Upload tokenizer
Browse files- special_tokens_map.json +6 -1
- tokenizer_config.json +6 -1
special_tokens_map.json
CHANGED
|
@@ -1,4 +1,9 @@
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 4 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"bos_token": "<|endoftext|>",
|
| 3 |
+
"cls_token": "[CLS]",
|
| 4 |
+
"eos_token": "<|endoftext|>",
|
| 5 |
+
"mask_token": "[MASK]",
|
| 6 |
+
"pad_token": "[PAD]",
|
| 7 |
+
"sep_token": "[SEP]",
|
| 8 |
+
"unk_token": "[UNK]"
|
| 9 |
}
|
tokenizer_config.json
CHANGED
|
@@ -51,7 +51,12 @@
|
|
| 51 |
},
|
| 52 |
"bos_token": "<|endoftext|>",
|
| 53 |
"clean_up_tokenization_spaces": false,
|
|
|
|
| 54 |
"eos_token": "<|endoftext|>",
|
|
|
|
| 55 |
"model_max_length": 1000000000000000019884624838656,
|
| 56 |
-
"
|
|
|
|
|
|
|
|
|
|
| 57 |
}
|
|
|
|
| 51 |
},
|
| 52 |
"bos_token": "<|endoftext|>",
|
| 53 |
"clean_up_tokenization_spaces": false,
|
| 54 |
+
"cls_token": "[CLS]",
|
| 55 |
"eos_token": "<|endoftext|>",
|
| 56 |
+
"mask_token": "[MASK]",
|
| 57 |
"model_max_length": 1000000000000000019884624838656,
|
| 58 |
+
"pad_token": "[PAD]",
|
| 59 |
+
"sep_token": "[SEP]",
|
| 60 |
+
"tokenizer_class": "PreTrainedTokenizerFast",
|
| 61 |
+
"unk_token": "[UNK]"
|
| 62 |
}
|