Upload tokenizer
Browse files- tokenizer_config.json +1 -2
tokenizer_config.json
CHANGED
|
@@ -1,14 +1,13 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"do_basic_tokenize": true,
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
-
"name_or_path": "indobenchmark/indobert-base-p1",
|
| 8 |
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
-
"special_tokens_map_file": "/root/.cache/huggingface/hub/models--indobenchmark--indobert-base-p1/snapshots/c2cd0b51ddce6580eb35263b39b0a1e5fb0a39e2/special_tokens_map.json",
|
| 12 |
"strip_accents": null,
|
| 13 |
"tokenize_chinese_chars": true,
|
| 14 |
"tokenizer_class": "BertTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_basic_tokenize": true,
|
| 5 |
"do_lower_case": true,
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 8 |
"never_split": null,
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
|
|
|
| 11 |
"strip_accents": null,
|
| 12 |
"tokenize_chinese_chars": true,
|
| 13 |
"tokenizer_class": "BertTokenizer",
|