Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer_config.json +8 -1
special_tokens_map.json
CHANGED
|
@@ -13,7 +13,13 @@
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
-
"pad_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 17 |
"sep_token": {
|
| 18 |
"content": "[SEP]",
|
| 19 |
"lstrip": false,
|
|
|
|
| 13 |
"rstrip": false,
|
| 14 |
"single_word": false
|
| 15 |
},
|
| 16 |
+
"pad_token": {
|
| 17 |
+
"content": "[MASK]",
|
| 18 |
+
"lstrip": true,
|
| 19 |
+
"normalized": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"single_word": false
|
| 22 |
+
},
|
| 23 |
"sep_token": {
|
| 24 |
"content": "[SEP]",
|
| 25 |
"lstrip": false,
|
tokenizer_config.json
CHANGED
|
@@ -949,13 +949,20 @@
|
|
| 949 |
"cls_token": "[CLS]",
|
| 950 |
"extra_special_tokens": {},
|
| 951 |
"mask_token": "[MASK]",
|
|
|
|
| 952 |
"model_input_names": [
|
| 953 |
"input_ids",
|
| 954 |
"attention_mask"
|
| 955 |
],
|
| 956 |
-
"model_max_length":
|
|
|
|
| 957 |
"pad_token": "[MASK]",
|
|
|
|
|
|
|
| 958 |
"sep_token": "[SEP]",
|
|
|
|
| 959 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
|
|
|
|
|
|
| 960 |
"unk_token": "[UNK]"
|
| 961 |
}
|
|
|
|
| 949 |
"cls_token": "[CLS]",
|
| 950 |
"extra_special_tokens": {},
|
| 951 |
"mask_token": "[MASK]",
|
| 952 |
+
"max_length": 179,
|
| 953 |
"model_input_names": [
|
| 954 |
"input_ids",
|
| 955 |
"attention_mask"
|
| 956 |
],
|
| 957 |
+
"model_max_length": 179,
|
| 958 |
+
"pad_to_multiple_of": null,
|
| 959 |
"pad_token": "[MASK]",
|
| 960 |
+
"pad_token_type_id": 0,
|
| 961 |
+
"padding_side": "right",
|
| 962 |
"sep_token": "[SEP]",
|
| 963 |
+
"stride": 0,
|
| 964 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 965 |
+
"truncation_side": "right",
|
| 966 |
+
"truncation_strategy": "longest_first",
|
| 967 |
"unk_token": "[UNK]"
|
| 968 |
}
|