Upload tokenizer
Browse files- tokenizer.json +2 -16
- tokenizer_config.json +1 -2
tokenizer.json
CHANGED
@@ -1,21 +1,7 @@
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
-
"truncation":
|
4 |
-
|
5 |
-
"max_length": 160,
|
6 |
-
"strategy": "LongestFirst",
|
7 |
-
"stride": 0
|
8 |
-
},
|
9 |
-
"padding": {
|
10 |
-
"strategy": {
|
11 |
-
"Fixed": 160
|
12 |
-
},
|
13 |
-
"direction": "Right",
|
14 |
-
"pad_to_multiple_of": null,
|
15 |
-
"pad_id": 21,
|
16 |
-
"pad_type_id": 0,
|
17 |
-
"pad_token": "[PAD]"
|
18 |
-
},
|
19 |
"added_tokens": [
|
20 |
{
|
21 |
"id": 0,
|
|
|
1 |
{
|
2 |
"version": "1.0",
|
3 |
+
"truncation": null,
|
4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
5 |
"added_tokens": [
|
6 |
{
|
7 |
"id": 0,
|
tokenizer_config.json
CHANGED
@@ -1,14 +1,13 @@
|
|
1 |
{
|
|
|
2 |
"cls_token": "[CLS]",
|
3 |
"do_basic_tokenize": true,
|
4 |
"do_lower_case": false,
|
5 |
"mask_token": "[MASK]",
|
6 |
"model_max_length": 160,
|
7 |
-
"name_or_path": "ablang_tokenizer",
|
8 |
"never_split": null,
|
9 |
"pad_token": "[PAD]",
|
10 |
"sep_token": "[SEP]",
|
11 |
-
"special_tokens_map_file": null,
|
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": false,
|
6 |
"mask_token": "[MASK]",
|
7 |
"model_max_length": 160,
|
|
|
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",
|