Upload tokenizer
Browse files- special_tokens_map.json +37 -0
- tokenizer.json +1540 -0
- tokenizer_config.json +854 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,37 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": {
|
| 3 |
+
"content": "[CLS]",
|
| 4 |
+
"lstrip": false,
|
| 5 |
+
"normalized": false,
|
| 6 |
+
"rstrip": false,
|
| 7 |
+
"single_word": false
|
| 8 |
+
},
|
| 9 |
+
"eos_token": {
|
| 10 |
+
"content": "[SEP]",
|
| 11 |
+
"lstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"rstrip": false,
|
| 14 |
+
"single_word": false
|
| 15 |
+
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"lstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
+
"sep_token": {
|
| 24 |
+
"content": "[SEP]",
|
| 25 |
+
"lstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"rstrip": false,
|
| 28 |
+
"single_word": false
|
| 29 |
+
},
|
| 30 |
+
"unk_token": {
|
| 31 |
+
"content": "[UNK]",
|
| 32 |
+
"lstrip": false,
|
| 33 |
+
"normalized": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"single_word": false
|
| 36 |
+
}
|
| 37 |
+
}
|
tokenizer.json
ADDED
|
@@ -0,0 +1,1540 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "[UNK]",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "[PAD]",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "[CLS]",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
},
|
| 33 |
+
{
|
| 34 |
+
"id": 3,
|
| 35 |
+
"content": "[SEP]",
|
| 36 |
+
"single_word": false,
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"rstrip": false,
|
| 39 |
+
"normalized": false,
|
| 40 |
+
"special": true
|
| 41 |
+
},
|
| 42 |
+
{
|
| 43 |
+
"id": 4,
|
| 44 |
+
"content": "[META]",
|
| 45 |
+
"single_word": false,
|
| 46 |
+
"lstrip": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"normalized": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
{
|
| 52 |
+
"id": 412,
|
| 53 |
+
"content": "[SEN_100]",
|
| 54 |
+
"single_word": false,
|
| 55 |
+
"lstrip": false,
|
| 56 |
+
"rstrip": false,
|
| 57 |
+
"normalized": false,
|
| 58 |
+
"special": true
|
| 59 |
+
},
|
| 60 |
+
{
|
| 61 |
+
"id": 413,
|
| 62 |
+
"content": "[SEN_99]",
|
| 63 |
+
"single_word": false,
|
| 64 |
+
"lstrip": false,
|
| 65 |
+
"rstrip": false,
|
| 66 |
+
"normalized": false,
|
| 67 |
+
"special": true
|
| 68 |
+
},
|
| 69 |
+
{
|
| 70 |
+
"id": 414,
|
| 71 |
+
"content": "[SEN_98]",
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"lstrip": false,
|
| 74 |
+
"rstrip": false,
|
| 75 |
+
"normalized": false,
|
| 76 |
+
"special": true
|
| 77 |
+
},
|
| 78 |
+
{
|
| 79 |
+
"id": 415,
|
| 80 |
+
"content": "[SEN_97]",
|
| 81 |
+
"single_word": false,
|
| 82 |
+
"lstrip": false,
|
| 83 |
+
"rstrip": false,
|
| 84 |
+
"normalized": false,
|
| 85 |
+
"special": true
|
| 86 |
+
},
|
| 87 |
+
{
|
| 88 |
+
"id": 416,
|
| 89 |
+
"content": "[SEN_96]",
|
| 90 |
+
"single_word": false,
|
| 91 |
+
"lstrip": false,
|
| 92 |
+
"rstrip": false,
|
| 93 |
+
"normalized": false,
|
| 94 |
+
"special": true
|
| 95 |
+
},
|
| 96 |
+
{
|
| 97 |
+
"id": 417,
|
| 98 |
+
"content": "[SEN_95]",
|
| 99 |
+
"single_word": false,
|
| 100 |
+
"lstrip": false,
|
| 101 |
+
"rstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"special": true
|
| 104 |
+
},
|
| 105 |
+
{
|
| 106 |
+
"id": 418,
|
| 107 |
+
"content": "[SEN_94]",
|
| 108 |
+
"single_word": false,
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"rstrip": false,
|
| 111 |
+
"normalized": false,
|
| 112 |
+
"special": true
|
| 113 |
+
},
|
| 114 |
+
{
|
| 115 |
+
"id": 419,
|
| 116 |
+
"content": "[SEN_93]",
|
| 117 |
+
"single_word": false,
|
| 118 |
+
"lstrip": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"normalized": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
{
|
| 124 |
+
"id": 420,
|
| 125 |
+
"content": "[SEN_92]",
|
| 126 |
+
"single_word": false,
|
| 127 |
+
"lstrip": false,
|
| 128 |
+
"rstrip": false,
|
| 129 |
+
"normalized": false,
|
| 130 |
+
"special": true
|
| 131 |
+
},
|
| 132 |
+
{
|
| 133 |
+
"id": 421,
|
| 134 |
+
"content": "[SEN_91]",
|
| 135 |
+
"single_word": false,
|
| 136 |
+
"lstrip": false,
|
| 137 |
+
"rstrip": false,
|
| 138 |
+
"normalized": false,
|
| 139 |
+
"special": true
|
| 140 |
+
},
|
| 141 |
+
{
|
| 142 |
+
"id": 422,
|
| 143 |
+
"content": "[SEN_90]",
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"lstrip": false,
|
| 146 |
+
"rstrip": false,
|
| 147 |
+
"normalized": false,
|
| 148 |
+
"special": true
|
| 149 |
+
},
|
| 150 |
+
{
|
| 151 |
+
"id": 423,
|
| 152 |
+
"content": "[SEN_89]",
|
| 153 |
+
"single_word": false,
|
| 154 |
+
"lstrip": false,
|
| 155 |
+
"rstrip": false,
|
| 156 |
+
"normalized": false,
|
| 157 |
+
"special": true
|
| 158 |
+
},
|
| 159 |
+
{
|
| 160 |
+
"id": 424,
|
| 161 |
+
"content": "[SEN_88]",
|
| 162 |
+
"single_word": false,
|
| 163 |
+
"lstrip": false,
|
| 164 |
+
"rstrip": false,
|
| 165 |
+
"normalized": false,
|
| 166 |
+
"special": true
|
| 167 |
+
},
|
| 168 |
+
{
|
| 169 |
+
"id": 425,
|
| 170 |
+
"content": "[SEN_87]",
|
| 171 |
+
"single_word": false,
|
| 172 |
+
"lstrip": false,
|
| 173 |
+
"rstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"special": true
|
| 176 |
+
},
|
| 177 |
+
{
|
| 178 |
+
"id": 426,
|
| 179 |
+
"content": "[SEN_86]",
|
| 180 |
+
"single_word": false,
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"rstrip": false,
|
| 183 |
+
"normalized": false,
|
| 184 |
+
"special": true
|
| 185 |
+
},
|
| 186 |
+
{
|
| 187 |
+
"id": 427,
|
| 188 |
+
"content": "[SEN_85]",
|
| 189 |
+
"single_word": false,
|
| 190 |
+
"lstrip": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"normalized": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
{
|
| 196 |
+
"id": 428,
|
| 197 |
+
"content": "[SEN_84]",
|
| 198 |
+
"single_word": false,
|
| 199 |
+
"lstrip": false,
|
| 200 |
+
"rstrip": false,
|
| 201 |
+
"normalized": false,
|
| 202 |
+
"special": true
|
| 203 |
+
},
|
| 204 |
+
{
|
| 205 |
+
"id": 429,
|
| 206 |
+
"content": "[SEN_83]",
|
| 207 |
+
"single_word": false,
|
| 208 |
+
"lstrip": false,
|
| 209 |
+
"rstrip": false,
|
| 210 |
+
"normalized": false,
|
| 211 |
+
"special": true
|
| 212 |
+
},
|
| 213 |
+
{
|
| 214 |
+
"id": 430,
|
| 215 |
+
"content": "[SEN_82]",
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"lstrip": false,
|
| 218 |
+
"rstrip": false,
|
| 219 |
+
"normalized": false,
|
| 220 |
+
"special": true
|
| 221 |
+
},
|
| 222 |
+
{
|
| 223 |
+
"id": 431,
|
| 224 |
+
"content": "[SEN_81]",
|
| 225 |
+
"single_word": false,
|
| 226 |
+
"lstrip": false,
|
| 227 |
+
"rstrip": false,
|
| 228 |
+
"normalized": false,
|
| 229 |
+
"special": true
|
| 230 |
+
},
|
| 231 |
+
{
|
| 232 |
+
"id": 432,
|
| 233 |
+
"content": "[SEN_80]",
|
| 234 |
+
"single_word": false,
|
| 235 |
+
"lstrip": false,
|
| 236 |
+
"rstrip": false,
|
| 237 |
+
"normalized": false,
|
| 238 |
+
"special": true
|
| 239 |
+
},
|
| 240 |
+
{
|
| 241 |
+
"id": 433,
|
| 242 |
+
"content": "[SEN_79]",
|
| 243 |
+
"single_word": false,
|
| 244 |
+
"lstrip": false,
|
| 245 |
+
"rstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"special": true
|
| 248 |
+
},
|
| 249 |
+
{
|
| 250 |
+
"id": 434,
|
| 251 |
+
"content": "[SEN_78]",
|
| 252 |
+
"single_word": false,
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"rstrip": false,
|
| 255 |
+
"normalized": false,
|
| 256 |
+
"special": true
|
| 257 |
+
},
|
| 258 |
+
{
|
| 259 |
+
"id": 435,
|
| 260 |
+
"content": "[SEN_77]",
|
| 261 |
+
"single_word": false,
|
| 262 |
+
"lstrip": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"normalized": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
{
|
| 268 |
+
"id": 436,
|
| 269 |
+
"content": "[SEN_76]",
|
| 270 |
+
"single_word": false,
|
| 271 |
+
"lstrip": false,
|
| 272 |
+
"rstrip": false,
|
| 273 |
+
"normalized": false,
|
| 274 |
+
"special": true
|
| 275 |
+
},
|
| 276 |
+
{
|
| 277 |
+
"id": 437,
|
| 278 |
+
