Upload tokenizer
Browse files- special_tokens_map.json +5 -42
- tokenizer_config.json +2 -11
- vocab.txt +1 -2
special_tokens_map.json
CHANGED
|
@@ -1,44 +1,7 @@
|
|
| 1 |
{
|
| 2 |
-
"cls_token":
|
| 3 |
-
|
| 4 |
-
|
| 5 |
-
|
| 6 |
-
|
| 7 |
-
"single_word": false
|
| 8 |
-
},
|
| 9 |
-
"eos_token": {
|
| 10 |
-
"content": "<eos>",
|
| 11 |
-
"lstrip": false,
|
| 12 |
-
"normalized": false,
|
| 13 |
-
"rstrip": false,
|
| 14 |
-
"single_word": false
|
| 15 |
-
},
|
| 16 |
-
"mask_token": {
|
| 17 |
-
"content": "*",
|
| 18 |
-
"lstrip": false,
|
| 19 |
-
"normalized": false,
|
| 20 |
-
"rstrip": false,
|
| 21 |
-
"single_word": false
|
| 22 |
-
},
|
| 23 |
-
"pad_token": {
|
| 24 |
-
"content": "<pad>",
|
| 25 |
-
"lstrip": false,
|
| 26 |
-
"normalized": false,
|
| 27 |
-
"rstrip": false,
|
| 28 |
-
"single_word": false
|
| 29 |
-
},
|
| 30 |
-
"sep_token": {
|
| 31 |
-
"content": "|",
|
| 32 |
-
"lstrip": false,
|
| 33 |
-
"normalized": false,
|
| 34 |
-
"rstrip": false,
|
| 35 |
-
"single_word": false
|
| 36 |
-
},
|
| 37 |
-
"unk_token": {
|
| 38 |
-
"content": "<unk>",
|
| 39 |
-
"lstrip": false,
|
| 40 |
-
"normalized": false,
|
| 41 |
-
"rstrip": false,
|
| 42 |
-
"single_word": false
|
| 43 |
-
}
|
| 44 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"cls_token": "<cls>",
|
| 3 |
+
"eos_token": "<eos>",
|
| 4 |
+
"mask_token": "<mask>",
|
| 5 |
+
"pad_token": "<pad>",
|
| 6 |
+
"unk_token": "<unk>"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 7 |
}
|
tokenizer_config.json
CHANGED
|
@@ -33,15 +33,7 @@
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"32": {
|
| 36 |
-
"content": "
|
| 37 |
-
"lstrip": false,
|
| 38 |
-
"normalized": false,
|
| 39 |
-
"rstrip": false,
|
| 40 |
-
"single_word": false,
|
| 41 |
-
"special": true
|
| 42 |
-
},
|
| 43 |
-
"33": {
|
| 44 |
-
"content": "|",
|
| 45 |
"lstrip": false,
|
| 46 |
"normalized": false,
|
| 47 |
"rstrip": false,
|
|
@@ -52,10 +44,9 @@
|
|
| 52 |
"clean_up_tokenization_spaces": false,
|
| 53 |
"cls_token": "<cls>",
|
| 54 |
"eos_token": "<eos>",
|
| 55 |
-
"mask_token": "
|
| 56 |
"model_max_length": 1000000000000000019884624838656,
|
| 57 |
"pad_token": "<pad>",
|
| 58 |
-
"sep_token": "|",
|
| 59 |
"tokenizer_class": "PairedSequenceTokenizer",
|
| 60 |
"unk_token": "<unk>"
|
| 61 |
}
|
|
|
|
| 33 |
"special": true
|
| 34 |
},
|
| 35 |
"32": {
|
| 36 |
+
"content": "<mask>",
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 37 |
"lstrip": false,
|
| 38 |
"normalized": false,
|
| 39 |
"rstrip": false,
|
|
|
|
| 44 |
"clean_up_tokenization_spaces": false,
|
| 45 |
"cls_token": "<cls>",
|
| 46 |
"eos_token": "<eos>",
|
| 47 |
+
"mask_token": "<mask>",
|
| 48 |
"model_max_length": 1000000000000000019884624838656,
|
| 49 |
"pad_token": "<pad>",
|
|
|
|
| 50 |
"tokenizer_class": "PairedSequenceTokenizer",
|
| 51 |
"unk_token": "<unk>"
|
| 52 |
}
|
vocab.txt
CHANGED
|
@@ -30,5 +30,4 @@ O
|
|
| 30 |
.
|
| 31 |
-
|
| 32 |
<null_1>
|
| 33 |
-
|
| 34 |
-
|
|
|
|
|
| 30 |
.
|
| 31 |
-
|
| 32 |
<null_1>
|
| 33 |
+
<mask>
|
|
|