Upload tokenizer
Browse files- added_tokens.json +542 -0
- merges.txt +1 -1
- tokenizer.json +0 -0
- tokenizer_config.json +0 -0
added_tokens.json
ADDED
@@ -0,0 +1,542 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
{
|
2 |
+
"0813-124 phase II": 50522,
|
3 |
+
"090008": 50332,
|
4 |
+
"1.2.20": 50304,
|
5 |
+
"15H5D-4a": 50748,
|
6 |
+
"1692": 50508,
|
7 |
+
"174/2": 50543,
|
8 |
+
"17Nkhm-UP2": 50435,
|
9 |
+
"18EpOKYJ": 50706,
|
10 |
+
"200023": 50500,
|
11 |
+
"21A": 50674,
|
12 |
+
"24.1": 50783,
|
13 |
+
"301": 50623,
|
14 |
+
"3347689II": 50678,
|
15 |
+
"3937": 50659,
|
16 |
+
"477": 50792,
|
17 |
+
"49125": 50351,
|
18 |
+
"5D": 50314,
|
19 |
+
"640": 50321,
|
20 |
+
"670-83": 50702,
|
21 |
+
"675": 50728,
|
22 |
+
"6D370": 50415,
|
23 |
+
"757": 50392,
|
24 |
+
"78-1320": 50587,
|
25 |
+
"7A": 50517,
|
26 |
+
"80813": 50647,
|
27 |
+
"A1": 50716,
|
28 |
+
"A1122": 50428,
|
29 |
+
"A2-F21": 50786,
|
30 |
+
"A212-S19-A16": 50506,
|
31 |
+
"A23BA": 50457,
|
32 |
+
"A398-S21-F17": 50328,
|
33 |
+
"ACYC.E9L": 50497,
|
34 |
+
"ANU1": 50612,
|
35 |
+
"AR": 50777,
|
36 |
+
"ARAD": 50681,
|
37 |
+
"AR_0082": 50756,
|
38 |
+
"AS9": 50791,
|
39 |
+
"ATCC 13028": 50621,
|
40 |
+
"ATCC 39140": 50646,
|
41 |
+
"ATCC 43969": 50536,
|
42 |
+
"ATCC 51329": 50790,
|
43 |
+
"ATCC BAA-895": 50635,
|
44 |
+
"AVS0177": 50593,
|
45 |
+
"Annandia": 50514,
|
46 |
+
"ArsBeeUS": 50696,
|
47 |
+
"Arsenophonus": 50640,
|
48 |
+
"Arsenophonus apicola": 50637,
|
49 |
+
"Arsenophonus endosymbiont of Aleurodicus dispersus": 50648,
|
50 |
+
"Arsenophonus endosymbiont of Aphis craccivora": 50348,
|
51 |
+
"Arsenophonus nasoniae": 50712,
|
52 |
+
"Atlantibacter": 50775,
|
53 |
+
"Atlantibacter hermannii": 50759,
|
54 |
+
"Atlantibacter subterranea": 50421,
|
55 |
+
"BDA62-3": 50299,
|
56 |
+
"BHKY": 50364,
|
57 |
+
"BO-1": 50704,
|
58 |
+
"BPEN": 50310,
|
59 |
+
"BVAF": 50461,
|
60 |
+
"BY21311": 50430,
|
61 |
+
"Bacteria": 50690,
|
62 |
+
"Blochmannia": 50447,
|
63 |
+
"Blochmannia endosymbiont of Camponotus (Colobopsis) obliquus": 50779,
|
64 |
+
"Blochmannia endosymbiont of Camponotus modoc": 50586,
|
65 |
+
"Blochmannia endosymbiont of Camponotus nipponensis": 50525,
|
66 |
+
"Blochmannia endosymbiont of Colobopsis nipponica": 50422,
|
67 |
+
"Blochmannia endosymbiont of Polyrhachis (Hedomyrma) turneri": 50427,
|
68 |
+
"Brenneria": 50745,
|
69 |
+
"Brenneria goodwinii": 50259,
|
70 |
+
"Brenneria izadpanahii": 50708,
|
71 |
+
"Brenneria nigrifluens": 50436,
|
72 |
+
"Brenneria rubrifaciens": 50396,
|
73 |
+
"Brenneria ulupoensis": 50721,
