File size: 1,716 Bytes
87dcd5f |
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 |
{
"add_prefix_space": false,
"added_tokens_decoder": {
"0": {
"content": "[UNK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"1": {
"content": "[CLS]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"2": {
"content": "[SEP]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"3": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"4": {
"content": "[MASK]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"5": {
"content": "[START]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"6": {
"content": "[END]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"bos_token": "[START]",
"bos_token_id": 5,
"clean_up_tokenization_spaces": true,
"cls_token": "[CLS]",
"cls_token_id": 1,
"eos_token": "[END]",
"eos_token_id": 6,
"mask_token": "[MASK]",
"mask_token_id": 4,
"model_max_len": 4096,
"model_max_length": 4096,
"pad_token": "[PAD]",
"pad_token_id": 3,
"seo_token_id": 2,
"sep_token": "[SEP]",
"tokenizer_class": "PreTrainedTokenizerFast",
"type": "Split",
"unk_token": "[UNK]",
"unk_token_id": 0
}
|