Commit
•
2c6c6fc
1
Parent(s):
a480337
End of training
Browse files- added_tokens.json +31 -0
- special_tokens_map.json +7 -0
- tokenizer_config.json +16 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,31 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"''": 30522,
|
| 3 |
+
"``": 30523,
|
| 4 |
+
"fw": 30524,
|
| 5 |
+
"jjr": 30525,
|
| 6 |
+
"jjs": 30526,
|
| 7 |
+
"ls": 30527,
|
| 8 |
+
"nn": 30528,
|
| 9 |
+
"nnp": 30529,
|
| 10 |
+
"nnps": 30530,
|
| 11 |
+
"nns": 30531,
|
| 12 |
+
"nn|sym": 30532,
|
| 13 |
+
"pdt": 30533,
|
| 14 |
+
"pos": 30534,
|
| 15 |
+
"prp": 30535,
|
| 16 |
+
"prp$": 30536,
|
| 17 |
+
"rbr": 30537,
|
| 18 |
+
"rbs": 30538,
|
| 19 |
+
"rp": 30539,
|
| 20 |
+
"sym": 30540,
|
| 21 |
+
"vb": 30541,
|
| 22 |
+
"vbd": 30542,
|
| 23 |
+
"vbg": 30543,
|
| 24 |
+
"vbn": 30544,
|
| 25 |
+
"vbp": 30545,
|
| 26 |
+
"vbz": 30546,
|
| 27 |
+
"wdt": 30547,
|
| 28 |
+
"wp": 30548,
|
| 29 |
+
"wp$": 30549,
|
| 30 |
+
"wrb": 30550
|
| 31 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"mask_token": "[MASK]",
|
| 4 |
+
"pad_token": "[PAD]",
|
| 5 |
+
"sep_token": "[SEP]",
|
| 6 |
+
"unk_token": "[UNK]"
|
| 7 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,16 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"cls_token": "[CLS]",
|
| 3 |
+
"do_basic_tokenize": true,
|
| 4 |
+
"do_lower_case": true,
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"model_max_length": 512,
|
| 7 |
+
"name_or_path": "bert-base-uncased",
|
| 8 |
+
"never_split": null,
|
| 9 |
+
"pad_token": "[PAD]",
|
| 10 |
+
"sep_token": "[SEP]",
|
| 11 |
+
"special_tokens_map_file": null,
|
| 12 |
+
"strip_accents": null,
|
| 13 |
+
"tokenize_chinese_chars": true,
|
| 14 |
+
"tokenizer_class": "BertTokenizer",
|
| 15 |
+
"unk_token": "[UNK]"
|
| 16 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|