Upload tokenizer
Browse files- tokenizer_config.json +3 -45
tokenizer_config.json
CHANGED
|
@@ -1,58 +1,16 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
-
"
|
| 4 |
-
"0": {
|
| 5 |
-
"content": "<s>",
|
| 6 |
-
"lstrip": false,
|
| 7 |
-
"normalized": true,
|
| 8 |
-
"rstrip": false,
|
| 9 |
-
"single_word": false,
|
| 10 |
-
"special": true
|
| 11 |
-
},
|
| 12 |
-
"1": {
|
| 13 |
-
"content": "<pad>",
|
| 14 |
-
"lstrip": false,
|
| 15 |
-
"normalized": true,
|
| 16 |
-
"rstrip": false,
|
| 17 |
-
"single_word": false,
|
| 18 |
-
"special": true
|
| 19 |
-
},
|
| 20 |
-
"2": {
|
| 21 |
-
"content": "</s>",
|
| 22 |
-
"lstrip": false,
|
| 23 |
-
"normalized": true,
|
| 24 |
-
"rstrip": false,
|
| 25 |
-
"single_word": false,
|
| 26 |
-
"special": true
|
| 27 |
-
},
|
| 28 |
-
"3": {
|
| 29 |
-
"content": "<unk>",
|
| 30 |
-
"lstrip": false,
|
| 31 |
-
"normalized": true,
|
| 32 |
-
"rstrip": false,
|
| 33 |
-
"single_word": false,
|
| 34 |
-
"special": true
|
| 35 |
-
},
|
| 36 |
-
"50264": {
|
| 37 |
-
"content": "<mask>",
|
| 38 |
-
"lstrip": true,
|
| 39 |
-
"normalized": true,
|
| 40 |
-
"rstrip": false,
|
| 41 |
-
"single_word": false,
|
| 42 |
-
"special": true
|
| 43 |
-
}
|
| 44 |
-
},
|
| 45 |
"bos_token": "<s>",
|
| 46 |
-
"clean_up_tokenization_spaces": false,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
| 49 |
"errors": "replace",
|
| 50 |
-
"
|
| 51 |
"mask_token": "<mask>",
|
| 52 |
"model_max_length": 1000000000000000019884624838656,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
"sep_token": "</s>",
|
| 55 |
-
"tokenizer_class": "
|
| 56 |
"trim_offsets": true,
|
| 57 |
"unk_token": "<unk>"
|
| 58 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
+
"backend": "tokenizers",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
"bos_token": "<s>",
|
|
|
|
| 5 |
"cls_token": "<s>",
|
| 6 |
"eos_token": "</s>",
|
| 7 |
"errors": "replace",
|
| 8 |
+
"is_local": false,
|
| 9 |
"mask_token": "<mask>",
|
| 10 |
"model_max_length": 1000000000000000019884624838656,
|
| 11 |
"pad_token": "<pad>",
|
| 12 |
"sep_token": "</s>",
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
"trim_offsets": true,
|
| 15 |
"unk_token": "<unk>"
|
| 16 |
}
|