"content": "[SEN_75]",
|
| 279 |
+
"single_word": false,
|
| 280 |
+
"lstrip": false,
|
| 281 |
+
"rstrip": false,
|
| 282 |
+
"normalized": false,
|
| 283 |
+
"special": true
|
| 284 |
+
},
|
| 285 |
+
{
|
| 286 |
+
"id": 438,
|
| 287 |
+
"content": "[SEN_74]",
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"lstrip": false,
|
| 290 |
+
"rstrip": false,
|
| 291 |
+
"normalized": false,
|
| 292 |
+
"special": true
|
| 293 |
+
},
|
| 294 |
+
{
|
| 295 |
+
"id": 439,
|
| 296 |
+
"content": "[SEN_73]",
|
| 297 |
+
"single_word": false,
|
| 298 |
+
"lstrip": false,
|
| 299 |
+
"rstrip": false,
|
| 300 |
+
"normalized": false,
|
| 301 |
+
"special": true
|
| 302 |
+
},
|
| 303 |
+
{
|
| 304 |
+
"id": 440,
|
| 305 |
+
"content": "[SEN_72]",
|
| 306 |
+
"single_word": false,
|
| 307 |
+
"lstrip": false,
|
| 308 |
+
"rstrip": false,
|
| 309 |
+
"normalized": false,
|
| 310 |
+
"special": true
|
| 311 |
+
},
|
| 312 |
+
{
|
| 313 |
+
"id": 441,
|
| 314 |
+
"content": "[SEN_71]",
|
| 315 |
+
"single_word": false,
|
| 316 |
+
"lstrip": false,
|
| 317 |
+
"rstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"special": true
|
| 320 |
+
},
|
| 321 |
+
{
|
| 322 |
+
"id": 442,
|
| 323 |
+
"content": "[SEN_70]",
|
| 324 |
+
"single_word": false,
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"rstrip": false,
|
| 327 |
+
"normalized": false,
|
| 328 |
+
"special": true
|
| 329 |
+
},
|
| 330 |
+
{
|
| 331 |
+
"id": 443,
|
| 332 |
+
"content": "[SEN_69]",
|
| 333 |
+
"single_word": false,
|
| 334 |
+
"lstrip": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"normalized": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
{
|
| 340 |
+
"id": 444,
|
| 341 |
+
"content": "[SEN_68]",
|
| 342 |
+
"single_word": false,
|
| 343 |
+
"lstrip": false,
|
| 344 |
+
"rstrip": false,
|
| 345 |
+
"normalized": false,
|
| 346 |
+
"special": true
|
| 347 |
+
},
|
| 348 |
+
{
|
| 349 |
+
"id": 445,
|
| 350 |
+
"content": "[SEN_67]",
|
| 351 |
+
"single_word": false,
|
| 352 |
+
"lstrip": false,
|
| 353 |
+
"rstrip": false,
|
| 354 |
+
"normalized": false,
|
| 355 |
+
"special": true
|
| 356 |
+
},
|
| 357 |
+
{
|
| 358 |
+
"id": 446,
|
| 359 |
+
"content": "[SEN_66]",
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"lstrip": false,
|
| 362 |
+
"rstrip": false,
|
| 363 |
+
"normalized": false,
|
| 364 |
+
"special": true
|
| 365 |
+
},
|
| 366 |
+
{
|
| 367 |
+
"id": 447,
|
| 368 |
+
"content": "[SEN_65]",
|
| 369 |
+
"single_word": false,
|
| 370 |
+
"lstrip": false,
|
| 371 |
+
"rstrip": false,
|
| 372 |
+
"normalized": false,
|
| 373 |
+
"special": true
|
| 374 |
+
},
|
| 375 |
+
{
|
| 376 |
+
"id": 448,
|
| 377 |
+
"content": "[SEN_64]",
|
| 378 |
+
"single_word": false,
|
| 379 |
+
"lstrip": false,
|
| 380 |
+
"rstrip": false,
|
| 381 |
+
"normalized": false,
|
| 382 |
+
"special": true
|
| 383 |
+
},
|
| 384 |
+
{
|
| 385 |
+
"id": 449,
|
| 386 |
+
"content": "[SEN_63]",
|
| 387 |
+
"single_word": false,
|
| 388 |
+
"lstrip": false,
|
| 389 |
+
"rstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"special": true
|
| 392 |
+
},
|
| 393 |
+
{
|
| 394 |
+
"id": 450,
|
| 395 |
+
"content": "[SEN_62]",
|
| 396 |
+
"single_word": false,
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"rstrip": false,
|
| 399 |
+
"normalized": false,
|
| 400 |
+
"special": true
|
| 401 |
+
},
|
| 402 |
+
{
|
| 403 |
+
"id": 451,
|
| 404 |
+
"content": "[SEN_61]",
|
| 405 |
+
"single_word": false,
|
| 406 |
+
"lstrip": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"normalized": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
{
|
| 412 |
+
"id": 452,
|
| 413 |
+
"content": "[SEN_60]",
|
| 414 |
+
"single_word": false,
|
| 415 |
+
"lstrip": false,
|
| 416 |
+
"rstrip": false,
|
| 417 |
+
"normalized": false,
|
| 418 |
+
"special": true
|
| 419 |
+
},
|
| 420 |
+
{
|
| 421 |
+
"id": 453,
|
| 422 |
+
"content": "[SEN_59]",
|
| 423 |
+
"single_word": false,
|
| 424 |
+
"lstrip": false,
|
| 425 |
+
"rstrip": false,
|
| 426 |
+
"normalized": false,
|
| 427 |
+
"special": true
|
| 428 |
+
},
|
| 429 |
+
{
|
| 430 |
+
"id": 454,
|
| 431 |
+
"content": "[SEN_58]",
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"lstrip": false,
|
| 434 |
+
"rstrip": false,
|
| 435 |
+
"normalized": false,
|
| 436 |
+
"special": true
|
| 437 |
+
},
|
| 438 |
+
{
|
| 439 |
+
"id": 455,
|
| 440 |
+
"content": "[SEN_57]",
|
| 441 |
+
"single_word": false,
|
| 442 |
+
"lstrip": false,
|
| 443 |
+
"rstrip": false,
|
| 444 |
+
"normalized": false,
|
| 445 |
+
"special": true
|
| 446 |
+
},
|
| 447 |
+
{
|
| 448 |
+
"id": 456,
|
| 449 |
+
"content": "[SEN_56]",
|
| 450 |
+
"single_word": false,
|
| 451 |
+
"lstrip": false,
|
| 452 |
+
"rstrip": false,
|
| 453 |
+
"normalized": false,
|
| 454 |
+
"special": true
|
| 455 |
+
},
|
| 456 |
+
{
|
| 457 |
+
"id": 457,
|
| 458 |
+
"content": "[SEN_55]",
|
| 459 |
+
"single_word": false,
|
| 460 |
+
"lstrip": false,
|
| 461 |
+
"rstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"special": true
|
| 464 |
+
},
|
| 465 |
+
{
|
| 466 |
+
"id": 458,
|
| 467 |
+
"content": "[SEN_54]",
|
| 468 |
+
"single_word": false,
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"rstrip": false,
|
| 471 |
+
"normalized": false,
|
| 472 |
+
"special": true
|
| 473 |
+
},
|
| 474 |
+
{
|
| 475 |
+
"id": 459,
|
| 476 |
+
"content": "[SEN_53]",
|
| 477 |
+
"single_word": false,
|
| 478 |
+
"lstrip": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"normalized": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
{
|
| 484 |
+
"id": 460,
|
| 485 |
+
"content": "[SEN_52]",
|
| 486 |
+
"single_word": false,
|
| 487 |
+
"lstrip": false,
|
| 488 |
+
"rstrip": false,
|
| 489 |
+
"normalized": false,
|
| 490 |
+
"special": true
|
| 491 |
+
},
|
| 492 |
+
{
|
| 493 |
+
"id": 461,
|
| 494 |
+
"content": "[SEN_51]",
|
| 495 |
+
"single_word": false,
|
| 496 |
+
"lstrip": false,
|
| 497 |
+
"rstrip": false,
|
| 498 |
+
"normalized": false,
|
| 499 |
+
"special": true
|
| 500 |
+
},
|
| 501 |
+
{
|
| 502 |
+
"id": 462,
|
| 503 |
+
"content": "[SEN_50]",
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"lstrip": false,
|
| 506 |
+
"rstrip": false,
|
| 507 |
+
"normalized": false,
|
| 508 |
+
"special": true
|
| 509 |
+
},
|
| 510 |
+
{
|
| 511 |
+
"id": 463,
|
| 512 |
+
"content": "[SEN_49]",
|
| 513 |
+
"single_word": false,
|
| 514 |
+
"lstrip": false,
|
| 515 |
+
"rstrip": false,
|
| 516 |
+
"normalized": false,
|
| 517 |
+
"special": true
|
| 518 |
+
},
|
| 519 |
+
{
|
| 520 |
+
"id": 464,
|
| 521 |
+
"content": "[SEN_48]",
|
| 522 |
+
"single_word": false,
|
| 523 |
+
"lstrip": false,
|
| 524 |
+
"rstrip": false,
|
| 525 |
+
"normalized": false,
|
| 526 |
+
"special": true
|
| 527 |
+
},
|
| 528 |
+
{
|
| 529 |
+
"id": 465,
|
| 530 |
+
"content": "[SEN_47]",
|
| 531 |
+
"single_word": false,
|
| 532 |
+
"lstrip": false,
|
| 533 |
+
"rstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"special": true
|
| 536 |
+
},
|
| 537 |
+
{
|
| 538 |
+
"id": 466,
|
| 539 |
+
"content": "[SEN_46]",
|
| 540 |
+
"single_word": false,
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"rstrip": false,
|
| 543 |
+
"normalized": false,
|
| 544 |
+
"special": true
|
| 545 |
+
},
|
| 546 |
+
{
|
| 547 |
+
"id": 467,
|
| 548 |
+
"content": "[SEN_45]",
|
| 549 |
+
"single_word": false,
|
| 550 |
+
"lstrip": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"normalized": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
{
|
| 556 |
+
"id": 468,
|
| 557 |
+
"content": "[SEN_44]",
|
| 558 |
+
"single_word": false,
|
| 559 |
+
"lstrip": false,
|
| 560 |
+
"rstrip": false,
|
| 561 |
+
"normalized": false,
|
| 562 |
+
"special": true
|
| 563 |
+
},
|
| 564 |
+
{
|
| 565 |
+
"id": 469,
|
| 566 |
+
"content": "[SEN_43]",
|
| 567 |
+
"single_word": false,
|
| 568 |
+
"lstrip": false,
|
| 569 |
+
"rstrip": false,
|
| 570 |
+
"normalized": false,
