add tokenizer
Browse files- added_tokens.json +4 -0
- special_tokens_map.json +4 -4
- tokenizer_config.json +4 -4
- vocab.txt +4 -4
added_tokens.json
ADDED
|
@@ -0,0 +1,4 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"</s>": 32001,
|
| 3 |
+
"<s>": 32000
|
| 4 |
+
}
|
special_tokens_map.json
CHANGED
|
@@ -7,7 +7,7 @@
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"cls_token": {
|
| 10 |
-
"content": "
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": true,
|
| 13 |
"rstrip": false,
|
|
@@ -21,21 +21,21 @@
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"mask_token": {
|
| 24 |
-
"content": "
|
| 25 |
"lstrip": true,
|
| 26 |
"normalized": true,
|
| 27 |
"rstrip": false,
|
| 28 |
"single_word": false
|
| 29 |
},
|
| 30 |
"pad_token": {
|
| 31 |
-
"content": "
|
| 32 |
"lstrip": false,
|
| 33 |
"normalized": true,
|
| 34 |
"rstrip": false,
|
| 35 |
"single_word": false
|
| 36 |
},
|
| 37 |
"sep_token": {
|
| 38 |
-
"content": "
|
| 39 |
"lstrip": false,
|
| 40 |
"normalized": true,
|
| 41 |
"rstrip": false,
|
|
|
|
| 7 |
"single_word": false
|
| 8 |
},
|
| 9 |
"cls_token": {
|
| 10 |
+
"content": "[CLS]",
|
| 11 |
"lstrip": false,
|
| 12 |
"normalized": true,
|
| 13 |
"rstrip": false,
|
|
|
|
| 21 |
"single_word": false
|
| 22 |
},
|
| 23 |
"mask_token": {
|
| 24 |
+
"content": "[MASK]",
|
| 25 |
"lstrip": true,
|
| 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,
|
tokenizer_config.json
CHANGED
|
@@ -9,7 +9,7 @@
|
|
| 9 |
},
|
| 10 |
"cls_token": {
|
| 11 |
"__type": "AddedToken",
|
| 12 |
-
"content": "
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": true,
|
| 15 |
"rstrip": false,
|
|
@@ -27,7 +27,7 @@
|
|
| 27 |
},
|
| 28 |
"mask_token": {
|
| 29 |
"__type": "AddedToken",
|
| 30 |
-
"content": "
|
| 31 |
"lstrip": true,
|
| 32 |
"normalized": true,
|
| 33 |
"rstrip": false,
|
|
@@ -37,7 +37,7 @@
|
|
| 37 |
"never_split": null,
|
| 38 |
"pad_token": {
|
| 39 |
"__type": "AddedToken",
|
| 40 |
-
"content": "
|
| 41 |
"lstrip": false,
|
| 42 |
"normalized": true,
|
| 43 |
"rstrip": false,
|
|
@@ -45,7 +45,7 @@
|
|
| 45 |
},
|
| 46 |
"sep_token": {
|
| 47 |
"__type": "AddedToken",
|
| 48 |
-
"content": "
|
| 49 |
"lstrip": false,
|
| 50 |
"normalized": true,
|
| 51 |
"rstrip": false,
|
|
|
|
| 9 |
},
|
| 10 |
"cls_token": {
|
| 11 |
"__type": "AddedToken",
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
"lstrip": false,
|
| 14 |
"normalized": true,
|
| 15 |
"rstrip": false,
|
|
|
|
| 27 |
},
|
| 28 |
"mask_token": {
|
| 29 |
"__type": "AddedToken",
|
| 30 |
+
"content": "[MASK]",
|
| 31 |
"lstrip": true,
|
| 32 |
"normalized": true,
|
| 33 |
"rstrip": false,
|
|
|
|
| 37 |
"never_split": null,
|
| 38 |
"pad_token": {
|
| 39 |
"__type": "AddedToken",
|
| 40 |
+
"content": "[PAD]",
|
| 41 |
"lstrip": false,
|
| 42 |
"normalized": true,
|
| 43 |
"rstrip": false,
|
|
|
|
| 45 |
},
|
| 46 |
"sep_token": {
|
| 47 |
"__type": "AddedToken",
|
| 48 |
+
"content": "[SEP]",
|
| 49 |
"lstrip": false,
|
| 50 |
"normalized": true,
|
| 51 |
"rstrip": false,
|
vocab.txt
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
-
|
| 2 |
[UNK]
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
0
|
| 7 |
1
|
| 8 |
2
|
|
|
|
| 1 |
+
[PAD]
|
| 2 |
[UNK]
|
| 3 |
+
[CLS]
|
| 4 |
+
[SEP]
|
| 5 |
+
[MASK]
|
| 6 |
0
|
| 7 |
1
|
| 8 |
2
|