Upload tokenizer
Browse files- tokenizer.json +2 -14
- tokenizer_config.json +7 -0
tokenizer.json
CHANGED
|
@@ -1,19 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"truncation":
|
| 4 |
-
|
| 5 |
-
"max_length": 500,
|
| 6 |
-
"strategy": "LongestFirst",
|
| 7 |
-
"stride": 0
|
| 8 |
-
},
|
| 9 |
-
"padding": {
|
| 10 |
-
"strategy": "BatchLongest",
|
| 11 |
-
"direction": "Right",
|
| 12 |
-
"pad_to_multiple_of": null,
|
| 13 |
-
"pad_id": 3,
|
| 14 |
-
"pad_type_id": 0,
|
| 15 |
-
"pad_token": "[PAD]"
|
| 16 |
-
},
|
| 17 |
"added_tokens": [
|
| 18 |
{
|
| 19 |
"id": 0,
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 5 |
"added_tokens": [
|
| 6 |
{
|
| 7 |
"id": 0,
|
tokenizer_config.json
CHANGED
|
@@ -44,9 +44,16 @@
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"mask_token": "[MASK]",
|
|
|
|
| 47 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 48 |
"pad_token": "[PAD]",
|
|
|
|
|
|
|
| 49 |
"sep_token": "[SEP]",
|
|
|
|
| 50 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
|
|
|
| 51 |
"unk_token": "[UNK]"
|
| 52 |
}
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
"cls_token": "[CLS]",
|
| 46 |
"mask_token": "[MASK]",
|
| 47 |
+
"max_length": 500,
|
| 48 |
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
+
"pad_to_multiple_of": null,
|
| 50 |
"pad_token": "[PAD]",
|
| 51 |
+
"pad_token_type_id": 0,
|
| 52 |
+
"padding_side": "right",
|
| 53 |
"sep_token": "[SEP]",
|
| 54 |
+
"stride": 0,
|
| 55 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 56 |
+
"truncation_side": "right",
|
| 57 |
+
"truncation_strategy": "longest_first",
|
| 58 |
"unk_token": "[UNK]"
|
| 59 |
}
|