Upload tokenizer.json with huggingface_hub
Browse files- tokenizer.json +119 -0
tokenizer.json
ADDED
|
@@ -0,0 +1,119 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
{
|
| 2 |
+
"version": "1.0",
|
| 3 |
+
"truncation": {
|
| 4 |
+
"direction": "Right",
|
| 5 |
+
"max_length": 1024,
|
| 6 |
+
"strategy": "LongestFirst",
|
| 7 |
+
"stride": 0
|
| 8 |
+
},
|
| 9 |
+
"padding": {
|
| 10 |
+
"strategy": {
|
| 11 |
+
"Fixed": 1024
|
| 12 |
+
},
|
| 13 |
+
"direction": "Right",
|
| 14 |
+
"pad_to_multiple_of": null,
|
| 15 |
+
"pad_id": 0,
|
| 16 |
+
"pad_type_id": 0,
|
| 17 |
+
"pad_token": "<|pad|>"
|
| 18 |
+
},
|
| 19 |
+
"added_tokens": [
|
| 20 |
+
{
|
| 21 |
+
"id": 0,
|
| 22 |
+
"content": "<|pad|>",
|
| 23 |
+
"single_word": false,
|
| 24 |
+
"lstrip": false,
|
| 25 |
+
"rstrip": false,
|
| 26 |
+
"normalized": false,
|
| 27 |
+
"special": true
|
| 28 |
+
},
|
| 29 |
+
{
|
| 30 |
+
"id": 1,
|
| 31 |
+
"content": "<|bos|>",
|
| 32 |
+
"single_word": false,
|
| 33 |
+
"lstrip": false,
|
| 34 |
+
"rstrip": false,
|
| 35 |
+
"normalized": false,
|
| 36 |
+
"special": true
|
| 37 |
+
},
|
| 38 |
+
{
|
| 39 |
+
"id": 2,
|
| 40 |
+
"content": "<|eos|>",
|
| 41 |
+
"single_word": false,
|
| 42 |
+
"lstrip": false,
|
| 43 |
+
"rstrip": false,
|
| 44 |
+
"normalized": false,
|
| 45 |
+
"special": true
|
| 46 |
+
},
|
| 47 |
+
{
|
| 48 |
+
"id": 30,
|
| 49 |
+
"content": "<|NTD|>",
|
| 50 |
+
"single_word": false,
|
| 51 |
+
"lstrip": false,
|
| 52 |
+
"rstrip": false,
|
| 53 |
+
"normalized": true,
|
| 54 |
+
"special": false
|
| 55 |
+
}
|
| 56 |
+
],
|
| 57 |
+
"normalizer": null,
|
| 58 |
+
"pre_tokenizer": {
|
| 59 |
+
"type": "ByteLevel",
|
| 60 |
+
"add_prefix_space": false,
|
| 61 |
+
"trim_offsets": true,
|
| 62 |
+
"use_regex": true
|
| 63 |
+
},
|
| 64 |
+
"post_processor": {
|
| 65 |
+
"type": "ByteLevel",
|
| 66 |
+
"add_prefix_space": true,
|
| 67 |
+
"trim_offsets": true,
|
| 68 |
+
"use_regex": true
|
| 69 |
+
},
|
| 70 |
+
"decoder": {
|
| 71 |
+
"type": "ByteLevel",
|
| 72 |
+
"add_prefix_space": true,
|
| 73 |
+
"trim_offsets": true,
|
| 74 |
+
"use_regex": true
|
| 75 |
+
},
|
| 76 |
+
"model": {
|
| 77 |
+
"type": "BPE",
|
| 78 |
+
"dropout": null,
|
| 79 |
+
"unk_token": null,
|
| 80 |
+
"continuing_subword_prefix": null,
|
| 81 |
+
"end_of_word_suffix": null,
|
| 82 |
+
"fuse_unk": false,
|
| 83 |
+
"byte_fallback": false,
|
| 84 |
+
"ignore_merges": false,
|
| 85 |
+
"vocab": {
|
| 86 |
+
"<|pad|>": 0,
|
| 87 |
+
"<|bos|>": 1,
|
| 88 |
+
"<|eos|>": 2,
|
| 89 |
+
"1": 3,
|
| 90 |
+
"2": 4,
|
| 91 |
+
"A": 5,
|
| 92 |
+
"B": 6,
|
| 93 |
+
"C": 7,
|
| 94 |
+
"D": 8,
|
| 95 |
+
"E": 9,
|
| 96 |
+
"F": 10,
|
| 97 |
+
"G": 11,
|
| 98 |
+
"H": 12,
|
| 99 |
+
"I": 13,
|
| 100 |
+
"K": 14,
|
| 101 |
+
"L": 15,
|
| 102 |
+
"M": 16,
|
| 103 |
+
"N": 17,
|
| 104 |
+
"O": 18,
|
| 105 |
+
"P": 19,
|
| 106 |
+
"Q": 20,
|
| 107 |
+
"R": 21,
|
| 108 |
+
"S": 22,
|
| 109 |
+
"T": 23,
|
| 110 |
+
"U": 24,
|
| 111 |
+
"V": 25,
|
| 112 |
+
"W": 26,
|
| 113 |
+
"X": 27,
|
| 114 |
+
"Y": 28,
|
| 115 |
+
"Z": 29
|
| 116 |
+
},
|
| 117 |
+
"merges": []
|
| 118 |
+
}
|
| 119 |
+
}
|