Upload tokenizer
Browse files- special_tokens_map.json +6 -1
- tokenizer.json +0 -0
- tokenizer_config.json +10 -1
special_tokens_map.json
CHANGED
|
@@ -1,3 +1,8 @@
|
|
| 1 |
{
|
| 2 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 3 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"bos_token": "|<BOS>|",
|
| 3 |
+
"cls_token": "|<CLS>|",
|
| 4 |
+
"eos_token": "|<EOS>|",
|
| 5 |
+
"mask_token": "|<MASK>|",
|
| 6 |
+
"pad_token": "|<PAD>|",
|
| 7 |
+
"sep_token": "|<SEP>|"
|
| 8 |
}
|
tokenizer.json
CHANGED
|
The diff for this file is too large to render.
See raw diff
|
|
|
tokenizer_config.json
CHANGED
|
@@ -57,8 +57,17 @@
|
|
| 57 |
"special": true
|
| 58 |
}
|
| 59 |
},
|
|
|
|
| 60 |
"clean_up_tokenization_spaces": true,
|
|
|
|
| 61 |
"eos_token": "|<EOS>|",
|
| 62 |
-
"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 63 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 64 |
}
|
|
|
|
| 57 |
"special": true
|
| 58 |
}
|
| 59 |
},
|
| 60 |
+
"bos_token": "|<BOS>|",
|
| 61 |
"clean_up_tokenization_spaces": true,
|
| 62 |
+
"cls_token": "|<CLS>|",
|
| 63 |
"eos_token": "|<EOS>|",
|
| 64 |
+
"mask_token": "|<MASK>|",
|
| 65 |
+
"max_length": null,
|
| 66 |
+
"model_max_length": 256,
|
| 67 |
+
"pad_to_multiple_of": null,
|
| 68 |
+
"pad_token": "|<PAD>|",
|
| 69 |
+
"pad_token_type_id": 0,
|
| 70 |
+
"padding_side": "right",
|
| 71 |
+
"sep_token": "|<SEP>|",
|
| 72 |
"tokenizer_class": "PreTrainedTokenizerFast"
|
| 73 |
}
|