|
| 571 |
+
"special": true
|
| 572 |
+
},
|
| 573 |
+
{
|
| 574 |
+
"id": 470,
|
| 575 |
+
"content": "[SEN_42]",
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"lstrip": false,
|
| 578 |
+
"rstrip": false,
|
| 579 |
+
"normalized": false,
|
| 580 |
+
"special": true
|
| 581 |
+
},
|
| 582 |
+
{
|
| 583 |
+
"id": 471,
|
| 584 |
+
"content": "[SEN_41]",
|
| 585 |
+
"single_word": false,
|
| 586 |
+
"lstrip": false,
|
| 587 |
+
"rstrip": false,
|
| 588 |
+
"normalized": false,
|
| 589 |
+
"special": true
|
| 590 |
+
},
|
| 591 |
+
{
|
| 592 |
+
"id": 472,
|
| 593 |
+
"content": "[SEN_40]",
|
| 594 |
+
"single_word": false,
|
| 595 |
+
"lstrip": false,
|
| 596 |
+
"rstrip": false,
|
| 597 |
+
"normalized": false,
|
| 598 |
+
"special": true
|
| 599 |
+
},
|
| 600 |
+
{
|
| 601 |
+
"id": 473,
|
| 602 |
+
"content": "[SEN_39]",
|
| 603 |
+
"single_word": false,
|
| 604 |
+
"lstrip": false,
|
| 605 |
+
"rstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"special": true
|
| 608 |
+
},
|
| 609 |
+
{
|
| 610 |
+
"id": 474,
|
| 611 |
+
"content": "[SEN_38]",
|
| 612 |
+
"single_word": false,
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"rstrip": false,
|
| 615 |
+
"normalized": false,
|
| 616 |
+
"special": true
|
| 617 |
+
},
|
| 618 |
+
{
|
| 619 |
+
"id": 475,
|
| 620 |
+
"content": "[SEN_37]",
|
| 621 |
+
"single_word": false,
|
| 622 |
+
"lstrip": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"normalized": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
{
|
| 628 |
+
"id": 476,
|
| 629 |
+
"content": "[SEN_36]",
|
| 630 |
+
"single_word": false,
|
| 631 |
+
"lstrip": false,
|
| 632 |
+
"rstrip": false,
|
| 633 |
+
"normalized": false,
|
| 634 |
+
"special": true
|
| 635 |
+
},
|
| 636 |
+
{
|
| 637 |
+
"id": 477,
|
| 638 |
+
"content": "[SEN_35]",
|
| 639 |
+
"single_word": false,
|
| 640 |
+
"lstrip": false,
|
| 641 |
+
"rstrip": false,
|
| 642 |
+
"normalized": false,
|
| 643 |
+
"special": true
|
| 644 |
+
},
|
| 645 |
+
{
|
| 646 |
+
"id": 478,
|
| 647 |
+
"content": "[SEN_34]",
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"lstrip": false,
|
| 650 |
+
"rstrip": false,
|
| 651 |
+
"normalized": false,
|
| 652 |
+
"special": true
|
| 653 |
+
},
|
| 654 |
+
{
|
| 655 |
+
"id": 479,
|
| 656 |
+
"content": "[SEN_33]",
|
| 657 |
+
"single_word": false,
|
| 658 |
+
"lstrip": false,
|
| 659 |
+
"rstrip": false,
|
| 660 |
+
"normalized": false,
|
| 661 |
+
"special": true
|
| 662 |
+
},
|
| 663 |
+
{
|
| 664 |
+
"id": 480,
|
| 665 |
+
"content": "[SEN_32]",
|
| 666 |
+
"single_word": false,
|
| 667 |
+
"lstrip": false,
|
| 668 |
+
"rstrip": false,
|
| 669 |
+
"normalized": false,
|
| 670 |
+
"special": true
|
| 671 |
+
},
|
| 672 |
+
{
|
| 673 |
+
"id": 481,
|
| 674 |
+
"content": "[SEN_31]",
|
| 675 |
+
"single_word": false,
|
| 676 |
+
"lstrip": false,
|
| 677 |
+
"rstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"special": true
|
| 680 |
+
},
|
| 681 |
+
{
|
| 682 |
+
"id": 482,
|
| 683 |
+
"content": "[SEN_30]",
|
| 684 |
+
"single_word": false,
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"rstrip": false,
|
| 687 |
+
"normalized": false,
|
| 688 |
+
"special": true
|
| 689 |
+
},
|
| 690 |
+
{
|
| 691 |
+
"id": 483,
|
| 692 |
+
"content": "[SEN_29]",
|
| 693 |
+
"single_word": false,
|
| 694 |
+
"lstrip": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"normalized": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
{
|
| 700 |
+
"id": 484,
|
| 701 |
+
"content": "[SEN_28]",
|
| 702 |
+
"single_word": false,
|
| 703 |
+
"lstrip": false,
|
| 704 |
+
"rstrip": false,
|
| 705 |
+
"normalized": false,
|
| 706 |
+
"special": true
|
| 707 |
+
},
|
| 708 |
+
{
|
| 709 |
+
"id": 485,
|
| 710 |
+
"content": "[SEN_27]",
|
| 711 |
+
"single_word": false,
|
| 712 |
+
"lstrip": false,
|
| 713 |
+
"rstrip": false,
|
| 714 |
+
"normalized": false,
|
| 715 |
+
"special": true
|
| 716 |
+
},
|
| 717 |
+
{
|
| 718 |
+
"id": 486,
|
| 719 |
+
"content": "[SEN_26]",
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"lstrip": false,
|
| 722 |
+
"rstrip": false,
|
| 723 |
+
"normalized": false,
|
| 724 |
+
"special": true
|
| 725 |
+
},
|
| 726 |
+
{
|
| 727 |
+
"id": 487,
|
| 728 |
+
"content": "[SEN_25]",
|
| 729 |
+
"single_word": false,
|
| 730 |
+
"lstrip": false,
|
| 731 |
+
"rstrip": false,
|
| 732 |
+
"normalized": false,
|
| 733 |
+
"special": true
|
| 734 |
+
},
|
| 735 |
+
{
|
| 736 |
+
"id": 488,
|
| 737 |
+
"content": "[SEN_24]",
|
| 738 |
+
"single_word": false,
|
| 739 |
+
"lstrip": false,
|
| 740 |
+
"rstrip": false,
|
| 741 |
+
"normalized": false,
|
| 742 |
+
"special": true
|
| 743 |
+
},
|
| 744 |
+
{
|
| 745 |
+
"id": 489,
|
| 746 |
+
"content": "[SEN_23]",
|
| 747 |
+
"single_word": false,
|
| 748 |
+
"lstrip": false,
|
| 749 |
+
"rstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"special": true
|
| 752 |
+
},
|
| 753 |
+
{
|
| 754 |
+
"id": 490,
|
| 755 |
+
"content": "[SEN_22]",
|
| 756 |
+
"single_word": false,
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"rstrip": false,
|
| 759 |
+
"normalized": false,
|
| 760 |
+
"special": true
|
| 761 |
+
},
|
| 762 |
+
{
|
| 763 |
+
"id": 491,
|
| 764 |
+
"content": "[SEN_21]",
|
| 765 |
+
"single_word": false,
|
| 766 |
+
"lstrip": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"normalized": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
{
|
| 772 |
+
"id": 492,
|
| 773 |
+
"content": "[SEN_20]",
|
| 774 |
+
"single_word": false,
|
| 775 |
+
"lstrip": false,
|
| 776 |
+
"rstrip": false,
|
| 777 |
+
"normalized": false,
|
| 778 |
+
"special": true
|
| 779 |
+
},
|
| 780 |
+
{
|
| 781 |
+
"id": 493,
|
| 782 |
+
"content": "[SEN_19]",
|
| 783 |
+
"single_word": false,
|
| 784 |
+
"lstrip": false,
|
| 785 |
+
"rstrip": false,
|
| 786 |
+
"normalized": false,
|
| 787 |
+
"special": true
|
| 788 |
+
},
|
| 789 |
+
{
|
| 790 |
+
"id": 494,
|
| 791 |
+
"content": "[SEN_18]",
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"lstrip": false,
|
| 794 |
+
"rstrip": false,
|
| 795 |
+
"normalized": false,
|
| 796 |
+
"special": true
|
| 797 |
+
},
|
| 798 |
+
{
|
| 799 |
+
"id": 495,
|
| 800 |
+
"content": "[SEN_17]",
|
| 801 |
+
"single_word": false,
|
| 802 |
+
"lstrip": false,
|
| 803 |
+
"rstrip": false,
|
| 804 |
+
"normalized": false,
|
| 805 |
+
"special": true
|
| 806 |
+
},
|
| 807 |
+
{
|
| 808 |
+
"id": 496,
|
| 809 |
+
"content": "[SEN_16]",
|
| 810 |
+
"single_word": false,
|
| 811 |
+
"lstrip": false,
|
| 812 |
+
"rstrip": false,
|
| 813 |
+
"normalized": false,
|
| 814 |
+
"special": true
|
| 815 |
+
},
|
| 816 |
+
{
|
| 817 |
+
"id": 497,
|
| 818 |
+
"content": "[SEN_15]",
|
| 819 |
+
"single_word": false,
|
| 820 |
+
"lstrip": false,
|
| 821 |
+
"rstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"special": true
|
| 824 |
+
},
|
| 825 |
+
{
|
| 826 |
+
"id": 498,
|
| 827 |
+
"content": "[SEN_14]",
|
| 828 |
+
"single_word": false,
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"rstrip": false,
|
| 831 |
+
"normalized": false,
|
| 832 |
+
"special": true
|
| 833 |
+
},
|
| 834 |
+
{
|
| 835 |
+
"id": 499,
|
| 836 |
+
"content": "[SEN_13]",
|
| 837 |
+
"single_word": false,
|
| 838 |
+
"lstrip": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"normalized": false,
|
| 841 |
+
"special": true
|
| 842 |
+
},
|
| 843 |
+
{
|
| 844 |
+
"id": 500,
|
| 845 |
+
"content": "[SEN_12]",
|
| 846 |
+
"single_word": false,
|
| 847 |
+
"lstrip": false,
|
| 848 |
+
"rstrip": false,
|
| 849 |
+
"normalized": false,
|
| 850 |
+
"special": true
|
| 851 |
+
},
|
| 852 |
+
{
|
| 853 |
+
"id": 501,
|
| 854 |
+
"content": "[SEN_11]",
|
| 855 |
+
"single_word": false,
|
| 856 |
+
"lstrip": false,
|
| 857 |
+
"rstrip": false,
|
| 858 |
+
"normalized": false,
|
| 859 |
+
"special": true
|
| 860 |
+
},
|
| 861 |
+
{
|
| 862 |
+
"id": 502,
|
| 863 |
+
"content": "[SEN_10]",
|
| 864 |
+
