Upload tokenizer
Browse files- added_tokens.json +3 -0
- special_tokens_map.json +10 -0
- tokenizer.json +0 -0
- tokenizer_config.json +17 -0
- vocab.txt +0 -0
added_tokens.json
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"[2024-02-29 10:52:00+09:00]": 20000
|
| 3 |
+
}
|
special_tokens_map.json
ADDED
|
@@ -0,0 +1,10 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"additional_special_tokens": [
|
| 3 |
+
"[2024-02-29 10:52:00+09:00]"
|
| 4 |
+
],
|
| 5 |
+
"cls_token": "[CLS]",
|
| 6 |
+
"mask_token": "[MASK]",
|
| 7 |
+
"pad_token": "[PAD]",
|
| 8 |
+
"sep_token": "[SEP]",
|
| 9 |
+
"unk_token": "[UNK]"
|
| 10 |
+
}
|
tokenizer.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
ADDED
|
@@ -0,0 +1,17 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 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": 512,
|
| 8 |
+
"name_or_path": "tkcho/commerce-tokenizer-kr",
|
| 9 |
+
"never_split": null,
|
| 10 |
+
"pad_token": "[PAD]",
|
| 11 |
+
"sep_token": "[SEP]",
|
| 12 |
+
"special_tokens_map_file": "/home/pjy/.cache/huggingface/hub/models--tkcho--commerce-tokenizer-kr/snapshots/44d34a84e4525678a94c3ebc09dfd796e84e0c53/special_tokens_map.json",
|
| 13 |
+
"strip_accents": false,
|
| 14 |
+
"tokenize_chinese_chars": true,
|
| 15 |
+
"tokenizer_class": "BertTokenizer",
|
| 16 |
+
"unk_token": "[UNK]"
|
| 17 |
+
}
|
vocab.txt
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|