Add tokenizer.json
Browse files- tokenizer.json +115 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,115 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": null,
|
| 4 |
+
"padding": null,
|
| 5 |
+
"added_tokens": [
|
| 6 |
+
{
|
| 7 |
+
"id": 0,
|
| 8 |
+
"content": "<|endoftext|>",
|
| 9 |
+
"single_word": false,
|
| 10 |
+
"lstrip": false,
|
| 11 |
+
"rstrip": false,
|
| 12 |
+
"normalized": false,
|
| 13 |
+
"special": true
|
| 14 |
+
},
|
| 15 |
+
{
|
| 16 |
+
"id": 1,
|
| 17 |
+
"content": "<|quantum|>",
|
| 18 |
+
"single_word": false,
|
| 19 |
+
"lstrip": false,
|
| 20 |
+
"rstrip": false,
|
| 21 |
+
"normalized": false,
|
| 22 |
+
"special": true
|
| 23 |
+
},
|
| 24 |
+
{
|
| 25 |
+
"id": 2,
|
| 26 |
+
"content": "<|classical|>",
|
| 27 |
+
"single_word": false,
|
| 28 |
+
"lstrip": false,
|
| 29 |
+
"rstrip": false,
|
| 30 |
+
"normalized": false,
|
| 31 |
+
"special": true
|
| 32 |
+
}
|
| 33 |
+
],
|
| 34 |
+
"normalizer": {
|
| 35 |
+
"type": "Sequence",
|
| 36 |
+
"normalizers": [
|
| 37 |
+
{
|
| 38 |
+
"type": "NFC"
|
| 39 |
+
},
|
| 40 |
+
{
|
| 41 |
+
"type": "Prepend",
|
| 42 |
+
"prepend": "▁"
|
| 43 |
+
}
|
| 44 |
+
]
|
| 45 |
+
},
|
| 46 |
+
"pre_tokenizer": {
|
| 47 |
+
"type": "Sequence",
|
| 48 |
+
"pretokenizers": [
|
| 49 |
+
{
|
| 50 |
+
"type": "Split",
|
| 51 |
+
"pattern": {
|
| 52 |
+
"Regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?\\p{L}+|\\p{N}{1,3}| ?[^\\s\\p{L}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
|
| 53 |
+
},
|
| 54 |
+
"behavior": "Isolated",
|
| 55 |
+
"invert": false
|
| 56 |
+
}
|
| 57 |
+
]
|
| 58 |
+
},
|
| 59 |
+
"post_processor": {
|
| 60 |
+
"type": "TemplateProcessing",
|
| 61 |
+
"single": [
|
| 62 |
+
{
|
| 63 |
+
"SpecialToken": {
|
| 64 |
+
"id": "<|endoftext|>",
|
| 65 |
+
"ids": [0]
|
| 66 |
+
}
|
| 67 |
+
}
|
| 68 |
+
],
|
| 69 |
+
"pair": [
|
| 70 |
+
{
|
| 71 |
+
"SpecialToken": {
|
| 72 |
+
"id": "<|endoftext|>",
|
| 73 |
+
"ids": [0]
|
| 74 |
+
}
|
| 75 |
+
}
|
| 76 |
+
],
|
| 77 |
+
"special_tokens": {
|
| 78 |
+
"<|endoftext|>": {
|
| 79 |
+
"id": 0,
|
| 80 |
+
"ids": [0]
|
| 81 |
+
},
|
| 82 |
+
"<|quantum|>": {
|
| 83 |
+
"id": 1,
|
| 84 |
+
"ids": [1]
|
| 85 |
+
},
|
| 86 |
+
"<|classical|>": {
|
| 87 |
+
"id": 2,
|
| 88 |
+
"ids": [2]
|
| 89 |
+
}
|
| 90 |
+
}
|
| 91 |
+
},
|
| 92 |
+
"decoder": {
|
| 93 |
+
"type": "Sequence",
|
| 94 |
+
"decoders": [
|
| 95 |
+
{
|
| 96 |
+
"type": "Replace",
|
| 97 |
+
"pattern": {
|
| 98 |
+
"String": "▁"
|
| 99 |
+
},
|
| 100 |
+
"content": " "
|
| 101 |
+
}
|
| 102 |
+
]
|
| 103 |
+
},
|
| 104 |
+
"model": {
|
| 105 |
+
"type": "BPE",
|
| 106 |
+
"dropout": null,
|
| 107 |
+
"unk_token": null,
|
| 108 |
+
"continuing_subword_prefix": null,
|
| 109 |
+
"end_of_word_suffix": null,
|
| 110 |
+
"fuse_unk": false,
|
| 111 |
+
"byte_fallback": false,
|
| 112 |
+
"vocab": {},
|
| 113 |
+
"merges": []
|
| 114 |
+
}
|
| 115 |
+
}
|