"single_word": false,
|
| 865 |
+
"lstrip": false,
|
| 866 |
+
"rstrip": false,
|
| 867 |
+
"normalized": false,
|
| 868 |
+
"special": true
|
| 869 |
+
},
|
| 870 |
+
{
|
| 871 |
+
"id": 503,
|
| 872 |
+
"content": "[SEN_9]",
|
| 873 |
+
"single_word": false,
|
| 874 |
+
"lstrip": false,
|
| 875 |
+
"rstrip": false,
|
| 876 |
+
"normalized": false,
|
| 877 |
+
"special": true
|
| 878 |
+
},
|
| 879 |
+
{
|
| 880 |
+
"id": 504,
|
| 881 |
+
"content": "[SEN_8]",
|
| 882 |
+
"single_word": false,
|
| 883 |
+
"lstrip": false,
|
| 884 |
+
"rstrip": false,
|
| 885 |
+
"normalized": false,
|
| 886 |
+
"special": true
|
| 887 |
+
},
|
| 888 |
+
{
|
| 889 |
+
"id": 505,
|
| 890 |
+
"content": "[SEN_7]",
|
| 891 |
+
"single_word": false,
|
| 892 |
+
"lstrip": false,
|
| 893 |
+
"rstrip": false,
|
| 894 |
+
"normalized": false,
|
| 895 |
+
"special": true
|
| 896 |
+
},
|
| 897 |
+
{
|
| 898 |
+
"id": 506,
|
| 899 |
+
"content": "[SEN_6]",
|
| 900 |
+
"single_word": false,
|
| 901 |
+
"lstrip": false,
|
| 902 |
+
"rstrip": false,
|
| 903 |
+
"normalized": false,
|
| 904 |
+
"special": true
|
| 905 |
+
},
|
| 906 |
+
{
|
| 907 |
+
"id": 507,
|
| 908 |
+
"content": "[SEN_5]",
|
| 909 |
+
"single_word": false,
|
| 910 |
+
"lstrip": false,
|
| 911 |
+
"rstrip": false,
|
| 912 |
+
"normalized": false,
|
| 913 |
+
"special": true
|
| 914 |
+
},
|
| 915 |
+
{
|
| 916 |
+
"id": 508,
|
| 917 |
+
"content": "[SEN_4]",
|
| 918 |
+
"single_word": false,
|
| 919 |
+
"lstrip": false,
|
| 920 |
+
"rstrip": false,
|
| 921 |
+
"normalized": false,
|
| 922 |
+
"special": true
|
| 923 |
+
},
|
| 924 |
+
{
|
| 925 |
+
"id": 509,
|
| 926 |
+
"content": "[SEN_3]",
|
| 927 |
+
"single_word": false,
|
| 928 |
+
"lstrip": false,
|
| 929 |
+
"rstrip": false,
|
| 930 |
+
"normalized": false,
|
| 931 |
+
"special": true
|
| 932 |
+
},
|
| 933 |
+
{
|
| 934 |
+
"id": 510,
|
| 935 |
+
"content": "[SEN_2]",
|
| 936 |
+
"single_word": false,
|
| 937 |
+
"lstrip": false,
|
| 938 |
+
"rstrip": false,
|
| 939 |
+
"normalized": false,
|
| 940 |
+
"special": true
|
| 941 |
+
},
|
| 942 |
+
{
|
| 943 |
+
"id": 511,
|
| 944 |
+
"content": "[SEN_1]",
|
| 945 |
+
"single_word": false,
|
| 946 |
+
"lstrip": false,
|
| 947 |
+
"rstrip": false,
|
| 948 |
+
"normalized": false,
|
| 949 |
+
"special": true
|
| 950 |
+
}
|
| 951 |
+
],
|
| 952 |
+
"normalizer": null,
|
| 953 |
+
"pre_tokenizer": {
|
| 954 |
+
"type": "Split",
|
| 955 |
+
"pattern": {
|
| 956 |
+
"String": ""
|
| 957 |
+
},
|
| 958 |
+
"behavior": "Isolated",
|
| 959 |
+
"invert": false
|
| 960 |
+
},
|
| 961 |
+
"post_processor": {
|
| 962 |
+
"type": "TemplateProcessing",
|
| 963 |
+
"single": [
|
| 964 |
+
{
|
| 965 |
+
"Sequence": {
|
| 966 |
+
"id": "A",
|
| 967 |
+
"type_id": 0
|
| 968 |
+
}
|
| 969 |
+
},
|
| 970 |
+
{
|
| 971 |
+
"SpecialToken": {
|
| 972 |
+
"id": "[SEP]",
|
| 973 |
+
"type_id": 0
|
| 974 |
+
}
|
| 975 |
+
}
|
| 976 |
+
],
|
| 977 |
+
"pair": [
|
| 978 |
+
{
|
| 979 |
+
"Sequence": {
|
| 980 |
+
"id": "A",
|
| 981 |
+
"type_id": 0
|
| 982 |
+
}
|
| 983 |
+
},
|
| 984 |
+
{
|
| 985 |
+
"SpecialToken": {
|
| 986 |
+
"id": "[SEP]",
|
| 987 |
+
"type_id": 0
|
| 988 |
+
}
|
| 989 |
+
},
|
| 990 |
+
{
|
| 991 |
+
"Sequence": {
|
| 992 |
+
"id": "B",
|
| 993 |
+
"type_id": 1
|
| 994 |
+
}
|
| 995 |
+
},
|
| 996 |
+
{
|
| 997 |
+
"SpecialToken": {
|
| 998 |
+
"id": "[SEP]",
|
| 999 |
+
"type_id": 1
|
| 1000 |
+
}
|
| 1001 |
+
}
|
| 1002 |
+
],
|
| 1003 |
+
"special_tokens": {
|
| 1004 |
+
"[SEP]": {
|
| 1005 |
+
"id": "[SEP]",
|
| 1006 |
+
"ids": [
|
| 1007 |
+
3
|
| 1008 |
+
],
|
| 1009 |
+
"tokens": [
|
| 1010 |
+
"[SEP]"
|
| 1011 |
+
]
|
| 1012 |
+
}
|
| 1013 |
+
}
|
| 1014 |
+
},
|
| 1015 |
+
"decoder": {
|
| 1016 |
+
"type": "WordPiece",
|
| 1017 |
+
"prefix": "",
|
| 1018 |
+
"cleanup": true
|
| 1019 |
+
},
|
| 1020 |
+
"model": {
|
| 1021 |
+
"type": "WordPiece",
|
| 1022 |
+
"unk_token": "[UNK]",
|
| 1023 |
+
"continuing_subword_prefix": "",
|
| 1024 |
+
"max_input_chars_per_word": 999999999,
|
| 1025 |
+
"vocab": {
|
| 1026 |
+
"[UNK]": 0,
|
| 1027 |
+
"[PAD]": 1,
|
| 1028 |
+
"[CLS]": 2,
|
| 1029 |
+
"[SEP]": 3,
|
| 1030 |
+
"[META]": 4,
|
| 1031 |
+
" ": 5,
|
| 1032 |
+
"а": 6,
|
| 1033 |
+
"и": 7,
|
| 1034 |
+
"е": 8,
|
| 1035 |
+
"о": 9,
|
| 1036 |
+
"т": 10,
|
| 1037 |
+
"н": 11,
|
| 1038 |
+
"р": 12,
|
| 1039 |
+
"с": 13,
|
| 1040 |
+
"в": 14,
|
| 1041 |
+
"л": 15,
|
| 1042 |
+
"д": 16,
|
| 1043 |
+
"к": 17,
|
| 1044 |
+
"п": 18,
|
| 1045 |
+
"м": 19,
|
| 1046 |
+
"з": 20,
|
| 1047 |
+
"я": 21,
|
| 1048 |
+
"ъ": 22,
|
| 1049 |
+
",": 23,
|
| 1050 |
+
"б": 24,
|
| 1051 |
+
".": 25,
|
| 1052 |
+
"г": 26,
|
| 1053 |
+
"у": 27,
|
| 1054 |
+
"ч": 28,
|
| 1055 |
+
"ж": 29,
|
| 1056 |
+
"ц": 30,
|
| 1057 |
+
"\n": 31,
|
| 1058 |
+
"щ": 32,
|
| 1059 |
+
"й": 33,
|
| 1060 |
+
"х": 34,
|
| 1061 |
+
"ш": 35,
|
| 1062 |
+
"0": 36,
|
| 1063 |
+
"-": 37,
|
| 1064 |
+
"1": 38,
|
| 1065 |
+
"ф": 39,
|
| 1066 |
+
"\"": 40,
|
| 1067 |
+
"2": 41,
|
| 1068 |
+
"С": 42,
|
| 1069 |
+
"П": 43,
|
| 1070 |
+
"e": 44,
|
| 1071 |
+
"Н": 45,
|
| 1072 |
+
"В": 46,
|
| 1073 |
+
"Т": 47,
|
| 1074 |
+
"a": 48,
|
| 1075 |
+
"А": 49,
|
| 1076 |
+
"К": 50,
|
| 1077 |
+
"o": 51,
|
| 1078 |
+
":": 52,
|
| 1079 |
+
"i": 53,
|
| 1080 |
+
"И": 54,
|
| 1081 |
+
"Б": 55,
|
| 1082 |
+
"Д": 56,
|
| 1083 |
+
"О": 57,
|
| 1084 |
+
"t": 58,
|
| 1085 |
+
"М": 59,
|
| 1086 |
+
"n": 60,
|
| 1087 |
+
"r": 61,
|
| 1088 |
+
"Р": 62,
|
| 1089 |
+
"3": 63,
|
| 1090 |
+
"ю": 64,
|
| 1091 |
+
"5": 65,
|
| 1092 |
+
"Е": 66,
|
| 1093 |
+
"s": 67,
|
| 1094 |
+
"4": 68,
|
| 1095 |
+
"l": 69,
|
| 1096 |
+
"9": 70,
|
| 1097 |
+
"З": 71,
|
| 1098 |
+
")": 72,
|
| 1099 |
+
"8": 73,
|
| 1100 |
+
"(": 74,
|
| 1101 |
+
"6": 75,
|
| 1102 |
+
"7": 76,
|
| 1103 |
+
"Г": 77,
|
| 1104 |
+
"c": 78,
|
| 1105 |
+
"Л": 79,
|
| 1106 |
+
"m": 80,
|
| 1107 |
+
"–": 81,
|
| 1108 |
+
"d": 82,
|
| 1109 |
+
"u": 83,
|
| 1110 |
+
"/": 84,
|
| 1111 |
+
"h": 85,
|
| 1112 |
+
"?": 86,
|
| 1113 |
+
"g": 87,
|
| 1114 |
+
"!": 88,
|
| 1115 |
+
"p": 89,
|
| 1116 |
+
"b": 90,
|
| 1117 |
+
"Х": 91,
|
| 1118 |
+
"S": 92,
|
| 1119 |
+
"—": 93,
|
| 1120 |
+
"У": 94,
|
| 1121 |
+
"A": 95,
|
| 1122 |
+
";": 96,
|
| 1123 |
+
"Ф": 97,
|
| 1124 |
+
"I": 98,
|
| 1125 |
+
"y": 99,
|
| 1126 |
+
"C": 100,
|
| 1127 |
+
"k": 101,
|
| 1128 |
+
"Ч": 102,
|
| 1129 |
+
"v": 103,
|
| 1130 |
+
"w": 104,
|
| 1131 |
+
"P": 105,
|
| 1132 |
+
"T": 106,
|
| 1133 |
+
"Ц": 107,
|
| 1134 |
+
"B": 108,
|
| 1135 |
+
"D": 109,
|
| 1136 |
+
"M": 110,
|
| 1137 |
+
"f": 111,
|
| 1138 |
+
"„": 112,
|
| 1139 |
+
"E": 113,
|
| 1140 |
+
"%": 114,
|
| 1141 |
+
"R": 115,
|
| 1142 |
+
"ь": 116,
|
| 1143 |
+
"“": 117,
|
| 1144 |
+
"N": 118,
|
| 1145 |
+
"L": 119,
|
| 1146 |
+
"G": 120,
|
| 1147 |
+
"O": 121,
|
| 1148 |
+
"Щ": 122,
|
| 1149 |
+
"V": 123,
|
| 1150 |
+
"F": 124,
|
| 1151 |
+
"Я": 125,
|
| 1152 |
+
"|": 126,
|
| 1153 |
+
"Ш": 127,
|
| 1154 |
+
"H": 128,
|
| 1155 |
+
"Ж": 129,
|
| 1156 |
+
"…": 130,
|
| 1157 |
+
"W": 131,
|
| 1158 |
+
"z": 132,
|
| 1159 |
+
"x": 133,
|
| 1160 |
+
"”": 134,
|
| 1161 |
+
"Й": 135,
|
| 1162 |
+
"U": 136,
|
| 1163 |
+
"]": 137,
|
| 1164 |
+
"[": 138,
|
| 1165 |
+
"Ю": 139,
|
| 1166 |
+
"'": 140,
|
| 1167 |
+
"*": 141,
|
| 1168 |
+
"K": 142,
|
| 1169 |
+
"#": 143,
|
| 1170 |
+
"Ъ": 144,
|
| 1171 |
+
"X": 145,
|
| 1172 |
+
"»": 146,
|
| 1173 |
+
"+": 147,
|
| 1174 |
+
"J": 148,
|
| 1175 |
+
"_": 149,
|
| 1176 |
+
"": 150,
|
| 1177 |
+
"•": 151,
|
| 1178 |
+
"q": 152,
|
| 1179 |
+
"№": 153,
|
| 1180 |
+
"j": 154,
|
| 1181 |
+
"Y": 155,
|
| 1182 |
+
"=": 156,
|
| 1183 |
+
"\t": 157,
|
| 1184 |
+
">": 158,
|
| 1185 |
+
"Z": 159,
|
| 1186 |
+
"&": 160,
|
| 1187 |
+
"І": 161,
|
| 1188 |
+
"·": 162,
|
| 1189 |
+
"«": 163,
|
| 1190 |
+
"°": 164,
|
| 1191 |
+
"Q": 165,
|
| 1192 |
+
"$": 166,
|
| 1193 |
+
"@": 167,
|
| 1194 |
+
"ѣ": 168,
|
| 1195 |
+
"ы": 169,
|
| 1196 |
+