|
74 |
+
"Bruguierivoracaceae": 50316,
|
75 |
+
"Buchnera": 50289,
|
76 |
+
"Buchnera aphidicola": 50505,
|
77 |
+
"Budviciaceae": 50433,
|
78 |
+
"Buttiauxella": 50750,
|
79 |
+
"Buttiauxella agrestis": 50740,
|
80 |
+
"Buttiauxella ferragutiae": 50356,
|
81 |
+
"C-002": 50598,
|
82 |
+
"C-005": 50504,
|
83 |
+
"C-006": 50362,
|
84 |
+
"C-050": 50741,
|
85 |
+
"C-7-2": 50575,
|
86 |
+
"CAVP490": 50582,
|
87 |
+
"CB": 50568,
|
88 |
+
"CCA6": 50758,
|
89 |
+
"CCUG 66741": 50776,
|
90 |
+
"CF-458": 50595,
|
91 |
+
"CFBP 3304": 50589,
|
92 |
+
"CFCC10813": 50401,
|
93 |
+
"CFPB1430": 50282,
|
94 |
+
"CFS1934": 50469,
|
95 |
+
"CQ10": 50785,
|
96 |
+
"CS-931": 50680,
|
97 |
+
"Candidatus": 50446,
|
98 |
+
"Candidatus Arsenophonus lipoptenae": 50496,
|
99 |
+
"Candidatus Blochmannia pennsylvanicus": 50484,
|
100 |
+
"Candidatus Blochmannia vafer": 50622,
|
101 |
+
"Candidatus Doolittlea endobia": 50669,
|
102 |
+
"Candidatus Fukatsuia symbiotica": 50701,
|
103 |
+
"Candidatus Gullanella endobia": 50766,
|
104 |
+
"Candidatus Hoaglandella endobia": 50509,
|
105 |
+
"Candidatus Mikella endobia": 50315,
|
106 |
+
"Candidatus Purcelliella pentastirinorum": 50738,
|
107 |
+
"Candidatus Riesia pediculicola": 50274,
|
108 |
+
"Candidatus Tachikawaea gelatinosa": 50366,
|
109 |
+
"Candidatus Westeberhardia cardiocondylae": 50261,
|
110 |
+
"Candidatus blochmannia chromaiodes": 50501,
|
111 |
+
"Candidatus ishikawaella capsulata": 50720,
|
112 |
+
"Candidatus moranella endobia": 50291,
|
113 |
+
"Candidatus sodalis pierantonius": 50608,
|
114 |
+
"Candidatus_antoea carbekii": 50407,
|
115 |
+
"Candidatus_ukatsuia": 50487,
|
116 |
+
"Cedecea": 50510,
|
117 |
+
"Cedecea lapagei": 50618,
|
118 |
+
"Cedecea neteri": 50719,
|
119 |
+
"Cf7303": 50743,
|
120 |
+
"Chania": 50558,
|
121 |
+
"Chania multitudinisentens": 50656,
|
122 |
+
"Citrobacter": 50523,
|
123 |
+
"Citrobacter amalonaticus": 50290,
|
124 |
+
"Citrobacter arsenatis": 50470,
|
125 |
+
"Citrobacter braakii": 50466,
|
126 |
+
"Citrobacter freundii": 50653,
|
127 |
+
"Citrobacter koseri": 50602,
|
128 |
+
"Citrobacter portucalensis": 50309,
|
129 |
+
"Citrobacter rodentium": 50664,
|
130 |
+
"Citrobacter sedlakii": 50423,
|
131 |
+
"Citrobacter tructae": 50463,
|
132 |
+
"Citrobacter werkmanii": 50414,
|
133 |
+
"Cp2": 50385,
|
134 |
+
"Cronobacter": 50402,
|
135 |
+
"Cronobacter condimenti": 50443,
|
136 |
+
"Cronobacter dublinensis": 50372,
|
137 |
+
"Cronobacter malonaticus": 50542,
|
138 |
+
"Cronobacter muytjensii": 50760,
|
139 |
+
"Cronobacter sakazakii": 50734,
