Commit
•
5d80da4
1
Parent(s):
18f4ad7
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": 512,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": {
|
| 11 |
-
"Fixed": 512
|
| 12 |
-
},
|
| 13 |
-
"direction": "Right",
|
| 14 |
-
"pad_to_multiple_of": null,
|
| 15 |
-
"pad_id": 0,
|
| 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
|
@@ -1,12 +1,11 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"cls_token": "[CLS]",
|
| 3 |
"do_lower_case": true,
|
| 4 |
"mask_token": "[MASK]",
|
| 5 |
"model_max_length": 512,
|
| 6 |
-
"name_or_path": "distilbert-base-uncased",
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
| 9 |
-
"special_tokens_map_file": null,
|
| 10 |
"strip_accents": null,
|
| 11 |
"tokenize_chinese_chars": true,
|
| 12 |
"tokenizer_class": "DistilBertTokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
+
"clean_up_tokenization_spaces": true,
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": true,
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"model_max_length": 512,
|
|
|
|
| 7 |
"pad_token": "[PAD]",
|
| 8 |
"sep_token": "[SEP]",
|
|
|
|
| 9 |
"strip_accents": null,
|
| 10 |
"tokenize_chinese_chars": true,
|
| 11 |
"tokenizer_class": "DistilBertTokenizer",
|