"<": 170,
|
| 1197 |
+
"": 171,
|
| 1198 |
+
" ": 172,
|
| 1199 |
+
"ĸ": 173,
|
| 1200 |
+
"}": 174,
|
| 1201 |
+
"{": 175,
|
| 1202 |
+
"↑": 176,
|
| 1203 |
+
"©": 177,
|
| 1204 |
+
"§": 178,
|
| 1205 |
+
"®": 179,
|
| 1206 |
+
"é": 180,
|
| 1207 |
+
"\\": 181,
|
| 1208 |
+
"›": 182,
|
| 1209 |
+
"→": 183,
|
| 1210 |
+
"’": 184,
|
| 1211 |
+
"�": 185,
|
| 1212 |
+
"α": 186,
|
| 1213 |
+
"€": 187,
|
| 1214 |
+
"ο": 188,
|
| 1215 |
+
"~": 189,
|
| 1216 |
+
"🙂": 190,
|
| 1217 |
+
"ѫ": 191,
|
| 1218 |
+
"`": 192,
|
| 1219 |
+
"ν": 193,
|
| 1220 |
+
"ü": 194,
|
| 1221 |
+
"ι": 195,
|
| 1222 |
+
"τ": 196,
|
| 1223 |
+
"►": 197,
|
| 1224 |
+
"″": 198,
|
| 1225 |
+
"ς": 199,
|
| 1226 |
+
"ρ": 200,
|
| 1227 |
+
"э": 201,
|
| 1228 |
+
"ε": 202,
|
| 1229 |
+
"ä": 203,
|
| 1230 |
+
"κ": 204,
|
| 1231 |
+
"σ": 205,
|
| 1232 |
+
"λ": 206,
|
| 1233 |
+
"⋅": 207,
|
| 1234 |
+
"™": 208,
|
| 1235 |
+
"²": 209,
|
| 1236 |
+
"ö": 210,
|
| 1237 |
+
"μ": 211,
|
| 1238 |
+
"á": 212,
|
| 1239 |
+
"️": 213,
|
| 1240 |
+
"←": 214,
|
| 1241 |
+
"†": 215,
|
| 1242 |
+
"Ь": 216,
|
| 1243 |
+
"ј": 217,
|
| 1244 |
+
"і": 218,
|
| 1245 |
+
"η": 219,
|
| 1246 |
+
"×": 220,
|
| 1247 |
+
"′": 221,
|
| 1248 |
+
"è": 222,
|
| 1249 |
+
"¬": 223,
|
| 1250 |
+
"υ": 224,
|
| 1251 |
+
"à": 225,
|
| 1252 |
+
"^": 226,
|
| 1253 |
+
"ó": 227,
|
| 1254 |
+
"π": 228,
|
| 1255 |
+
"í": 229,
|
| 1256 |
+
"ί": 230,
|
| 1257 |
+
"": 231,
|
| 1258 |
+
"Π": 232,
|
| 1259 |
+
"ا": 233,
|
| 1260 |
+
"£": 234,
|
| 1261 |
+
"ά": 235,
|
| 1262 |
+
"ı": 236,
|
| 1263 |
+
"●": 237,
|
| 1264 |
+
"★": 238,
|
| 1265 |
+
"½": 239,
|
| 1266 |
+
"γ": 240,
|
| 1267 |
+
"‑": 241,
|
| 1268 |
+
"ç": 242,
|
| 1269 |
+
"‘": 243,
|
| 1270 |
+
"ω": 244,
|
| 1271 |
+
"ό": 245,
|
| 1272 |
+
"ل": 246,
|
| 1273 |
+
"😉": 247,
|
| 1274 |
+
"δ": 248,
|
| 1275 |
+
"Э": 249,
|
| 1276 |
+
"✔": 250,
|
| 1277 |
+
"😀": 251,
|
| 1278 |
+
"♥": 252,
|
| 1279 |
+
"Δ": 253,
|
| 1280 |
+
"š": 254,
|
| 1281 |
+
"😂": 255,
|
| 1282 |
+
"ñ": 256,
|
| 1283 |
+
"❤": 257,
|
| 1284 |
+
"є": 258,
|
| 1285 |
+
"β": 259,
|
| 1286 |
+
"č": 260,
|
| 1287 |
+
"−": 261,
|
| 1288 |
+
"ł": 262,
|
| 1289 |
+
"ή": 263,
|
| 1290 |
+
"́": 264,
|
| 1291 |
+
"Ε": 265,
|
| 1292 |
+
"â": 266,
|
| 1293 |
+
"Α": 267,
|
| 1294 |
+
"έ": 268,
|
| 1295 |
+
"ر": 269,
|
| 1296 |
+
"º": 270,
|
| 1297 |
+
"ي": 271,
|
| 1298 |
+
"å": 272,
|
| 1299 |
+
"ò": 273,
|
| 1300 |
+
"±": 274,
|
| 1301 |
+
"Ø": 275,
|
| 1302 |
+
"ş": 276,
|
| 1303 |
+
"ú": 277,
|
| 1304 |
+
"ù": 278,
|
| 1305 |
+
"ß": 279,
|
| 1306 |
+
"µ": 280,
|
| 1307 |
+
"ă": 281,
|
| 1308 |
+
"ê": 282,
|
| 1309 |
+
"【": 283,
|
| 1310 |
+
"】": 284,
|
| 1311 |
+
"ë": 285,
|
| 1312 |
+
"م": 286,
|
| 1313 |
+
"و": 287,
|
| 1314 |
+
"ё": 288,
|
| 1315 |
+
"θ": 289,
|
| 1316 |
+
"ύ": 290,
|
| 1317 |
+
"χ": 291,
|
| 1318 |
+
"⇒": 292,
|
| 1319 |
+
"✓": 293,
|
| 1320 |
+
"ô": 294,
|
| 1321 |
+
"♦": 295,
|
| 1322 |
+
"ć": 296,
|
| 1323 |
+
" ": 297,
|
| 1324 |
+
"î": 298,
|
| 1325 |
+
"Ü": 299,
|
| 1326 |
+
"": 300,
|
| 1327 |
+
"¼": 301,
|
| 1328 |
+
"Σ": 302,
|
| 1329 |
+
"Μ": 303,
|
| 1330 |
+
"φ": 304,
|
| 1331 |
+
"ї": 305,
|
| 1332 |
+
"Κ": 306,
|
| 1333 |
+
"É": 307,
|
| 1334 |
+
"ن": 308,
|
| 1335 |
+
"Ö": 309,
|
| 1336 |
+
"ώ": 310,
|
| 1337 |
+
"✅": 311,
|
| 1338 |
+
"̆": 312,
|
| 1339 |
+
"ø": 313,
|
| 1340 |
+
"♠": 314,
|
| 1341 |
+
"ب": 315,
|
| 1342 |
+
"ᐉ": 316,
|
| 1343 |
+
"Ι": 317,
|
| 1344 |
+
"Ο": 318,
|
| 1345 |
+
"ѕ": 319,
|
| 1346 |
+
"İ": 320,
|
| 1347 |
+
"њ": 321,
|
| 1348 |
+
"▼": 322,
|
| 1349 |
+
"Ѕ": 323,
|
| 1350 |
+
"ت": 324,
|
| 1351 |
+
"ž": 325,
|
| 1352 |
+
"ћ": 326,
|
| 1353 |
+
"↓": 327,
|
| 1354 |
+
"ع": 328,
|
| 1355 |
+
"Č": 329,
|
| 1356 |
+
"ę": 330,
|
| 1357 |
+
"😁": 331,
|
| 1358 |
+
"ā": 332,
|
| 1359 |
+
"د": 333,
|
| 1360 |
+
"³": 334,
|
| 1361 |
+
"Τ": 335,
|
| 1362 |
+
"Β": 336,
|
| 1363 |
+
"🔘": 337,
|
| 1364 |
+
"َ": 338,
|
| 1365 |
+
"ğ": 339,
|
| 1366 |
+
"▷": 340,
|
| 1367 |
+
"📕": 341,
|
| 1368 |
+
"ة": 342,
|
| 1369 |
+
"℃": 343,
|
| 1370 |
+
"س": 344,
|
| 1371 |
+
"‹": 345,
|
| 1372 |
+
"Ν": 346,
|
| 1373 |
+
"‒": 347,
|
| 1374 |
+
"‰": 348,
|
| 1375 |
+
"": 349,
|
| 1376 |
+
"➡": 350,
|
| 1377 |
+
"æ": 351,
|
| 1378 |
+
"Š": 352,
|
| 1379 |
+
"☆": 353,
|
| 1380 |
+
"÷": 354,
|
| 1381 |
+
"י": 355,
|
| 1382 |
+
"😊": 356,
|
| 1383 |
+
"🤣": 357,
|
| 1384 |
+
"ã": 358,
|
| 1385 |
+
"ف": 359,
|
| 1386 |
+
"ه": 360,
|
| 1387 |
+
"Γ": 361,
|
| 1388 |
+
"ð": 362,
|
| 1389 |
+
"➤": 363,
|
| 1390 |
+
"■": 364,
|
| 1391 |
+
"≥": 365,
|
| 1392 |
+
"": 366,
|
| 1393 |
+
"Θ": 367,
|
| 1394 |
+
"Ј": 368,
|
| 1395 |
+
"ý": 369,
|
| 1396 |
+
"": 370,
|
| 1397 |
+
"中": 371,
|
| 1398 |
+
"⋆": 372,
|
| 1399 |
+
"▪": 373,
|
| 1400 |
+
"⭐": 374,
|
| 1401 |
+
"̣": 375,
|
| 1402 |
+
"¾": 376,
|
| 1403 |
+
"文": 377,
|
| 1404 |
+
"": 378,
|
| 1405 |
+
"―": 379,
|
| 1406 |
+
"ï": 380,
|
| 1407 |
+
"ζ": 381,
|
| 1408 |
+
"Ş": 382,
|
| 1409 |
+
"ì": 383,
|
| 1410 |
+
"Η": 384,
|
| 1411 |
+
"љ": 385,
|
| 1412 |
+
"》": 386,
|
| 1413 |
+
"≤": 387,
|
| 1414 |
+
"─": 388,
|
| 1415 |
+
"ξ": 389,
|
| 1416 |
+
" ": 390,
|
| 1417 |
+
"ی": 391,
|
| 1418 |
+
"☎": 392,
|
| 1419 |
+
"ś": 393,
|
| 1420 |
+
"̄": 394,
|
| 1421 |
+
"": 395,
|
| 1422 |
+
"Ы": 396,
|
| 1423 |
+
"า": 397,
|
| 1424 |
+
"⠀": 398,
|
| 1425 |
+
"∞": 399,
|
| 1426 |
+
"Λ": 400,
|
| 1427 |
+
"ě": 401,
|
| 1428 |
+
"¹": 402,
|
| 1429 |
+
"◊": 403,
|
| 1430 |
+
"ą": 404,
|
| 1431 |
+
"《": 405,
|
| 1432 |
+
"Á": 406,
|
| 1433 |
+
"ك": 407,
|
| 1434 |
+
"‐": 408,
|
| 1435 |
+
"👉": 409,
|
| 1436 |
+
"ق": 410,
|
| 1437 |
+
"Ç": 411,
|
| 1438 |
+
"[SEN_100]": 412,
|
| 1439 |
+
"[SEN_99]": 413,
|
| 1440 |
+
"[SEN_98]": 414,
|
| 1441 |
+
"[SEN_97]": 415,
|
| 1442 |
+
"[SEN_96]": 416,
|
| 1443 |
+
"[SEN_95]": 417,
|
| 1444 |
+
"[SEN_94]": 418,
|
| 1445 |
+
"[SEN_93]": 419,
|
| 1446 |
+
"[SEN_92]": 420,
|
| 1447 |
+
"[SEN_91]": 421,
|
| 1448 |
+
"[SEN_90]": 422,
|
| 1449 |
+
"[SEN_89]": 423,
|
| 1450 |
+
"[SEN_88]": 424,
|
| 1451 |
+
"[SEN_87]": 425,
|
| 1452 |
+
"[SEN_86]": 426,
|
| 1453 |
+
"[SEN_85]": 427,
|
| 1454 |
+
"[SEN_84]": 428,
|
| 1455 |
+
"[SEN_83]": 429,
|
| 1456 |
+
"[SEN_82]": 430,
|
| 1457 |
+
"[SEN_81]": 431,
|
| 1458 |
+
"[SEN_80]": 432,
|
| 1459 |
+
"[SEN_79]": 433,
|
| 1460 |
+
"[SEN_78]": 434,
|
| 1461 |
+
"[SEN_77]": 435,
|
| 1462 |
+
"[SEN_76]": 436,
|
| 1463 |
+
"[SEN_75]": 437,
|
| 1464 |
+
"[SEN_74]": 438,
|
| 1465 |
+
"[SEN_73]": 439,
|
| 1466 |
+
"[SEN_72]": 440,
|
| 1467 |
+
"[SEN_71]": 441,
|
| 1468 |
+
"[SEN_70]": 442,
|
| 1469 |
+
"[SEN_69]": 443,
|
| 1470 |
+
"[SEN_68]": 444,
|
| 1471 |
+
"[SEN_67]": 445,
|
| 1472 |
+
"[SEN_66]": 446,
|
| 1473 |
+
"[SEN_65]": 447,
|
| 1474 |
+
"[SEN_64]": 448,
|
| 1475 |
+
"[SEN_63]": 449,
|
| 1476 |
+
"[SEN_62]": 450,
|
| 1477 |
+
"[SEN_61]": 451,
|
| 1478 |
+
"[SEN_60]": 452,
|
| 1479 |
+
"[SEN_59]": 453,
|
| 1480 |
+
"[SEN_58]": 454,
|
| 1481 |
+
"[SEN_57]": 455,
|
| 1482 |
+
"[SEN_56]": 456,
|
| 1483 |
+
"[SEN_55]": 457,
|
| 1484 |
+
"[SEN_54]": 458,
|
| 1485 |
+
"[SEN_53]": 459,
|
| 1486 |
+
"[SEN_52]": 460,
|
| 1487 |
+
"[SEN_51]": 461,
|
| 1488 |
+
"[SEN_50]": 462,
|
| 1489 |
+
"[SEN_49]": 463,
|
| 1490 |
+
"[SEN_48]": 464,
|
| 1491 |
+
"[SEN_47]": 465,
|
| 1492 |
+
"[SEN_46]": 466,
|
| 1493 |
+
"[SEN_45]": 467,
|
| 1494 |
+
"[SEN_44]": 468,
|
| 1495 |
+
"[SEN_43]": 469,
|
| 1496 |
+
"[SEN_42]": 470,
|
| 1497 |
+
"[SEN_41]": 471,
|
| 1498 |
+
"[SEN_40]": 472,
|
| 1499 |
+
"[SEN_39]": 473,
|
| 1500 |
+
"[SEN_38]": 474,
|
| 1501 |
+
"[SEN_37]": 475,
|
| 1502 |
+
"[SEN_36]": 476,
|
| 1503 |
+
"[SEN_35]": 477,
|
| 1504 |
+
"[SEN_34]": 478,
|
| 1505 |
+
"[SEN_33]": 479,
|
| 1506 |
+
"[SEN_32]": 480,
|
| 1507 |
+
"[SEN_31]": 481,
|
| 1508 |
+
"[SEN_30]": 482,
|
| 1509 |
+
"[SEN_29]": 483,
|
| 1510 |
+
"[SEN_28]": 484,
|
| 1511 |
+
"[SEN_27]": 485,
|
| 1512 |
+
"[SEN_26]": 486,
|
| 1513 |
+
"[SEN_25]": 487,
|
| 1514 |
+
"[SEN_24]": 488,
|