|
140 |
+
"Cronobacter universalis": 50349,
|
141 |
+
"DH-S01": 50600,
|
142 |
+
"DSM 101947": 50442,
|
143 |
+
"DSM 102253": 50387,
|
144 |
+
"DSM 107547": 50677,
|
145 |
+
"DSM 15199": 50529,
|
146 |
+
"DSM 16636": 50493,
|
147 |
+
"DSM 16690": 50521,
|
148 |
+
"DSM 22758": 50585,
|
149 |
+
"DSM 32899": 50345,
|
150 |
+
"DSM 4481": 50533,
|
151 |
+
"DSM 4576": 50651,
|
152 |
+
"DSM 9389": 50762,
|
153 |
+
"Dickeya": 50545,
|
154 |
+
"Dickeya aquatica": 50502,
|
155 |
+
"Dickeya chrysanthemi": 50393,
|
156 |
+
"Dickeya dadantii": 50703,
|
157 |
+
"Dickeya dianthicola": 50524,
|
158 |
+
"Dickeya fangzhongdai": 50692,
|
159 |
+
"Dickeya parazeae": 50302,
|
160 |
+
"Dickeya poaceiphila": 50404,
|
161 |
+
"Dickeya solani": 50604,
|
162 |
+
"Dickeya zeae": 50263,
|
163 |
+
"Doolittlea": 50382,
|
164 |
+
"Duffyella": 50660,
|
165 |
+
"Duffyella gerundensis": 50645,
|
166 |
+
"EBP3064": 50429,
|
167 |
+
"EN-119": 50537,
|
168 |
+
"ERMR1:05": 50267,
|
169 |
+
"Eb661": 50569,
|
170 |
+
"Ech1591": 50699,
|
171 |
+
"Ech586": 50337,
|
172 |
+
"Ech703": 50273,
|
173 |
+
"Edwardsiella": 50601,
|
174 |
+
"Edwardsiella anguillarum": 50313,
|
175 |
+
"Edwardsiella hoshinae": 50462,
|
176 |
+
"Edwardsiella ictaluri": 50285,
|
177 |
+
"Edwardsiella piscicida": 50476,
|
178 |
+
"Edwardsiella tarda": 50691,
|
179 |
+
"Enterobacter": 50311,
|
180 |
+
"Enterobacter asburiae": 50705,
|
181 |
+
"Enterobacter bugandensis": 50467,
|
182 |
+
"Enterobacter chengduensis": 50494,
|
183 |
+
"Enterobacter cloacae": 50667,
|
184 |
+
"Enterobacter hormaechei": 50688,
|
185 |
+
"Enterobacter huaxiensis": 50363,
|
186 |
+
"Enterobacter ludwigii": 50742,
|
187 |
+
"Enterobacter mori": 50295,
|
188 |
+
"Enterobacter oligotrophicus": 50685,
|
189 |
+
"Enterobacter pseudoroggenkampii": 50383,
|
190 |
+
"Enterobacter roggenkampii": 50540,
|
191 |
+
"Enterobacter sichuanensis": 50276,
|
192 |
+
"Enterobacter soli": 50679,
|
193 |
+
"Enterobacterales": 50513,
|
194 |
+
"Enterobacteriaceae": 50610,
|
195 |
+
"Enterobacteriaceae endosymbiont of Macroplea mutica": 50489,
|
196 |
+
"Enterobacteriaceae endosymbiont of Plateumaris pusilla": 50344,
|
197 |
+
"Enterobacteriaceae endosymbiont of_acroplea mutica": 50636,
|
198 |
+
"EpK1/15": 50528,
|
199 |
+
"ErCicurvipes": 50403,
|
200 |
+
"Erwinia": 50475,
|
201 |
+
"Erwinia amylovora": 50319,
|
202 |
+
"Erwinia billingiae": 50652,
|
203 |
+
"Erwinia persicina": 50693,
|
204 |
+
"Erwinia pyrifoliae": 50359,
|
205 |
+
"Erwinia rhapontici": 50516,
|
206 |
+
"Erwinia sorbitola": 50736,
|
207 |
+
"Erwinia tasmaniensis": 50606,
