set clean_up_tokenization_spaces to false by default
Browse files- tokenizer_config.json +1 -1
tokenizer_config.json
CHANGED
|
@@ -1,7 +1,7 @@
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
-
"clean_up_tokenization_spaces":
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 8192,
|
| 7 |
"tokenizer_class": "GPT4Tokenizer",
|
|
|
|
| 1 |
{
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
+
"clean_up_tokenization_spaces": false,
|
| 5 |
"eos_token": "<|endoftext|>",
|
| 6 |
"model_max_length": 8192,
|
| 7 |
"tokenizer_class": "GPT4Tokenizer",
|