| 1515 |
+
"[SEN_23]": 489,
|
| 1516 |
+
"[SEN_22]": 490,
|
| 1517 |
+
"[SEN_21]": 491,
|
| 1518 |
+
"[SEN_20]": 492,
|
| 1519 |
+
"[SEN_19]": 493,
|
| 1520 |
+
"[SEN_18]": 494,
|
| 1521 |
+
"[SEN_17]": 495,
|
| 1522 |
+
"[SEN_16]": 496,
|
| 1523 |
+
"[SEN_15]": 497,
|
| 1524 |
+
"[SEN_14]": 498,
|
| 1525 |
+
"[SEN_13]": 499,
|
| 1526 |
+
"[SEN_12]": 500,
|
| 1527 |
+
"[SEN_11]": 501,
|
| 1528 |
+
"[SEN_10]": 502,
|
| 1529 |
+
"[SEN_9]": 503,
|
| 1530 |
+
"[SEN_8]": 504,
|
| 1531 |
+
"[SEN_7]": 505,
|
| 1532 |
+
"[SEN_6]": 506,
|
| 1533 |
+
"[SEN_5]": 507,
|
| 1534 |
+
"[SEN_4]": 508,
|
| 1535 |
+
"[SEN_3]": 509,
|
| 1536 |
+
"[SEN_2]": 510,
|
| 1537 |
+
"[SEN_1]": 511
|
| 1538 |
+
}
|
| 1539 |
+
}
|
| 1540 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,854 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[UNK]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[PAD]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[CLS]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[SEP]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"4": {
|
| 36 |
+
"content": "[META]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
},
|
| 43 |
+
"412": {
|
| 44 |
+
"content": "[SEN_100]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"413": {
|
| 52 |
+
"content": "[SEN_99]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"414": {
|
| 60 |
+
"content": "[SEN_98]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
+
},
|
| 67 |
+
"415": {
|
| 68 |
+
"content": "[SEN_97]",
|
| 69 |
+
"lstrip": false,
|
| 70 |
+
"normalized": false,
|
| 71 |
+
"rstrip": false,
|
| 72 |
+
"single_word": false,
|
| 73 |
+
"special": true
|
| 74 |
+
},
|
| 75 |
+
"416": {
|
| 76 |
+
"content": "[SEN_96]",
|
| 77 |
+
"lstrip": false,
|
| 78 |
+
"normalized": false,
|
| 79 |
+
"rstrip": false,
|
| 80 |
+
"single_word": false,
|
| 81 |
+
"special": true
|
| 82 |
+
},
|
| 83 |
+
"417": {
|
| 84 |
+
"content": "[SEN_95]",
|
| 85 |
+
"lstrip": false,
|
| 86 |
+
"normalized": false,
|
| 87 |
+
"rstrip": false,
|
| 88 |
+
"single_word": false,
|
| 89 |
+
"special": true
|
| 90 |
+
},
|
| 91 |
+
"418": {
|
| 92 |
+
"content": "[SEN_94]",
|
| 93 |
+
"lstrip": false,
|
| 94 |
+
"normalized": false,
|
| 95 |
+
"rstrip": false,
|
| 96 |
+
"single_word": false,
|
| 97 |
+
"special": true
|
| 98 |
+
},
|
| 99 |
+
"419": {
|
| 100 |
+
"content": "[SEN_93]",
|
| 101 |
+
"lstrip": false,
|
| 102 |
+
"normalized": false,
|
| 103 |
+
"rstrip": false,
|
| 104 |
+
"single_word": false,
|
| 105 |
+
"special": true
|
| 106 |
+
},
|
| 107 |
+
"420": {
|
| 108 |
+
"content": "[SEN_92]",
|
| 109 |
+
"lstrip": false,
|
| 110 |
+
"normalized": false,
|
| 111 |
+
"rstrip": false,
|
| 112 |
+
"single_word": false,
|
| 113 |
+
"special": true
|
| 114 |
+
},
|
| 115 |
+
"421": {
|
| 116 |
+
"content": "[SEN_91]",
|
| 117 |
+
"lstrip": false,
|
| 118 |
+
"normalized": false,
|
| 119 |
+
"rstrip": false,
|
| 120 |
+
"single_word": false,
|
| 121 |
+
"special": true
|
| 122 |
+
},
|
| 123 |
+
"422": {
|
| 124 |
+
"content": "[SEN_90]",
|
| 125 |
+
"lstrip": false,
|
| 126 |
+
"normalized": false,
|
| 127 |
+
"rstrip": false,
|
| 128 |
+
"single_word": false,
|
| 129 |
+
"special": true
|
| 130 |
+
},
|
| 131 |
+
"423": {
|
| 132 |
+
"content": "[SEN_89]",
|
| 133 |
+
"lstrip": false,
|
| 134 |
+
"normalized": false,
|
| 135 |
+
"rstrip": false,
|
| 136 |
+
"single_word": false,
|
| 137 |
+
"special": true
|
| 138 |
+
},
|
| 139 |
+
"424": {
|
| 140 |
+
"content": "[SEN_88]",
|
| 141 |
+
"lstrip": false,
|
| 142 |
+
"normalized": false,
|
| 143 |
+
"rstrip": false,
|
| 144 |
+
"single_word": false,
|
| 145 |
+
"special": true
|
| 146 |
+
},
|
| 147 |
+
"425": {
|
| 148 |
+
"content": "[SEN_87]",
|
| 149 |
+
"lstrip": false,
|
| 150 |
+
"normalized": false,
|
| 151 |
+
"rstrip": false,
|
| 152 |
+
"single_word": false,
|
| 153 |
+
"special": true
|
| 154 |
+
},
|
| 155 |
+
"426": {
|
| 156 |
+
"content": "[SEN_86]",
|
| 157 |
+
"lstrip": false,
|
| 158 |
+
"normalized": false,
|
| 159 |
+
"rstrip": false,
|
| 160 |
+
"single_word": false,
|
| 161 |
+
"special": true
|
| 162 |
+
},
|
| 163 |
+
"427": {
|
| 164 |
+
"content": "[SEN_85]",
|
| 165 |
+
"lstrip": false,
|
| 166 |
+
"normalized": false,
|
| 167 |
+
"rstrip": false,
|
| 168 |
+
"single_word": false,
|
| 169 |
+
"special": true
|
| 170 |
+
},
|
| 171 |
+
"428": {
|
| 172 |
+
"content": "[SEN_84]",
|
| 173 |
+
"lstrip": false,
|
| 174 |
+
"normalized": false,
|
| 175 |
+
"rstrip": false,
|
| 176 |
+
"single_word": false,
|
| 177 |
+
"special": true
|
| 178 |
+
},
|
| 179 |
+
"429": {
|
| 180 |
+
"content": "[SEN_83]",
|
| 181 |
+
"lstrip": false,
|
| 182 |
+
"normalized": false,
|
| 183 |
+
"rstrip": false,
|
| 184 |
+
"single_word": false,
|
| 185 |
+
"special": true
|
| 186 |
+
},
|
| 187 |
+
"430": {
|
| 188 |
+
"content": "[SEN_82]",
|
| 189 |
+
"lstrip": false,
|
| 190 |
+
"normalized": false,
|
| 191 |
+
"rstrip": false,
|
| 192 |
+
"single_word": false,
|
| 193 |
+
"special": true
|
| 194 |
+
},
|
| 195 |
+
"431": {
|
| 196 |
+
"content": "[SEN_81]",
|
| 197 |
+
"lstrip": false,
|
| 198 |
+
"normalized": false,
|
| 199 |
+
"rstrip": false,
|
| 200 |
+
"single_word": false,
|
| 201 |
+
"special": true
|
| 202 |
+
},
|
| 203 |
+
"432": {
|
| 204 |
+
"content": "[SEN_80]",
|
| 205 |
+
"lstrip": false,
|
| 206 |
+
"normalized": false,
|
| 207 |
+
"rstrip": false,
|
| 208 |
+
"single_word": false,
|
| 209 |
+
"special": true
|
| 210 |
+
},
|
| 211 |
+
"433": {
|
| 212 |
+
"content": "[SEN_79]",
|
| 213 |
+
"lstrip": false,
|
| 214 |
+
"normalized": false,
|
| 215 |
+
"rstrip": false,
|
| 216 |
+
"single_word": false,
|
| 217 |
+
"special": true
|
| 218 |
+
},
|
| 219 |
+
"434": {
|
| 220 |
+
"content": "[SEN_78]",
|
| 221 |
+
"lstrip": false,
|
| 222 |
+
"normalized": false,
|
| 223 |
+
"rstrip": false,
|
| 224 |
+
"single_word": false,
|
| 225 |
+
"special": true
|
| 226 |
+
},
|
| 227 |
+
"435": {
|
| 228 |
+
"content": "[SEN_77]",
|
| 229 |
+
"lstrip": false,
|
| 230 |
+
"normalized": false,
|
| 231 |
+
"rstrip": false,
|
| 232 |
+
"single_word": false,
|
| 233 |
+
"special": true
|
| 234 |
+
},
|
| 235 |
+
"436": {
|
| 236 |
+
"content": "[SEN_76]",
|
| 237 |
+
"lstrip": false,
|
| 238 |
+
"normalized": false,
|
| 239 |
+
"rstrip": false,
|
| 240 |
+
"single_word": false,
|
| 241 |
+
"special": true
|
| 242 |
+
},
|
| 243 |
+
"437": {
|
| 244 |
+
"content": "[SEN_75]",
|
| 245 |
+
"lstrip": false,
|
| 246 |
+
"normalized": false,
|
| 247 |
+
"rstrip": false,
|
| 248 |
+
"single_word": false,
|
| 249 |
+
"special": true
|
| 250 |
+
},
|
| 251 |
+
"438": {
|
| 252 |
+
"content": "[SEN_74]",
|
| 253 |
+
"lstrip": false,
|
| 254 |
+
"normalized": false,
|
| 255 |
+
"rstrip": false,
|
| 256 |
+
"single_word": false,
|
| 257 |
+
"special": true
|
| 258 |
+
},
|
| 259 |
+
"439": {
|
| 260 |
+
"content": "[SEN_73]",
|
| 261 |
+
"lstrip": false,
|
| 262 |
+
"normalized": false,
|
| 263 |
+
"rstrip": false,
|
| 264 |
+
"single_word": false,
|
| 265 |
+
"special": true
|
| 266 |
+
},
|
| 267 |
+
"440": {
|
| 268 |
+
"content": "[SEN_72]",
|
| 269 |
+
"lstrip": false,
|
| 270 |
+
"normalized": false,
|
| 271 |
+
"rstrip": false,
|
| 272 |
+
"single_word": false,
|
| 273 |
+
"special": true
|
| 274 |
+
},
|
| 275 |
+
"441": {
|
| 276 |
+
"content": "[SEN_71]",
|
| 277 |
+
"lstrip": false,
|
| 278 |
+
"normalized": false,
|
| 279 |
+
"rstrip": false,
|
| 280 |
+
"single_word": false,
|
| 281 |
+
"special": true
|
| 282 |
+
},
|
| 283 |
+
"442": {
|
| 284 |
+
"content": "[SEN_70]",
|
| 285 |
+
"lstrip": false,
|
| 286 |
+
"normalized": false,
|
| 287 |
+
"rstrip": false,
|
| 288 |
+
"single_word": false,
|
| 289 |
+
"special": true
|
| 290 |
+
},
|
| 291 |
+
"443": {
|
| 292 |
+
"content": "[SEN_69]",
|
| 293 |
+
"lstrip": false,
|
| 294 |
+
"normalized": false,
|
| 295 |
+
"rstrip": false,
|
| 296 |
+
