Upload tokenizer
Browse files- special_tokens_map.json +10 -0
- tokenizer_config.json +27 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[EMPTY]"
|
| 4 |
+
],
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"unk_token": "[UNK]"
|
| 10 |
+
}
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[EMPTY]"
|
| 4 |
+
],
|
| 5 |
+
"cell_trim_length": -1,
|
| 6 |
+
"clean_up_tokenization_spaces": true,
|
| 7 |
+
"cls_token": "[CLS]",
|
| 8 |
+
"do_basic_tokenize": true,
|
| 9 |
+
"do_lower_case": true,
|
| 10 |
+
"drop_rows_to_fit": false,
|
| 11 |
+
"empty_token": "[EMPTY]",
|
| 12 |
+
"mask_token": "[MASK]",
|
| 13 |
+
"max_column_id": null,
|
| 14 |
+
"max_question_length": null,
|
| 15 |
+
"max_row_id": null,
|
| 16 |
+
"min_question_length": null,
|
| 17 |
+
"model_max_length": 512,
|
| 18 |
+
"never_split": null,
|
| 19 |
+
"pad_token": "[PAD]",
|
| 20 |
+
"sep_token": "[SEP]",
|
| 21 |
+
"strip_accents": null,
|
| 22 |
+
"strip_column_names": false,
|
| 23 |
+
"tokenize_chinese_chars": true,
|
| 24 |
+
"tokenizer_class": "TapasTokenizer",
|
| 25 |
+
"unk_token": "[UNK]",
|
| 26 |
+
"update_answer_coordinates": false
|
| 27 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|