|
208 |
+
"Erwinia tracheiphila": 50733,
|
209 |
+
"Erwiniaceae": 50576,
|
210 |
+
"Escherichia": 50723,
|
211 |
+
"Escherichia albertii": 50642,
|
212 |
+
"Escherichia coli ": 50628,
|
213 |
+
"Escherichia fergusonii": 50279,
|
214 |
+
"Escherichia marmotae": 50431,
|
215 |
+
"Et1/99": 50668,
|
216 |
+
"FDAARGOS 1447": 50499,
|
217 |
+
"FDAARGOS_1499": 50481,
|
218 |
+
"FDAARGOS_165": 50346,
|
219 |
+
"FDAARGOS_186": 50418,
|
220 |
+
"FDAARGOS_392": 50468,
|
221 |
+
"FDAARGOS_408": 50491,
|
222 |
+
"FDAARGOS_500": 50384,
|
223 |
+
"FDAARGOS_616": 50455,
|
224 |
+
"FDAARGOS_730": 50794,
|
225 |
+
"FDAARGOS_926": 50599,
|
226 |
+
"FDAARGOS_940": 50675,
|
227 |
+
"FIN": 50746,
|
228 |
+
"FN20211": 50488,
|
229 |
+
"FRB141": 50338,
|
230 |
+
"FRB97": 50486,
|
231 |
+
"FRM16": 50343,
|
232 |
+
"FY-07": 50451,
|
233 |
+
"FY158": 50737,
|
234 |
+
"G5": 50551,
|
235 |
+
"G6": 50386,
|
236 |
+
"Gammaproteobacteria": 50747,
|
237 |
+
"Gibbsiella": 50503,
|
238 |
+
"Gibbsiella quercinecans": 50571,
|
239 |
+
"Gullanella": 50334,
|
240 |
+
"H4-C11": 50465,
|
241 |
+
"HI4320": 50550,
|
242 |
+
"HS1": 50726,
|
243 |
+
"HS11286": 50769,
|
244 |
+
"HYN0051": 50754,
|
245 |
+
"Hafnia": 50312,
|
246 |
+
"Hafnia alvei": 50397,
|
247 |
+
"Hafnia paralvei": 50278,
|
248 |
+
"Hafniaceae": 50672,
|
249 |
+
"Hoaglandella": 50388,
|
250 |
+
"IFB5427": 50266,
|
251 |
+
"IP32953": 50419,
|
252 |
+
"Iran 50": 50567,
|
253 |
+
"Ishikawaella": 50574,
|
254 |
+
"J780": 50552,
|
255 |
+
"JH01": 50444,
|
256 |
+
"JK2.1": 50293,
|
257 |
+
"JZ-GX1": 50770,
|
258 |
+
"JZB2120001": 50262,
|
259 |
+
"Jejubacter": 50573,
|
260 |
+
"Jejubacter calystegiae": 50566,
|
261 |
+
"K-12 substr. MG1655": 50518,
|
262 |
+
"K61": 50725,
|
263 |
+
"KACC 18508": 50774,
|
264 |
+
"KC-Pc-HB1": 50671,
|
265 |
+
"KMM821": 50287,
|
266 |
+
"KSNA2": 50590,
|
267 |
+
"KUDC3025": 50485,
|
268 |
+
"Ka37751": 50639,
|
269 |
+
"Kalro": 50411,
|
270 |
+
"Klebsiella": 50474,
|
271 |
+
"Klebsiella aerogenes": 50630,
|
272 |
+
"Klebsiella africana": 50594,
|
273 |
+
"Klebsiella electrica": 50275,
|
274 |
+
"Klebsiella huaxiensis": 50439,
|
275 |
+
"Klebsiella michiganensis": 50417,
|
276 |
+
"Klebsiella oxytoca": 50298,
|
277 |
+
"Klebsiella pasteurii": 50546,
|
278 |
+
"Klebsiella pneumoniae": 50557,
|
279 |
+
"Klebsiella quasipneumoniae": 50658,
|
280 |
+
"Klebsiella variicola": 50507,
|
281 |
+
"Kluyvera": 50613,
|
282 |
+
"Kluyvera ascorbata": 50520,
|
283 |
+
"Kluyvera intermedia": 50534,
|
284 |
+
"Kosakonia": 50413,
|
285 |
+
"Kosakonia arachidis": 50644,
|
286 |
+
