{ "version": "1.0", "truncation": null, "padding": null, "added_tokens": [ { "id": 0, "content": "[START]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 1, "content": "[END]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 2, "content": "[PAD]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 3, "content": "[UNK]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": false, "special": true }, { "id": 8, "content": "[Acinetobacter]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 9, "content": "[Acinetobacter baumannii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 10, "content": "[Acinetobacter haemolyticus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 11, "content": "[Acinetobacter johnsonii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 12, "content": "[Acinetobacter lwoffii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 13, "content": "[Acinetobacter nosocomialis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 14, "content": "[Acinetobacter pittii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 15, "content": "[Acinetobacter seifertii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 16, "content": "[Acinetobacter soli]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 17, "content": "[Aeromonas caviae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 18, "content": "[Aeromonas hydrophila]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 19, "content": "[Aeromonas salmonicida]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 20, "content": "[Aeromonas veronii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 21, "content": "[Bacillus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 22, "content": "[Bacillus anthracis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 23, "content": "[Bacillus cereus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 24, "content": "[Bacillus cytotoxicus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 25, "content": "[Bacillus mycoides]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 26, "content": "[Bacillus subtilis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 27, "content": "[Bacillus thuringiensis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 28, "content": "[Bacillus velezensis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 29, "content": "[Bacteroides fragilis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 30, "content": "[Campylobacter coli]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 31, "content": "[Campylobacter jejuni]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 32, "content": "[Citrobacter]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 33, "content": "[Citrobacter braakii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 34, "content": "[Citrobacter freundii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 35, "content": "[Citrobacter portucalensis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 36, "content": "[Citrobacter youngae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 37, "content": "[Clostridium perfringens]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 38, "content": "[Edwardsiella ictaluri]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 39, "content": "[Enterobacter]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 40, "content": "[Enterobacter asburiae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 41, "content": "[Enterobacter cloacae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 42, "content": "[Enterobacter hormaechei]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 43, "content": "[Enterobacter kobei]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 44, "content": "[Enterobacter roggenkampii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 45, "content": "[Enterococcus faecalis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 46, "content": "[Enterococcus faecium]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 47, "content": "[Enterococcus hirae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 48, "content": "[Escherichia]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 49, "content": "[Escherichia albertii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 50, "content": "[Escherichia coli]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 51, "content": "[Escherichia fergusonii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 52, "content": "[Escherichia marmotae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 53, "content": "[Helicobacter pylori]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 54, "content": "[Klebsiella]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 55, "content": "[Klebsiella aerogenes]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 56, "content": "[Klebsiella grimontii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 57, "content": "[Klebsiella michiganensis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 58, "content": "[Klebsiella oxytoca]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 59, "content": "[Klebsiella pneumoniae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 60, "content": "[Klebsiella quasipneumoniae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 61, "content": "[Klebsiella variicola]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 62, "content": "[Komagataeibacter nataicola]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 63, "content": "[Lacticaseibacillus paracasei]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 64, "content": "[Lactiplantibacillus pentosus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 65, "content": "[Lactiplantibacillus plantarum]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 66, "content": "[Lactobacillus backii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 67, "content": "[Lactobacillus plantarum]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 68, "content": "[Lactococcus cremoris]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 69, "content": "[Lactococcus lactis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 70, "content": "[Latilactobacillus sakei]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 71, "content": "[Leuconostoc mesenteroides]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 72, "content": "[Levilactobacillus brevis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 73, "content": "[Ligilactobacillus salivarius]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 74, "content": "[Listeria innocua]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 75, "content": "[Listeria monocytogenes]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 76, "content": "[Loigolactobacillus backii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 77, "content": "[Moraxella osloensis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 78, "content": "[Pediococcus damnosus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 79, "content": "[Pediococcus pentosaceus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 80, "content": "[Priestia megaterium]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 81, "content": "[Proteus mirabilis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 82, "content": "[Providencia rettgeri]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 83, "content": "[Providencia stuartii]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 84, "content": "[Pseudomonas]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 85, "content": "[Pseudomonas aeruginosa]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 86, "content": "[Pseudomonas putida]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 87, "content": "[Psychrobacter]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 88, "content": "[Raoultella ornithinolytica]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 89, "content": "[Raoultella planticola]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 90, "content": "[Salmonella]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 91, "content": "[Salmonella enterica]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 92, "content": "[Serratia marcescens]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 93, "content": "[Shigella dysenteriae]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 94, "content": "[Shigella flexneri]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 95, "content": "[Shigella sonnei]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 96, "content": "[Staphylococcus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 97, "content": "[Staphylococcus aureus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 98, "content": "[Staphylococcus chromogenes]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 99, "content": "[Staphylococcus epidermidis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 100, "content": "[Staphylococcus equorum]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 101, "content": "[Staphylococcus haemolyticus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 102, "content": "[Staphylococcus hominis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 103, "content": "[Staphylococcus lugdunensis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 104, "content": "[Staphylococcus pasteuri]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 105, "content": "[Staphylococcus saprophyticus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 106, "content": "[Staphylococcus simulans]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 107, "content": "[Staphylococcus warneri]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 108, "content": "[Streptococcus thermophilus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 109, "content": "[Tetragenococcus halophilus]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 110, "content": "[Yersinia enterocolitica]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 111, "content": "[Yersinia pestis]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 112, "content": "[uncultured bacterium]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 113, "content": "[UNKNOWN_SPECIES]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 114, "content": "[UNANNOTATED_SPECIES]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 115, "content": "[None]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 116, "content": "[PF01051]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 117, "content": "[PF01446]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 118, "content": "[PF01815]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 119, "content": "[PF02387]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 120, "content": "[PF03090]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 121, "content": "[PF04796]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 122, "content": "[PF05732]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 123, "content": "[PF06504]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 124, "content": "[PF06970]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 125, "content": "[PF08708]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 126, "content": "[PF10134]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 127, "content": "[PF10723]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 128, "content": "[UNKNOWN_REP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false }, { "id": 129, "content": "[UNANNOTATED_REP]", "single_word": false, "lstrip": false, "rstrip": false, "normalized": true, "special": false } ], "normalizer": null, "pre_tokenizer": { "type": "Whitespace" }, "post_processor": null, "decoder": null, "model": { "type": "BPE", "dropout": null, "unk_token": "[UNK]", "continuing_subword_prefix": null, "end_of_word_suffix": null, "fuse_unk": false, "byte_fallback": false, "ignore_merges": false, "vocab": { "[START]": 0, "[END]": 1, "[PAD]": 2, "[UNK]": 3, "A": 4, "C": 5, "G": 6, "T": 7 }, "merges": [] } }