Commit
•
8c14620
1
Parent(s):
1af48bc
Upload tokenizer
Browse files- tokenizer_config.json +7 -1
tokenizer_config.json
CHANGED
|
@@ -42,15 +42,21 @@
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"additional_special_tokens": [],
|
|
|
|
| 45 |
"clean_up_tokenization_spaces": true,
|
|
|
|
|
|
|
|
|
|
| 46 |
"max_length": 512,
|
| 47 |
"model_max_length": 512,
|
| 48 |
"pad_to_multiple_of": null,
|
| 49 |
"pad_token": "<pad>",
|
| 50 |
"pad_token_type_id": 0,
|
| 51 |
"padding_side": "right",
|
|
|
|
| 52 |
"stride": 0,
|
| 53 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 54 |
"truncation_side": "right",
|
| 55 |
-
"truncation_strategy": "longest_first"
|
|
|
|
| 56 |
}
|
|
|
|
| 42 |
}
|
| 43 |
},
|
| 44 |
"additional_special_tokens": [],
|
| 45 |
+
"bos_token": "<s>",
|
| 46 |
"clean_up_tokenization_spaces": true,
|
| 47 |
+
"cls_token": "<s>",
|
| 48 |
+
"eos_token": "</s>",
|
| 49 |
+
"mask_token": "<mask>",
|
| 50 |
"max_length": 512,
|
| 51 |
"model_max_length": 512,
|
| 52 |
"pad_to_multiple_of": null,
|
| 53 |
"pad_token": "<pad>",
|
| 54 |
"pad_token_type_id": 0,
|
| 55 |
"padding_side": "right",
|
| 56 |
+
"sep_token": "</s>",
|
| 57 |
"stride": 0,
|
| 58 |
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 59 |
"truncation_side": "right",
|
| 60 |
+
"truncation_strategy": "longest_first",
|
| 61 |
+
"unk_token": "<unk>"
|
| 62 |
}
|