"Kosakonia cowanii": 50325,
|
287 |
+
"Kosakonia oryzae": 50318,
|
288 |
+
"Kosakonia oryzendophytica": 50687,
|
289 |
+
"Kosakonia pseudosacchari": 50673,
|
290 |
+
"Kosakonia radicincitans": 50272,
|
291 |
+
"Kosakonia sacchari": 50554,
|
292 |
+
"KqPF26": 50257,
|
293 |
+
"L6": 50292,
|
294 |
+
"LEMB11": 50614,
|
295 |
+
"LF7a": 50580,
|
296 |
+
"LH84-a": 50342,
|
297 |
+
"LJ1": 50663,
|
298 |
+
"LMG 23823": 50649,
|
299 |
+
"LMG 23826": 50731,
|
300 |
+
"LMG 24197": 50391,
|
301 |
+
"LMG 24199": 50297,
|
302 |
+
"LMG 26250": 50532,
|
303 |
+
"LMG24200": 50729,
|
304 |
+
"LST-1": 50562,
|
305 |
+
"LT-1": 50270,
|
306 |
+
"LT2": 50347,
|
307 |
+
"LTYR-11Z": 50695,
|
308 |
+
"LY-1": 50498,
|
309 |
+
"Leclercia": 50684,
|
310 |
+
"Leclercia adecarboxylata": 50381,
|
311 |
+
"Leclercia pneumoniae": 50781,
|
312 |
+
"Lelliottia": 50445,
|
313 |
+
"Lelliottia steviae": 50722,
|
314 |
+
"Leminorella": 50339,
|
315 |
+
"Leminorella richardii": 50512,
|
316 |
+
"Limnobaculum": 50333,
|
317 |
+
"Limnobaculum parvum": 50670,
|
318 |
+
"Limnobaculum zhutongyuii": 50300,
|
319 |
+
"Lonsdalea": 50634,
|
320 |
+
"Lonsdalea britannica": 50350,
|
321 |
+
"Lonsdalea populi": 50519,
|
322 |
+
"Lsch": 50379,
|
323 |
+
"ME23": 50563,
|
324 |
+
"MS2": 50424,
|
325 |
+
"MiY-A": 50395,
|
326 |
+
"Mikella": 50572,
|
327 |
+
"Mixta": 50556,
|
328 |
+
"Mixta gaviniae": 50744,
|
329 |
+
"Mixta hanseatica": 50390,
|
330 |
+
"Mixta intestinalis": 50570,
|
331 |
+
"Moellerella": 50788,
|
332 |
+
"Moellerella wisconsensis": 50714,
|
333 |
+
"Moranella": 50654,
|
334 |
+
"Morganella": 50326,
|
335 |
+
"Morganella morganii": 50360,
|
336 |
+
"Morganellaceae": 50441,
|
337 |
+
"Mpkobe": 50753,
|
338 |
+
"Musicola": 50603,
|
339 |
+
"Musicola paradisiaca": 50625,
|
340 |
+
"N-5-1": 50609,
|
341 |
+
"N2-1": 50416,
|
342 |
+
"N268-08": 50559,
|
343 |
+
"NA": 50629,
|
344 |
+
"NCPPB 569": 50268,
|
345 |
+
"NCTC 14382": 50605,
|
346 |
+
"NCTC 9529": 50412,
|
347 |
+
"NCTC11466": 50697,
|
348 |
+
"NCTC12003": 50281,
|
349 |
+
"NCTC12148": 50377,
|
350 |
+
"NCTC12151": 50449,
|
351 |
+
"NCTC12284": 50694,
|
352 |
+
"NCTC13188": 50495,
|
353 |
+
"NIBIO1392": 50555,
|
354 |
+
"OLIH": 50438,
|
355 |
+
"Ola 51": 50330,
|
356 |
+
"PA13": 50305,
|
357 |
+
"PCVAL": 50432,
|
358 |
+
"PPO 9019": 50711,
|
359 |
+
"PR-310": 50265,
|
360 |
+
"PRI-2C": 50477,
|
361 |
+
"Pantoea": 50511,
|
362 |
+
"Pantoea agglomerans": 50483,
|
363 |
+
"Pantoea alfalfae": 50323,
|
364 |
+
"Pantoea alhagi": 50535,
|
365 |
+
"Pantoea ananatis": 50643,
|
366 |
+
"Pantoea deleyi": 50453,
|
