add tokenizer
Browse files- special_tokens_map.json +1 -15
- tokenizer.json +0 -0
- tokenizer_config.json +1 -16
special_tokens_map.json
CHANGED
|
@@ -1,15 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"bos_token": "<s>",
|
| 3 |
-
"cls_token": "<s>",
|
| 4 |
-
"eos_token": "</s>",
|
| 5 |
-
"mask_token": {
|
| 6 |
-
"content": "<mask>",
|
| 7 |
-
"lstrip": true,
|
| 8 |
-
"normalized": false,
|
| 9 |
-
"rstrip": false,
|
| 10 |
-
"single_word": false
|
| 11 |
-
},
|
| 12 |
-
"pad_token": "<pad>",
|
| 13 |
-
"sep_token": "</s>",
|
| 14 |
-
"unk_token": "<unk>"
|
| 15 |
-
}
|
|
|
|
| 1 |
+
{"bos_token": "<s>", "eos_token": "</s>", "unk_token": "<unk>", "sep_token": "</s>", "pad_token": "<pad>", "cls_token": "<s>", "mask_token": {"content": "<mask>", "single_word": false, "lstrip": true, "rstrip": false, "normalized": false}}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,16 +1 @@
|
|
| 1 |
-
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"bos_token": "<s>",
|
| 4 |
-
"cls_token": "<s>",
|
| 5 |
-
"eos_token": "</s>",
|
| 6 |
-
"errors": "replace",
|
| 7 |
-
"mask_token": "<mask>",
|
| 8 |
-
"model_max_length": 512,
|
| 9 |
-
"name_or_path": "roberta-large-conll2003",
|
| 10 |
-
"pad_token": "<pad>",
|
| 11 |
-
"sep_token": "</s>",
|
| 12 |
-
"special_tokens_map_file": null,
|
| 13 |
-
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
-
"trim_offsets": true,
|
| 15 |
-
"unk_token": "<unk>"
|
| 16 |
-
}
|
|
|
|
| 1 |
+
{"unk_token": "<unk>", "bos_token": "<s>", "eos_token": "</s>", "add_prefix_space": false, "errors": "replace", "sep_token": "</s>", "cls_token": "<s>", "pad_token": "<pad>", "mask_token": "<mask>", "model_max_length": 512, "name_or_path": "roberta-large-conll2003", "special_tokens_map_file": null, "trim_offsets": true, "tokenizer_class": "RobertaTokenizer"}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|