Commit
•
58b1f08
1
Parent(s):
8e3db8d
Upload 3 files
Browse files- special_tokens_map.json +1 -0
- tokenizer_config.json +12 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1 @@
|
|
|
|
|
|
|
| 1 |
+
{"unk_token": "[UNK]", "sep_token": "[SEP]", "pad_token": "[PAD]", "cls_token": "[CLS]", "mask_token": "[MASK]"}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,12 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"tokenizer_class": "sudachitra.tokenization_electra_sudachipy.ElectraSudachipyTokenizer",
|
| 3 |
+
"do_lower_case": false,
|
| 4 |
+
"do_word_tokenize": true,
|
| 5 |
+
"do_subword_tokenize": true,
|
| 6 |
+
"word_tokenizer_type": "sudachipy",
|
| 7 |
+
"word_form_type": "dictionary_and_surface",
|
| 8 |
+
"subword_tokenizer_type": "wordpiece",
|
| 9 |
+
"model_max_length": 512,
|
| 10 |
+
"sudachipy_kwargs": {"split_mode":"A","dict_type":"core"}
|
| 11 |
+
}
|
| 12 |
+
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|