Upload tokenizer
Browse files- special_tokens_map.json +7 -1
- tokenizer.json +3 -2
- tokenizer_config.json +43 -2
special_tokens_map.json
CHANGED
|
@@ -5,5 +5,11 @@
|
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
| 8 |
-
"unk_token":
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 9 |
}
|
|
|
|
| 5 |
"mask_token": "[MASK]",
|
| 6 |
"pad_token": "[PAD]",
|
| 7 |
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": {
|
| 9 |
+
"content": "[UNK]",
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"normalized": true,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
}
|
| 15 |
}
|
tokenizer.json
CHANGED
|
@@ -50,7 +50,7 @@
|
|
| 50 |
"single_word": false,
|
| 51 |
"lstrip": false,
|
| 52 |
"rstrip": false,
|
| 53 |
-
"normalized":
|
| 54 |
"special": true
|
| 55 |
},
|
| 56 |
{
|
|
@@ -512178,6 +512178,7 @@
|
|
| 512178 |
"얻",
|
| 512179 |
-24.518644332885742
|
| 512180 |
]
|
| 512181 |
-
]
|
|
|
|
| 512182 |
}
|
| 512183 |
}
|
|
|
|
| 50 |
"single_word": false,
|
| 51 |
"lstrip": false,
|
| 52 |
"rstrip": false,
|
| 53 |
+
"normalized": true,
|
| 54 |
"special": true
|
| 55 |
},
|
| 56 |
{
|
|
|
|
| 512178 |
"얻",
|
| 512179 |
-24.518644332885742
|
| 512180 |
]
|
| 512181 |
+
],
|
| 512182 |
+
"byte_fallback": false
|
| 512183 |
}
|
| 512184 |
}
|
tokenizer_config.json
CHANGED
|
@@ -1,15 +1,56 @@
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"bos_token": "[CLS]",
|
|
|
|
| 3 |
"cls_token": "[CLS]",
|
| 4 |
"do_lower_case": false,
|
| 5 |
"eos_token": "[SEP]",
|
| 6 |
"mask_token": "[MASK]",
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
-
"name_or_path": "microsoft/deberta-v3-base",
|
| 9 |
"pad_token": "[PAD]",
|
| 10 |
"sep_token": "[SEP]",
|
| 11 |
"sp_model_kwargs": {},
|
| 12 |
-
"special_tokens_map_file": null,
|
| 13 |
"split_by_punct": false,
|
| 14 |
"tokenizer_class": "DebertaV2Tokenizer",
|
| 15 |
"unk_token": "[UNK]",
|
|
|
|
| 1 |
{
|
| 2 |
+
"added_tokens_decoder": {
|
| 3 |
+
"0": {
|
| 4 |
+
"content": "[PAD]",
|
| 5 |
+
"lstrip": false,
|
| 6 |
+
"normalized": false,
|
| 7 |
+
"rstrip": false,
|
| 8 |
+
"single_word": false,
|
| 9 |
+
"special": true
|
| 10 |
+
},
|
| 11 |
+
"1": {
|
| 12 |
+
"content": "[CLS]",
|
| 13 |
+
"lstrip": false,
|
| 14 |
+
"normalized": false,
|
| 15 |
+
"rstrip": false,
|
| 16 |
+
"single_word": false,
|
| 17 |
+
"special": true
|
| 18 |
+
},
|
| 19 |
+
"2": {
|
| 20 |
+
"content": "[SEP]",
|
| 21 |
+
"lstrip": false,
|
| 22 |
+
"normalized": false,
|
| 23 |
+
"rstrip": false,
|
| 24 |
+
"single_word": false,
|
| 25 |
+
"special": true
|
| 26 |
+
},
|
| 27 |
+
"3": {
|
| 28 |
+
"content": "[UNK]",
|
| 29 |
+
"lstrip": false,
|
| 30 |
+
"normalized": true,
|
| 31 |
+
"rstrip": false,
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"special": true
|
| 34 |
+
},
|
| 35 |
+
"128000": {
|
| 36 |
+
"content": "[MASK]",
|
| 37 |
+
"lstrip": false,
|
| 38 |
+
"normalized": false,
|
| 39 |
+
"rstrip": false,
|
| 40 |
+
"single_word": false,
|
| 41 |
+
"special": true
|
| 42 |
+
}
|
| 43 |
+
},
|
| 44 |
"bos_token": "[CLS]",
|
| 45 |
+
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "[CLS]",
|
| 47 |
"do_lower_case": false,
|
| 48 |
"eos_token": "[SEP]",
|
| 49 |
"mask_token": "[MASK]",
|
| 50 |
"model_max_length": 1000000000000000019884624838656,
|
|
|
|
| 51 |
"pad_token": "[PAD]",
|
| 52 |
"sep_token": "[SEP]",
|
| 53 |
"sp_model_kwargs": {},
|
|
|
|
| 54 |
"split_by_punct": false,
|
| 55 |
"tokenizer_class": "DebertaV2Tokenizer",
|
| 56 |
"unk_token": "[UNK]",
|