Set `clean_up_tokenization_spaces` to false
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -8005,7 +8005,7 @@
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
| 8008 |
-
"clean_up_tokenization_spaces":
|
| 8009 |
"eos_token": "</s>",
|
| 8010 |
"model_max_length": 1000000000000000019884624838656,
|
| 8011 |
"tokenizer_class": "GPT2Tokenizer",
|
|
|
|
| 8005 |
}
|
| 8006 |
},
|
| 8007 |
"bos_token": "<s>",
|
| 8008 |
+
"clean_up_tokenization_spaces": false,
|
| 8009 |
"eos_token": "</s>",
|
| 8010 |
"model_max_length": 1000000000000000019884624838656,
|
| 8011 |
"tokenizer_class": "GPT2Tokenizer",
|