Fix tokenizer special token config
Browse files- tokenizer_config.json +5 -5
tokenizer_config.json
CHANGED
|
@@ -4,15 +4,15 @@
|
|
| 4 |
"bos_token": "<bos>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<eos>",
|
| 7 |
-
"extra_special_tokens": [
|
| 8 |
-
"<|im_start|>",
|
| 9 |
-
"<|im_end|>"
|
| 10 |
-
],
|
| 11 |
"is_local": false,
|
| 12 |
"local_files_only": false,
|
| 13 |
"model_max_length": 1000000000,
|
| 14 |
"pad_token": "<eos>",
|
| 15 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 16 |
"unk_token": "<unk>",
|
| 17 |
-
"vocab_size": 4096
|
|
|
|
|
|
|
|
|
|
|
|
|
| 18 |
}
|
|
|
|
| 4 |
"bos_token": "<bos>",
|
| 5 |
"clean_up_tokenization_spaces": false,
|
| 6 |
"eos_token": "<eos>",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
"is_local": false,
|
| 8 |
"local_files_only": false,
|
| 9 |
"model_max_length": 1000000000,
|
| 10 |
"pad_token": "<eos>",
|
| 11 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 12 |
"unk_token": "<unk>",
|
| 13 |
+
"vocab_size": 4096,
|
| 14 |
+
"additional_special_tokens": [
|
| 15 |
+
"<|im_start|>",
|
| 16 |
+
"<|im_end|>"
|
| 17 |
+
]
|
| 18 |
}
|