"normalized":
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
{
|
|
@@ -54,7 +54,7 @@
|
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
-
"normalized":
|
| 58 |
"special": true
|
| 59 |
},
|
| 60 |
{
|
|
@@ -63,7 +63,7 @@
|
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
-
"normalized":
|
| 67 |
"special": true
|
| 68 |
}
|
| 69 |
],
|
|
@@ -32170,7 +32170,11 @@
|
|
| 32170 |
"왕": 31996,
|
| 32171 |
"收": 31997,
|
| 32172 |
"弘": 31998,
|
| 32173 |
-
"给": 31999
|
|
|
|
|
|
|
|
|
|
|
|
|
| 32174 |
},
|
| 32175 |
"merges": [
|
| 32176 |
"▁ t",
|
|
|
|
| 36 |
"single_word": false,
|
| 37 |
"lstrip": false,
|
| 38 |
"rstrip": false,
|
| 39 |
+
"normalized": true,
|
| 40 |
"special": true
|
| 41 |
},
|
| 42 |
{
|
|
|
|
| 45 |
"single_word": false,
|
| 46 |
"lstrip": false,
|
| 47 |
"rstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
"special": true
|
| 50 |
},
|
| 51 |
{
|
|
|
|
| 54 |
"single_word": false,
|
| 55 |
"lstrip": false,
|
| 56 |
"rstrip": false,
|
| 57 |
+
"normalized": true,
|
| 58 |
"special": true
|
| 59 |
},
|
| 60 |
{
|
|
|
|
| 63 |
"single_word": false,
|
| 64 |
"lstrip": false,
|
| 65 |
"rstrip": false,
|
| 66 |
+
"normalized": true,
|
| 67 |
"special": true
|
| 68 |
}
|
| 69 |
],
|
|
|
|
| 32170 |
"왕": 31996,
|
| 32171 |
"收": 31997,
|
| 32172 |
"弘": 31998,
|
| 32173 |
+
"给": 31999,
|
| 32174 |
+
"<pad>": 32000,
|
| 32175 |
+
"<sep>": 32001,
|
| 32176 |
+
"<cls>": 32002,
|
| 32177 |
+
"<mask>": 32003
|
| 32178 |
},
|
| 32179 |
"merges": [
|
| 32180 |
"▁ t",
|
tokenizer_config.json
CHANGED
|
@@ -29,7 +29,7 @@
|
|
| 29 |
"32000": {
|
| 30 |
"content": "<pad>",
|
| 31 |
"lstrip": false,
|
| 32 |
-
"normalized":
|
| 33 |
"rstrip": false,
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"32001": {
|
| 38 |
"content": "<sep>",
|
| 39 |
"lstrip": false,
|
| 40 |
-
"normalized":
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false,
|
| 43 |
"special": true
|
|
@@ -45,7 +45,7 @@
|
|
| 45 |
"32002": {
|
| 46 |
"content": "<cls>",
|
| 47 |
"lstrip": false,
|
| 48 |
-
"normalized":
|
| 49 |
"rstrip": false,
|
| 50 |
"single_word": false,
|
| 51 |
"special": true
|
|
@@ -53,7 +53,7 @@
|
|
| 53 |
"32003": {
|
| 54 |
"content": "<mask>",
|
| 55 |
"lstrip": false,
|
| 56 |
-
"normalized":
|
| 57 |
"rstrip": false,
|
| 58 |
"single_word": false,
|
| 59 |
"special": true
|
|
|
|
| 29 |
"32000": {
|
| 30 |
"content": "<pad>",
|
| 31 |
"lstrip": false,
|
| 32 |
+
"normalized": true,
|
| 33 |
"rstrip": false,
|
| 34 |
"single_word": false,
|
| 35 |
"special": true
|
|
|
|
| 37 |
"32001": {
|
| 38 |
"content": "<sep>",
|
| 39 |
"lstrip": false,
|
| 40 |
+
"normalized": true,
|
| 41 |
"rstrip": false,
|
| 42 |
"single_word": false,
|
| 43 |
"special": true
|
|
|
|
| 45 |
"32002": {
|
| 46 |
"content": "<cls>",
|
| 47 |
"lstrip": false,
|
| 48 |
+
"normalized": true,
|
| 49 |
"rstrip": false,
|
| 50 |
"single_word": false,
|
| 51 |
"special": true
|
|
|
|
| 53 |
"32003": {
|
| 54 |
"content": "<mask>",
|
| 55 |
"lstrip": false,
|
| 56 |
+
"normalized": true,
|
| 57 |
"rstrip": false,
|
| 58 |
"single_word": false,
|
| 59 |
"special": true
|