"single_word": false,
|
| 297 |
+
"special": true
|
| 298 |
+
},
|
| 299 |
+
"444": {
|
| 300 |
+
"content": "[SEN_68]",
|
| 301 |
+
"lstrip": false,
|
| 302 |
+
"normalized": false,
|
| 303 |
+
"rstrip": false,
|
| 304 |
+
"single_word": false,
|
| 305 |
+
"special": true
|
| 306 |
+
},
|
| 307 |
+
"445": {
|
| 308 |
+
"content": "[SEN_67]",
|
| 309 |
+
"lstrip": false,
|
| 310 |
+
"normalized": false,
|
| 311 |
+
"rstrip": false,
|
| 312 |
+
"single_word": false,
|
| 313 |
+
"special": true
|
| 314 |
+
},
|
| 315 |
+
"446": {
|
| 316 |
+
"content": "[SEN_66]",
|
| 317 |
+
"lstrip": false,
|
| 318 |
+
"normalized": false,
|
| 319 |
+
"rstrip": false,
|
| 320 |
+
"single_word": false,
|
| 321 |
+
"special": true
|
| 322 |
+
},
|
| 323 |
+
"447": {
|
| 324 |
+
"content": "[SEN_65]",
|
| 325 |
+
"lstrip": false,
|
| 326 |
+
"normalized": false,
|
| 327 |
+
"rstrip": false,
|
| 328 |
+
"single_word": false,
|
| 329 |
+
"special": true
|
| 330 |
+
},
|
| 331 |
+
"448": {
|
| 332 |
+
"content": "[SEN_64]",
|
| 333 |
+
"lstrip": false,
|
| 334 |
+
"normalized": false,
|
| 335 |
+
"rstrip": false,
|
| 336 |
+
"single_word": false,
|
| 337 |
+
"special": true
|
| 338 |
+
},
|
| 339 |
+
"449": {
|
| 340 |
+
"content": "[SEN_63]",
|
| 341 |
+
"lstrip": false,
|
| 342 |
+
"normalized": false,
|
| 343 |
+
"rstrip": false,
|
| 344 |
+
"single_word": false,
|
| 345 |
+
"special": true
|
| 346 |
+
},
|
| 347 |
+
"450": {
|
| 348 |
+
"content": "[SEN_62]",
|
| 349 |
+
"lstrip": false,
|
| 350 |
+
"normalized": false,
|
| 351 |
+
"rstrip": false,
|
| 352 |
+
"single_word": false,
|
| 353 |
+
"special": true
|
| 354 |
+
},
|
| 355 |
+
"451": {
|
| 356 |
+
"content": "[SEN_61]",
|
| 357 |
+
"lstrip": false,
|
| 358 |
+
"normalized": false,
|
| 359 |
+
"rstrip": false,
|
| 360 |
+
"single_word": false,
|
| 361 |
+
"special": true
|
| 362 |
+
},
|
| 363 |
+
"452": {
|
| 364 |
+
"content": "[SEN_60]",
|
| 365 |
+
"lstrip": false,
|
| 366 |
+
"normalized": false,
|
| 367 |
+
"rstrip": false,
|
| 368 |
+
"single_word": false,
|
| 369 |
+
"special": true
|
| 370 |
+
},
|
| 371 |
+
"453": {
|
| 372 |
+
"content": "[SEN_59]",
|
| 373 |
+
"lstrip": false,
|
| 374 |
+
"normalized": false,
|
| 375 |
+
"rstrip": false,
|
| 376 |
+
"single_word": false,
|
| 377 |
+
"special": true
|
| 378 |
+
},
|
| 379 |
+
"454": {
|
| 380 |
+
"content": "[SEN_58]",
|
| 381 |
+
"lstrip": false,
|
| 382 |
+
"normalized": false,
|
| 383 |
+
"rstrip": false,
|
| 384 |
+
"single_word": false,
|
| 385 |
+
"special": true
|
| 386 |
+
},
|
| 387 |
+
"455": {
|
| 388 |
+
"content": "[SEN_57]",
|
| 389 |
+
"lstrip": false,
|
| 390 |
+
"normalized": false,
|
| 391 |
+
"rstrip": false,
|
| 392 |
+
"single_word": false,
|
| 393 |
+
"special": true
|
| 394 |
+
},
|
| 395 |
+
"456": {
|
| 396 |
+
"content": "[SEN_56]",
|
| 397 |
+
"lstrip": false,
|
| 398 |
+
"normalized": false,
|
| 399 |
+
"rstrip": false,
|
| 400 |
+
"single_word": false,
|
| 401 |
+
"special": true
|
| 402 |
+
},
|
| 403 |
+
"457": {
|
| 404 |
+
"content": "[SEN_55]",
|
| 405 |
+
"lstrip": false,
|
| 406 |
+
"normalized": false,
|
| 407 |
+
"rstrip": false,
|
| 408 |
+
"single_word": false,
|
| 409 |
+
"special": true
|
| 410 |
+
},
|
| 411 |
+
"458": {
|
| 412 |
+
"content": "[SEN_54]",
|
| 413 |
+
"lstrip": false,
|
| 414 |
+
"normalized": false,
|
| 415 |
+
"rstrip": false,
|
| 416 |
+
"single_word": false,
|
| 417 |
+
"special": true
|
| 418 |
+
},
|
| 419 |
+
"459": {
|
| 420 |
+
"content": "[SEN_53]",
|
| 421 |
+
"lstrip": false,
|
| 422 |
+
"normalized": false,
|
| 423 |
+
"rstrip": false,
|
| 424 |
+
"single_word": false,
|
| 425 |
+
"special": true
|
| 426 |
+
},
|
| 427 |
+
"460": {
|
| 428 |
+
"content": "[SEN_52]",
|
| 429 |
+
"lstrip": false,
|
| 430 |
+
"normalized": false,
|
| 431 |
+
"rstrip": false,
|
| 432 |
+
"single_word": false,
|
| 433 |
+
"special": true
|
| 434 |
+
},
|
| 435 |
+
"461": {
|
| 436 |
+
"content": "[SEN_51]",
|
| 437 |
+
"lstrip": false,
|
| 438 |
+
"normalized": false,
|
| 439 |
+
"rstrip": false,
|
| 440 |
+
"single_word": false,
|
| 441 |
+
"special": true
|
| 442 |
+
},
|
| 443 |
+
"462": {
|
| 444 |
+
"content": "[SEN_50]",
|
| 445 |
+
"lstrip": false,
|
| 446 |
+
"normalized": false,
|
| 447 |
+
"rstrip": false,
|
| 448 |
+
"single_word": false,
|
| 449 |
+
"special": true
|
| 450 |
+
},
|
| 451 |
+
"463": {
|
| 452 |
+
"content": "[SEN_49]",
|
| 453 |
+
"lstrip": false,
|
| 454 |
+
"normalized": false,
|
| 455 |
+
"rstrip": false,
|
| 456 |
+
"single_word": false,
|
| 457 |
+
"special": true
|
| 458 |
+
},
|
| 459 |
+
"464": {
|
| 460 |
+
"content": "[SEN_48]",
|
| 461 |
+
"lstrip": false,
|
| 462 |
+
"normalized": false,
|
| 463 |
+
"rstrip": false,
|
| 464 |
+
"single_word": false,
|
| 465 |
+
"special": true
|
| 466 |
+
},
|
| 467 |
+
"465": {
|
| 468 |
+
"content": "[SEN_47]",
|
| 469 |
+
"lstrip": false,
|
| 470 |
+
"normalized": false,
|
| 471 |
+
"rstrip": false,
|
| 472 |
+
"single_word": false,
|
| 473 |
+
"special": true
|
| 474 |
+
},
|
| 475 |
+
"466": {
|
| 476 |
+
"content": "[SEN_46]",
|
| 477 |
+
"lstrip": false,
|
| 478 |
+
"normalized": false,
|
| 479 |
+
"rstrip": false,
|
| 480 |
+
"single_word": false,
|
| 481 |
+
"special": true
|
| 482 |
+
},
|
| 483 |
+
"467": {
|
| 484 |
+
"content": "[SEN_45]",
|
| 485 |
+
"lstrip": false,
|
| 486 |
+
"normalized": false,
|
| 487 |
+
"rstrip": false,
|
| 488 |
+
"single_word": false,
|
| 489 |
+
"special": true
|
| 490 |
+
},
|
| 491 |
+
"468": {
|
| 492 |
+
"content": "[SEN_44]",
|
| 493 |
+
"lstrip": false,
|
| 494 |
+
"normalized": false,
|
| 495 |
+
"rstrip": false,
|
| 496 |
+
"single_word": false,
|
| 497 |
+
"special": true
|
| 498 |
+
},
|
| 499 |
+
"469": {
|
| 500 |
+
"content": "[SEN_43]",
|
| 501 |
+
"lstrip": false,
|
| 502 |
+
"normalized": false,
|
| 503 |
+
"rstrip": false,
|
| 504 |
+
"single_word": false,
|
| 505 |
+
"special": true
|
| 506 |
+
},
|
| 507 |
+
"470": {
|
| 508 |
+
"content": "[SEN_42]",
|
| 509 |
+
"lstrip": false,
|
| 510 |
+
"normalized": false,
|
| 511 |
+
"rstrip": false,
|
| 512 |
+
"single_word": false,
|
| 513 |
+
"special": true
|
| 514 |
+
},
|
| 515 |
+
"471": {
|
| 516 |
+
"content": "[SEN_41]",
|
| 517 |
+
"lstrip": false,
|
| 518 |
+
"normalized": false,
|
| 519 |
+
"rstrip": false,
|
| 520 |
+
"single_word": false,
|
| 521 |
+
"special": true
|
| 522 |
+
},
|
| 523 |
+
"472": {
|
| 524 |
+
"content": "[SEN_40]",
|
| 525 |
+
"lstrip": false,
|
| 526 |
+
"normalized": false,
|
| 527 |
+
"rstrip": false,
|
| 528 |
+
"single_word": false,
|
| 529 |
+
"special": true
|
| 530 |
+
},
|
| 531 |
+
"473": {
|
| 532 |
+
"content": "[SEN_39]",
|
| 533 |
+
"lstrip": false,
|
| 534 |
+
"normalized": false,
|
| 535 |
+
"rstrip": false,
|
| 536 |
+
"single_word": false,
|
| 537 |
+
"special": true
|
| 538 |
+
},
|
| 539 |
+
"474": {
|
| 540 |
+
"content": "[SEN_38]",
|
| 541 |
+
"lstrip": false,
|
| 542 |
+
"normalized": false,
|
| 543 |
+
"rstrip": false,
|
| 544 |
+
"single_word": false,
|
| 545 |
+
"special": true
|
| 546 |
+
},
|
| 547 |
+
"475": {
|
| 548 |
+
"content": "[SEN_37]",
|
| 549 |
+
"lstrip": false,
|
| 550 |
+
"normalized": false,
|
| 551 |
+
"rstrip": false,
|
| 552 |
+
"single_word": false,
|
| 553 |
+
"special": true
|
| 554 |
+
},
|
| 555 |
+
"476": {
|
| 556 |
+
"content": "[SEN_36]",
|
| 557 |
+
"lstrip": false,
|
| 558 |
+
"normalized": false,
|
| 559 |
+
"rstrip": false,
|
| 560 |
+
"single_word": false,
|
| 561 |
+
"special": true
|
| 562 |
+
},
|
| 563 |
+
"477": {
|
| 564 |
+
"content": "[SEN_35]",
|
| 565 |
+
"lstrip": false,
|
| 566 |
+
"normalized": false,
|
| 567 |
+
"rstrip": false,
|
| 568 |
+
"single_word": false,
|
| 569 |
+
"special": true
|
| 570 |
+
},
|
| 571 |
+
"478": {
|
| 572 |
+
"content": "[SEN_34]",
|
| 573 |
+
"lstrip": false,
|
| 574 |
+
"normalized": false,
|
| 575 |
+
"rstrip": false,
|
| 576 |
+
"single_word": false,
|
