File size: 1,857 Bytes
0011d71 690df0f 8548504 a09934c d0e3d7d 01c7334 0011d71 cae744f 0011d71 cae744f 0011d71 cae744f 0011d71 cae744f 0011d71 cae744f 0011d71 78413bf cae744f 0011d71 d3dc4cc 97bf18c 0011d71 | 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 | {
"tokenizer_class": "SrnaTokenizer",
"auto_map": {
"AutoTokenizer": ["tokenization_srna.SrnaTokenizer", null]
},
"add_prefix_space": false,
"added_tokens_decoder": {
"248044": {
"content": "[PAD]",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"248047": {
"content": "<csta>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"248048": {
"content": "<cend>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"248049": {
"content": "<capi>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
},
"248050": {
"content": "<uppe>",
"lstrip": false,
"normalized": false,
"rstrip": false,
"single_word": false,
"special": true
}
},
"clean_up_tokenization_spaces": false,
"errors": "replace",
"model_max_length": 50001,
"pad_token": "[PAD]",
"split_special_tokens": false,
"unk_token": null,
"add_bos_token": false,
"boc_token": "<csta>",
"eoc_token": "<cend>",
"cap_token": "<capi>",
"up_token": "<uppe>",
"case_compression": true,
"script_compression": true,
"omit_tags": false,
"pretokenize_regex": "(?i:'s|'t|'re|'ve|'m|'ll|'d)|[^\\r\\n\\p{L}\\p{N}]?[\\p{L}\\p{M}]+|\\p{N}| ?[^\\s\\p{L}\\p{M}\\p{N}]+[\\r\\n]*|\\s*[\\r\\n]+|\\s+(?!\\S)|\\s+"
} |