Upload tokenizer
Browse files- special_tokens_map.json +9 -1
- tokenizer.json +0 -0
- tokenizer_config.json +5 -3
- vocab.txt +0 -0
special_tokens_map.json
CHANGED
|
@@ -1,6 +1,14 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"pad_token": "[PAD]",
|
| 5 |
"sep_token": "[SEP]",
|
| 6 |
"unk_token": "[UNK]"
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "[SEP]",
|
| 5 |
+
"mask_token": {
|
| 6 |
+
"content": "[MASK]",
|
| 7 |
+
"lstrip": true,
|
| 8 |
+
"normalized": false,
|
| 9 |
+
"rstrip": false,
|
| 10 |
+
"single_word": false
|
| 11 |
+
},
|
| 12 |
"pad_token": "[PAD]",
|
| 13 |
"sep_token": "[SEP]",
|
| 14 |
"unk_token": "[UNK]"
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,15 +1,17 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_basic_tokenize": true,
|
| 5 |
-
"do_lower_case":
|
|
|
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
-
"model_max_length":
|
| 8 |
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
"strip_accents": null,
|
| 12 |
"tokenize_chinese_chars": true,
|
| 13 |
-
"tokenizer_class": "
|
| 14 |
"unk_token": "[UNK]"
|
| 15 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "[CLS]",
|
| 3 |
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "[CLS]",
|
| 5 |
"do_basic_tokenize": true,
|
| 6 |
+
"do_lower_case": false,
|
| 7 |
+
"eos_token": "[SEP]",
|
| 8 |
"mask_token": "[MASK]",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
"never_split": null,
|
| 11 |
"pad_token": "[PAD]",
|
| 12 |
"sep_token": "[SEP]",
|
| 13 |
"strip_accents": null,
|
| 14 |
"tokenize_chinese_chars": true,
|
| 15 |
+
"tokenizer_class": "MPNetTokenizer",
|
| 16 |
"unk_token": "[UNK]"
|
| 17 |
}
|
vocab.txt
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|