update config tokenizer
Browse files- tokenizer_config.json +1 -16
tokenizer_config.json
CHANGED
|
@@ -1,11 +1,4 @@
|
|
| 1 |
{
|
| 2 |
-
"add_prefix_space": false,
|
| 3 |
-
"backend": "tokenizers",
|
| 4 |
-
"bos_token": "<|endoftext|>",
|
| 5 |
-
"clean_up_tokenization_spaces": true,
|
| 6 |
-
"eos_token": "<|endoftext|>",
|
| 7 |
-
"errors": "replace",
|
| 8 |
-
"extra_special_tokens": {
|
| 9 |
"add_prefix_space": false,
|
| 10 |
"bos_token": "<|endoftext|>",
|
| 11 |
"eos_token": "<|endoftext|>",
|
|
@@ -15,12 +8,4 @@
|
|
| 15 |
"model_max_length": 1000000000000000019884624838656,
|
| 16 |
"tokenizer_class": "GPT2Tokenizer",
|
| 17 |
"vocab_size": 49152
|
| 18 |
-
}
|
| 19 |
-
"is_local": false,
|
| 20 |
-
"local_files_only": false,
|
| 21 |
-
"model_max_length": 1000000000000000019884624838656,
|
| 22 |
-
"pad_token": "<|endoftext|>",
|
| 23 |
-
"tokenizer_class": "GPT2Tokenizer",
|
| 24 |
-
"unk_token": "<|endoftext|>",
|
| 25 |
-
"vocab_size": 49152
|
| 26 |
-
}
|
|
|
|
| 1 |
{
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 2 |
"add_prefix_space": false,
|
| 3 |
"bos_token": "<|endoftext|>",
|
| 4 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 8 |
"model_max_length": 1000000000000000019884624838656,
|
| 9 |
"tokenizer_class": "GPT2Tokenizer",
|
| 10 |
"vocab_size": 49152
|
| 11 |
+
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|