EslamAhmed
commited on
Commit
•
976e2bd
1
Parent(s):
2c4f2ed
Upload tokenizer
Browse files- special_tokens_map.json +7 -0
- tokenizer_config.json +19 -0
- vocab.txt +0 -0
special_tokens_map.json
ADDED
@@ -0,0 +1,7 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"mask_token": "[MASK]",
|
4 |
+
"pad_token": "[PAD]",
|
5 |
+
"sep_token": "[SEP]",
|
6 |
+
"unk_token": "[UNK]"
|
7 |
+
}
|
tokenizer_config.json
ADDED
@@ -0,0 +1,19 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"cls_token": "[CLS]",
|
3 |
+
"do_basic_tokenize": true,
|
4 |
+
"do_lower_case": true,
|
5 |
+
"labels": false,
|
6 |
+
"mask_token": "[MASK]",
|
7 |
+
"max_len": 128,
|
8 |
+
"model_max_length": 128,
|
9 |
+
"name_or_path": "tokenizer_loc",
|
10 |
+
"never_split": null,
|
11 |
+
"pad_token": "[PAD]",
|
12 |
+
"sep_token": "[SEP]",
|
13 |
+
"special_tokens_map_file": null,
|
14 |
+
"strip_accents": null,
|
15 |
+
"tokenize_chinese_chars": true,
|
16 |
+
"tokenizer_class": "BertTokenizer",
|
17 |
+
"unk_token": "[UNK]",
|
18 |
+
"use_fast": true
|
19 |
+
}
|
vocab.txt
ADDED
The diff for this file is too large to render.
See raw diff
|
|