Upload tokenizer files (vocab, config, README)
Browse files- tokenizer.json +37 -13
tokenizer.json
CHANGED
|
@@ -1,38 +1,62 @@
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
-
"
|
| 4 |
-
|
|
|
|
| 5 |
"content": "<pad>",
|
|
|
|
| 6 |
"lstrip": false,
|
| 7 |
-
"normalized": false,
|
| 8 |
"rstrip": false,
|
| 9 |
-
"
|
| 10 |
"special": true
|
| 11 |
},
|
| 12 |
-
|
|
|
|
| 13 |
"content": "<unk>",
|
|
|
|
| 14 |
"lstrip": false,
|
| 15 |
-
"normalized": false,
|
| 16 |
"rstrip": false,
|
| 17 |
-
"
|
| 18 |
"special": true
|
| 19 |
},
|
| 20 |
-
|
|
|
|
| 21 |
"content": "<bos>",
|
|
|
|
| 22 |
"lstrip": false,
|
| 23 |
-
"normalized": false,
|
| 24 |
"rstrip": false,
|
| 25 |
-
"
|
| 26 |
"special": true
|
| 27 |
},
|
| 28 |
-
|
|
|
|
| 29 |
"content": "<eos>",
|
|
|
|
| 30 |
"lstrip": false,
|
| 31 |
-
"normalized": false,
|
| 32 |
"rstrip": false,
|
| 33 |
-
"
|
| 34 |
"special": true
|
| 35 |
}
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 36 |
},
|
| 37 |
"decoder": {
|
| 38 |
"type": "WordPiece",
|
|
|
|
| 1 |
{
|
| 2 |
"version": "1.0",
|
| 3 |
+
"added_tokens": [
|
| 4 |
+
{
|
| 5 |
+
"id": 0,
|
| 6 |
"content": "<pad>",
|
| 7 |
+
"single_word": false,
|
| 8 |
"lstrip": false,
|
|
|
|
| 9 |
"rstrip": false,
|
| 10 |
+
"normalized": false,
|
| 11 |
"special": true
|
| 12 |
},
|
| 13 |
+
{
|
| 14 |
+
"id": 1,
|
| 15 |
"content": "<unk>",
|
| 16 |
+
"single_word": false,
|
| 17 |
"lstrip": false,
|
|
|
|
| 18 |
"rstrip": false,
|
| 19 |
+
"normalized": false,
|
| 20 |
"special": true
|
| 21 |
},
|
| 22 |
+
{
|
| 23 |
+
"id": 2,
|
| 24 |
"content": "<bos>",
|
| 25 |
+
"single_word": false,
|
| 26 |
"lstrip": false,
|
|
|
|
| 27 |
"rstrip": false,
|
| 28 |
+
"normalized": false,
|
| 29 |
"special": true
|
| 30 |
},
|
| 31 |
+
{
|
| 32 |
+
"id": 3,
|
| 33 |
"content": "<eos>",
|
| 34 |
+
"single_word": false,
|
| 35 |
"lstrip": false,
|
|
|
|
| 36 |
"rstrip": false,
|
| 37 |
+
"normalized": false,
|
| 38 |
"special": true
|
| 39 |
}
|
| 40 |
+
],
|
| 41 |
+
"normalizer": {
|
| 42 |
+
"type": "Sequence",
|
| 43 |
+
"normalizers": [
|
| 44 |
+
{
|
| 45 |
+
"type": "NFC"
|
| 46 |
+
}
|
| 47 |
+
]
|
| 48 |
+
},
|
| 49 |
+
"pre_tokenizer": {
|
| 50 |
+
"type": "Sequence",
|
| 51 |
+
"pretokenizers": [
|
| 52 |
+
{
|
| 53 |
+
"type": "Whitespace"
|
| 54 |
+
},
|
| 55 |
+
{
|
| 56 |
+
"type": "Punctuation",
|
| 57 |
+
"behavior": "Isolated"
|
| 58 |
+
}
|
| 59 |
+
]
|
| 60 |
},
|
| 61 |
"decoder": {
|
| 62 |
"type": "WordPiece",
|