Upload tokenizer
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -1,12 +1,12 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
|
|
|
| 3 |
"cls_token": "<s>",
|
| 4 |
"eos_token": "</s>",
|
| 5 |
"mask_token": "<mask>",
|
| 6 |
"model_max_length": 1000000000000000019884624838656,
|
| 7 |
"pad_token": "<pad>",
|
| 8 |
"sep_token": "</s>",
|
| 9 |
-
"special_tokens_map_file": "models/twerto-base-uncased/special_tokens_map.json",
|
| 10 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 11 |
"unk_token": "<unk>"
|
| 12 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<s>",
|
| 3 |
+
"clean_up_tokenization_spaces": true,
|
| 4 |
"cls_token": "<s>",
|
| 5 |
"eos_token": "</s>",
|
| 6 |
"mask_token": "<mask>",
|
| 7 |
"model_max_length": 1000000000000000019884624838656,
|
| 8 |
"pad_token": "<pad>",
|
| 9 |
"sep_token": "</s>",
|
|
|
|
| 10 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 11 |
"unk_token": "<unk>"
|
| 12 |
}
|