Add tokenizer
Browse files- tokenizer.json +0 -0
- tokenizer_config.json +11 -9
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -1,14 +1,16 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"backend": "tokenizers",
|
| 3 |
-
"
|
| 4 |
-
"
|
|
|
|
|
|
|
| 5 |
"is_local": false,
|
| 6 |
-
"mask_token": "
|
| 7 |
"model_max_length": 512,
|
| 8 |
-
"pad_token": "
|
| 9 |
-
"sep_token": "
|
| 10 |
-
"
|
| 11 |
-
"
|
| 12 |
-
"
|
| 13 |
-
"unk_token": "[UNK]"
|
| 14 |
}
|
|
|
|
| 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": 512,
|
| 11 |
+
"pad_token": "<pad>",
|
| 12 |
+
"sep_token": "</s>",
|
| 13 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 14 |
+
"trim_offsets": true,
|
| 15 |
+
"unk_token": "<unk>"
|
|
|
|
| 16 |
}
|