Upload tokenizer
Browse files- tokenizer_config.json +1 -2
tokenizer_config.json
CHANGED
|
@@ -1,5 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": true,
|
| 3 |
"added_tokens_decoder": {
|
| 4 |
"0": {
|
| 5 |
"content": "<s>",
|
|
@@ -46,11 +45,11 @@
|
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
"cls_token": "<s>",
|
| 48 |
"eos_token": "</s>",
|
|
|
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"pad_token": "<pad>",
|
| 52 |
"sep_token": "</s>",
|
| 53 |
"tokenizer_class": "XLMRobertaTokenizer",
|
| 54 |
-
"trim_offsets": true,
|
| 55 |
"unk_token": "<unk>"
|
| 56 |
}
|
|
|
|
| 1 |
{
|
|
|
|
| 2 |
"added_tokens_decoder": {
|
| 3 |
"0": {
|
| 4 |
"content": "<s>",
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
| 46 |
"cls_token": "<s>",
|
| 47 |
"eos_token": "</s>",
|
| 48 |
+
"extra_special_tokens": {},
|
| 49 |
"mask_token": "<mask>",
|
| 50 |
"model_max_length": 512,
|
| 51 |
"pad_token": "<pad>",
|
| 52 |
"sep_token": "</s>",
|
| 53 |
"tokenizer_class": "XLMRobertaTokenizer",
|
|
|
|
| 54 |
"unk_token": "<unk>"
|
| 55 |
}
|