Upload tokenizer_config.json with huggingface_hub
Browse files- tokenizer_config.json +5 -4
tokenizer_config.json
CHANGED
|
@@ -931,14 +931,15 @@
|
|
| 931 |
},
|
| 932 |
"clean_up_tokenization_spaces": true,
|
| 933 |
"cls_token": "[CLS]",
|
|
|
|
| 934 |
"mask_token": "[MASK]",
|
| 935 |
-
"model_max_length": 8192,
|
| 936 |
-
"pad_token": "[PAD]",
|
| 937 |
-
"sep_token": "[SEP]",
|
| 938 |
-
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 939 |
"model_input_names": [
|
| 940 |
"input_ids",
|
| 941 |
"attention_mask"
|
| 942 |
],
|
|
|
|
|
|
|
|
|
|
|
|
|
| 943 |
"unk_token": "[UNK]"
|
| 944 |
}
|
|
|
|
| 931 |
},
|
| 932 |
"clean_up_tokenization_spaces": true,
|
| 933 |
"cls_token": "[CLS]",
|
| 934 |
+
"extra_special_tokens": {},
|
| 935 |
"mask_token": "[MASK]",
|
|
|
|
|
|
|
|
|
|
|
|
|
| 936 |
"model_input_names": [
|
| 937 |
"input_ids",
|
| 938 |
"attention_mask"
|
| 939 |
],
|
| 940 |
+
"model_max_length": 4096,
|
| 941 |
+
"pad_token": "[PAD]",
|
| 942 |
+
"sep_token": "[SEP]",
|
| 943 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 944 |
"unk_token": "[UNK]"
|
| 945 |
}
|