Upload tokenizer
Browse files- special_tokens_map.json +1 -37
- tokenizer.json +0 -0
- tokenizer_config.json +25 -6
special_tokens_map.json
CHANGED
|
@@ -1,37 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"cls_token": {
|
| 3 |
-
"content": "[CLS]",
|
| 4 |
-
"lstrip": false,
|
| 5 |
-
"normalized": false,
|
| 6 |
-
"rstrip": false,
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"mask_token": {
|
| 10 |
-
"content": "[MASK]",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"pad_token": {
|
| 17 |
-
"content": "[PAD]",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"sep_token": {
|
| 24 |
-
"content": "[SEP]",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
},
|
| 30 |
-
"unk_token": {
|
| 31 |
-
"content": "[UNK]",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
}
|
| 37 |
-
}
|
|
|
|
| 1 |
+
{}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -39,14 +39,33 @@
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"clean_up_tokenization_spaces": true,
|
| 45 |
-
"cls_token": "[CLS]",
|
| 46 |
-
"mask_token": "[MASK]",
|
| 47 |
"model_max_length": 1000000000000000019884624838656,
|
| 48 |
-
"
|
| 49 |
-
"sep_token": "[SEP]",
|
| 50 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 51 |
-
"unk_token": "[UNK]"
|
| 52 |
}
|
|
|
|
| 39 |
"rstrip": false,
|
| 40 |
"single_word": false,
|
| 41 |
"special": true
|
| 42 |
+
},
|
| 43 |
+
"5": {
|
| 44 |
+
"content": "[DIALECT_LARI]",
|
| 45 |
+
"lstrip": false,
|
| 46 |
+
"normalized": false,
|
| 47 |
+
"rstrip": false,
|
| 48 |
+
"single_word": false,
|
| 49 |
+
"special": true
|
| 50 |
+
},
|
| 51 |
+
"6": {
|
| 52 |
+
"content": "[DIALECT_MUNUKUTUBA]",
|
| 53 |
+
"lstrip": false,
|
| 54 |
+
"normalized": false,
|
| 55 |
+
"rstrip": false,
|
| 56 |
+
"single_word": false,
|
| 57 |
+
"special": true
|
| 58 |
+
},
|
| 59 |
+
"7": {
|
| 60 |
+
"content": "[DIALECT_KISINGANI]",
|
| 61 |
+
"lstrip": false,
|
| 62 |
+
"normalized": false,
|
| 63 |
+
"rstrip": false,
|
| 64 |
+
"single_word": false,
|
| 65 |
+
"special": true
|
| 66 |
}
|
| 67 |
},
|
| 68 |
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
| 69 |
"model_max_length": 1000000000000000019884624838656,
|
| 70 |
+
"tokenizer_class": "PreTrainedTokenizerFast"
|
|
|
|
|
|
|
|
|
|
| 71 |
}
|