| 577 |
+
"special": true
|
| 578 |
+
},
|
| 579 |
+
"479": {
|
| 580 |
+
"content": "[SEN_33]",
|
| 581 |
+
"lstrip": false,
|
| 582 |
+
"normalized": false,
|
| 583 |
+
"rstrip": false,
|
| 584 |
+
"single_word": false,
|
| 585 |
+
"special": true
|
| 586 |
+
},
|
| 587 |
+
"480": {
|
| 588 |
+
"content": "[SEN_32]",
|
| 589 |
+
"lstrip": false,
|
| 590 |
+
"normalized": false,
|
| 591 |
+
"rstrip": false,
|
| 592 |
+
"single_word": false,
|
| 593 |
+
"special": true
|
| 594 |
+
},
|
| 595 |
+
"481": {
|
| 596 |
+
"content": "[SEN_31]",
|
| 597 |
+
"lstrip": false,
|
| 598 |
+
"normalized": false,
|
| 599 |
+
"rstrip": false,
|
| 600 |
+
"single_word": false,
|
| 601 |
+
"special": true
|
| 602 |
+
},
|
| 603 |
+
"482": {
|
| 604 |
+
"content": "[SEN_30]",
|
| 605 |
+
"lstrip": false,
|
| 606 |
+
"normalized": false,
|
| 607 |
+
"rstrip": false,
|
| 608 |
+
"single_word": false,
|
| 609 |
+
"special": true
|
| 610 |
+
},
|
| 611 |
+
"483": {
|
| 612 |
+
"content": "[SEN_29]",
|
| 613 |
+
"lstrip": false,
|
| 614 |
+
"normalized": false,
|
| 615 |
+
"rstrip": false,
|
| 616 |
+
"single_word": false,
|
| 617 |
+
"special": true
|
| 618 |
+
},
|
| 619 |
+
"484": {
|
| 620 |
+
"content": "[SEN_28]",
|
| 621 |
+
"lstrip": false,
|
| 622 |
+
"normalized": false,
|
| 623 |
+
"rstrip": false,
|
| 624 |
+
"single_word": false,
|
| 625 |
+
"special": true
|
| 626 |
+
},
|
| 627 |
+
"485": {
|
| 628 |
+
"content": "[SEN_27]",
|
| 629 |
+
"lstrip": false,
|
| 630 |
+
"normalized": false,
|
| 631 |
+
"rstrip": false,
|
| 632 |
+
"single_word": false,
|
| 633 |
+
"special": true
|
| 634 |
+
},
|
| 635 |
+
"486": {
|
| 636 |
+
"content": "[SEN_26]",
|
| 637 |
+
"lstrip": false,
|
| 638 |
+
"normalized": false,
|
| 639 |
+
"rstrip": false,
|
| 640 |
+
"single_word": false,
|
| 641 |
+
"special": true
|
| 642 |
+
},
|
| 643 |
+
"487": {
|
| 644 |
+
"content": "[SEN_25]",
|
| 645 |
+
"lstrip": false,
|
| 646 |
+
"normalized": false,
|
| 647 |
+
"rstrip": false,
|
| 648 |
+
"single_word": false,
|
| 649 |
+
"special": true
|
| 650 |
+
},
|
| 651 |
+
"488": {
|
| 652 |
+
"content": "[SEN_24]",
|
| 653 |
+
"lstrip": false,
|
| 654 |
+
"normalized": false,
|
| 655 |
+
"rstrip": false,
|
| 656 |
+
"single_word": false,
|
| 657 |
+
"special": true
|
| 658 |
+
},
|
| 659 |
+
"489": {
|
| 660 |
+
"content": "[SEN_23]",
|
| 661 |
+
"lstrip": false,
|
| 662 |
+
"normalized": false,
|
| 663 |
+
"rstrip": false,
|
| 664 |
+
"single_word": false,
|
| 665 |
+
"special": true
|
| 666 |
+
},
|
| 667 |
+
"490": {
|
| 668 |
+
"content": "[SEN_22]",
|
| 669 |
+
"lstrip": false,
|
| 670 |
+
"normalized": false,
|
| 671 |
+
"rstrip": false,
|
| 672 |
+
"single_word": false,
|
| 673 |
+
"special": true
|
| 674 |
+
},
|
| 675 |
+
"491": {
|
| 676 |
+
"content": "[SEN_21]",
|
| 677 |
+
"lstrip": false,
|
| 678 |
+
"normalized": false,
|
| 679 |
+
"rstrip": false,
|
| 680 |
+
"single_word": false,
|
| 681 |
+
"special": true
|
| 682 |
+
},
|
| 683 |
+
"492": {
|
| 684 |
+
"content": "[SEN_20]",
|
| 685 |
+
"lstrip": false,
|
| 686 |
+
"normalized": false,
|
| 687 |
+
"rstrip": false,
|
| 688 |
+
"single_word": false,
|
| 689 |
+
"special": true
|
| 690 |
+
},
|
| 691 |
+
"493": {
|
| 692 |
+
"content": "[SEN_19]",
|
| 693 |
+
"lstrip": false,
|
| 694 |
+
"normalized": false,
|
| 695 |
+
"rstrip": false,
|
| 696 |
+
"single_word": false,
|
| 697 |
+
"special": true
|
| 698 |
+
},
|
| 699 |
+
"494": {
|
| 700 |
+
"content": "[SEN_18]",
|
| 701 |
+
"lstrip": false,
|
| 702 |
+
"normalized": false,
|
| 703 |
+
"rstrip": false,
|
| 704 |
+
"single_word": false,
|
| 705 |
+
"special": true
|
| 706 |
+
},
|
| 707 |
+
"495": {
|
| 708 |
+
"content": "[SEN_17]",
|
| 709 |
+
"lstrip": false,
|
| 710 |
+
"normalized": false,
|
| 711 |
+
"rstrip": false,
|
| 712 |
+
"single_word": false,
|
| 713 |
+
"special": true
|
| 714 |
+
},
|
| 715 |
+
"496": {
|
| 716 |
+
"content": "[SEN_16]",
|
| 717 |
+
"lstrip": false,
|
| 718 |
+
"normalized": false,
|
| 719 |
+
"rstrip": false,
|
| 720 |
+
"single_word": false,
|
| 721 |
+
"special": true
|
| 722 |
+
},
|
| 723 |
+
"497": {
|
| 724 |
+
"content": "[SEN_15]",
|
| 725 |
+
"lstrip": false,
|
| 726 |
+
"normalized": false,
|
| 727 |
+
"rstrip": false,
|
| 728 |
+
"single_word": false,
|
| 729 |
+
"special": true
|
| 730 |
+
},
|
| 731 |
+
"498": {
|
| 732 |
+
"content": "[SEN_14]",
|
| 733 |
+
"lstrip": false,
|
| 734 |
+
"normalized": false,
|
| 735 |
+
"rstrip": false,
|
| 736 |
+
"single_word": false,
|
| 737 |
+
"special": true
|
| 738 |
+
},
|
| 739 |
+
"499": {
|
| 740 |
+
"content": "[SEN_13]",
|
| 741 |
+
"lstrip": false,
|
| 742 |
+
"normalized": false,
|
| 743 |
+
"rstrip": false,
|
| 744 |
+
"single_word": false,
|
| 745 |
+
"special": true
|
| 746 |
+
},
|
| 747 |
+
"500": {
|
| 748 |
+
"content": "[SEN_12]",
|
| 749 |
+
"lstrip": false,
|
| 750 |
+
"normalized": false,
|
| 751 |
+
"rstrip": false,
|
| 752 |
+
"single_word": false,
|
| 753 |
+
"special": true
|
| 754 |
+
},
|
| 755 |
+
"501": {
|
| 756 |
+
"content": "[SEN_11]",
|
| 757 |
+
"lstrip": false,
|
| 758 |
+
"normalized": false,
|
| 759 |
+
"rstrip": false,
|
| 760 |
+
"single_word": false,
|
| 761 |
+
"special": true
|
| 762 |
+
},
|
| 763 |
+
"502": {
|
| 764 |
+
"content": "[SEN_10]",
|
| 765 |
+
"lstrip": false,
|
| 766 |
+
"normalized": false,
|
| 767 |
+
"rstrip": false,
|
| 768 |
+
"single_word": false,
|
| 769 |
+
"special": true
|
| 770 |
+
},
|
| 771 |
+
"503": {
|
| 772 |
+
"content": "[SEN_9]",
|
| 773 |
+
"lstrip": false,
|
| 774 |
+
"normalized": false,
|
| 775 |
+
"rstrip": false,
|
| 776 |
+
"single_word": false,
|
| 777 |
+
"special": true
|
| 778 |
+
},
|
| 779 |
+
"504": {
|
| 780 |
+
"content": "[SEN_8]",
|
| 781 |
+
"lstrip": false,
|
| 782 |
+
"normalized": false,
|
| 783 |
+
"rstrip": false,
|
| 784 |
+
"single_word": false,
|
| 785 |
+
"special": true
|
| 786 |
+
},
|
| 787 |
+
"505": {
|
| 788 |
+
"content": "[SEN_7]",
|
| 789 |
+
"lstrip": false,
|
| 790 |
+
"normalized": false,
|
| 791 |
+
"rstrip": false,
|
| 792 |
+
"single_word": false,
|
| 793 |
+
"special": true
|
| 794 |
+
},
|
| 795 |
+
"506": {
|
| 796 |
+
"content": "[SEN_6]",
|
| 797 |
+
"lstrip": false,
|
| 798 |
+
"normalized": false,
|
| 799 |
+
"rstrip": false,
|
| 800 |
+
"single_word": false,
|
| 801 |
+
"special": true
|
| 802 |
+
},
|
| 803 |
+
"507": {
|
| 804 |
+
"content": "[SEN_5]",
|
| 805 |
+
"lstrip": false,
|
| 806 |
+
"normalized": false,
|
| 807 |
+
"rstrip": false,
|
| 808 |
+
"single_word": false,
|
| 809 |
+
"special": true
|
| 810 |
+
},
|
| 811 |
+
"508": {
|
| 812 |
+
"content": "[SEN_4]",
|
| 813 |
+
"lstrip": false,
|
| 814 |
+
"normalized": false,
|
| 815 |
+
"rstrip": false,
|
| 816 |
+
"single_word": false,
|
| 817 |
+
"special": true
|
| 818 |
+
},
|
| 819 |
+
"509": {
|
| 820 |
+
"content": "[SEN_3]",
|
| 821 |
+
"lstrip": false,
|
| 822 |
+
"normalized": false,
|
| 823 |
+
"rstrip": false,
|
| 824 |
+
"single_word": false,
|
| 825 |
+
"special": true
|
| 826 |
+
},
|
| 827 |
+
"510": {
|
| 828 |
+
"content": "[SEN_2]",
|
| 829 |
+
"lstrip": false,
|
| 830 |
+
"normalized": false,
|
| 831 |
+
"rstrip": false,
|
| 832 |
+
"single_word": false,
|
| 833 |
+
"special": true
|
| 834 |
+
},
|
| 835 |
+
"511": {
|
| 836 |
+
"content": "[SEN_1]",
|
| 837 |
+
"lstrip": false,
|
| 838 |
+
"normalized": false,
|
| 839 |
+
"rstrip": false,
|
| 840 |
+
"single_word": false,
|
| 841 |
+
"special": true
|
| 842 |
+
}
|
| 843 |
+
},
|
| 844 |
+
"clean_up_tokenization_spaces": true,
|
| 845 |
+
"cls_token": "[CLS]",
|
| 846 |
+
"eos_token": "[SEP]",
|
| 847 |
+
"extra_special_tokens": {},
|
| 848 |
+
"meta_token": "[META]",
|
| 849 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 850 |
+
"pad_token": "[PAD]",
|
| 851 |
+
"sep_token": "[SEP]",
|
| 852 |
+
"tokenizer_class": "PreTrainedTokenizer",
|
| 853 |
+
"unk_token": "[UNK]"
|
| 854 |
+
}
|