Commit
•
9edc7b7
1
Parent(s):
5d005b2
Create tokenizer_config.json
Browse files- tokenizer_config.json +23 -0
tokenizer_config.json
ADDED
|
@@ -0,0 +1,23 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"add_prefix_space": true,
|
| 3 |
+
"bos_token": "<s>",
|
| 4 |
+
"cls_token": "<s>",
|
| 5 |
+
"eos_token": "</s>",
|
| 6 |
+
"errors": "replace",
|
| 7 |
+
"mask_token": {
|
| 8 |
+
"__type": "AddedToken",
|
| 9 |
+
"content": "<mask>",
|
| 10 |
+
"lstrip": true,
|
| 11 |
+
"normalized": false,
|
| 12 |
+
"rstrip": false,
|
| 13 |
+
"single_word": false
|
| 14 |
+
},
|
| 15 |
+
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
+
"name_or_path": "suchirsalhan/ZH-CamBabyTokeniser-BabyBERTa",
|
| 17 |
+
"pad_token": "<pad>",
|
| 18 |
+
"sep_token": "</s>",
|
| 19 |
+
"special_tokens_map_file": null,
|
| 20 |
+
"tokenizer_class": "RobertaTokenizer",
|
| 21 |
+
"trim_offsets": true,
|
| 22 |
+
"unk_token": "<unk>"
|
| 23 |
+
}
|