File size: 1,632 Bytes
e8df098 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 | {
"version": "1.0",
"truncation": null,
"padding": null,
"added_tokens": [
{
"id": 0,
"special": true,
"content": "<|pad|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 1,
"special": true,
"content": "<|bos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
},
{
"id": 2,
"special": true,
"content": "<|eos|>",
"single_word": false,
"lstrip": false,
"rstrip": false,
"normalized": false
}
],
"normalizer": null,
"pre_tokenizer": {
"type": "ByteLevel",
"add_prefix_space": false,
"trim_offsets": true
},
"post_processor": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true
},
"decoder": {
"type": "ByteLevel",
"add_prefix_space": true,
"trim_offsets": true
},
"model": {
"type": "BPE",
"dropout": null,
"unk_token": null,
"continuing_subword_prefix": null,
"end_of_word_suffix": null,
"fuse_unk": false,
"vocab": {
"<|pad|>": 0,
"<|bos|>": 1,
"<|eos|>": 2,
"1": 3,
"2": 4,
"A": 5,
"B": 6,
"C": 7,
"D": 8,
"E": 9,
"F": 10,
"G": 11,
"H": 12,
"I": 13,
"K": 14,
"L": 15,
"M": 16,
"N": 17,
"O": 18,
"P": 19,
"Q": 20,
"R": 21,
"S": 22,
"T": 23,
"U": 24,
"V": 25,
"W": 26,
"X": 27,
"Y": 28,
"Z": 29
},
"merges": []
}
} |