367 |
+
"Pantoea dispersa": 50479,
|
368 |
+
"Pantoea eucalypti": 50264,
|
369 |
+
"Pantoea eucrina": 50471,
|
370 |
+
"Pantoea soli": 50294,
|
371 |
+
"Pantoea stewartii": 50757,
|
372 |
+
"Pantoea vagans": 50340,
|
373 |
+
"Pectobacteriaceae": 50341,
|
374 |
+
"Pectobacterium": 50665,
|
375 |
+
"Pectobacterium aquaticum": 50303,
|
376 |
+
"Pectobacterium aroidearum": 50420,
|
377 |
+
"Pectobacterium atrosepticum": 50778,
|
378 |
+
"Pectobacterium brasiliense": 50378,
|
379 |
+
"Pectobacterium cacticida": 50394,
|
380 |
+
"Pectobacterium carotovorum": 50369,
|
381 |
+
"Pectobacterium colocasium": 50727,
|
382 |
+
"Pectobacterium odoriferum": 50408,
|
383 |
+
"Pectobacterium parmentieri": 50713,
|
384 |
+
"Pectobacterium parvum": 50492,
|
385 |
+
"Pectobacterium polaris": 50768,
|
386 |
+
"Pectobacterium punjabense": 50288,
|
387 |
+
"Pectobacterium quasiaquaticum": 50380,
|
388 |
+
"Pectobacterium wasabiae": 50771,
|
389 |
+
"Photorhabdus": 50472,
|
390 |
+
"Photorhabdus akhurstii": 50717,
|
391 |
+
"Photorhabdus asymbiotica": 50324,
|
392 |
+
"Photorhabdus laumondii": 50548,
|
393 |
+
"Photorhabdus thracensis": 50322,
|
394 |
+
"Phytobacter": 50538,
|
395 |
+
"Phytobacter diazotrophicus": 50650,
|
396 |
+
"Plesiomonas": 50710,
|
397 |
+
"Plesiomonas shigelloides": 50440,
|
398 |
+
"Pluralibacter": 50478,
|
399 |
+
"Pluralibacter gergoviae": 50409,
|
400 |
+
"Pragia": 50591,
|
401 |
+
"Pragia fontium": 50277,
|
402 |
+
"Profftia": 50666,
|
403 |
+
"Proteus": 50773,
|
404 |
+
"Proteus hauseri": 50626,
|
405 |
+
"Proteus mirabilis": 50454,
|
406 |
+
"Proteus penneri": 50751,
|
407 |
+
"Proteus terrae": 50541,
|
408 |
+
"Providencia": 50683,
|
409 |
+
"Providencia alcalifaciens": 50655,
|
410 |
+
"Providencia hangzhouensis": 50689,
|
411 |
+
"Providencia heimbachae": 50755,
|
412 |
+
"Providencia huaxiensis": 50588,
|
413 |
+
"Providencia rettgeri": 50373,
|
414 |
+
"Providencia stuartii": 50700,
|
415 |
+
"Pseudocitrobacter": 50375,
|
416 |
+
"Pseudocitrobacter corydidari": 50676,
|
417 |
+
"Pseudomonadota": 50682,
|
418 |
+
"Purcelliella": 50553,
|
419 |
+
"RB-25": 50730,
|
420 |
+
"Rahnella": 50616,
|
421 |
+
"Rahnella aceris": 50286,
|
422 |
+
"Rahnella sikkimica": 50280,
|
423 |
+
"Rahnella victoriana": 50389,
|
424 |
+
"Raoultella": 50354,
|
425 |
+
"Raoultella planticola": 50464,
|
426 |
+
"Raoultella terrigena": 50355,
|
427 |
+
"Riesia": 50724,
|
428 |
+
"S07-698": 50399,
|
429 |
+
"S1": 50617,
|
430 |
+
"S178-2": 50633,
|
431 |
+
"S2-A69": 50620,
|
432 |
+
"SCPM-O-B-7604": 50260,
|
433 |
+
"SE6-1": 50405,
|
434 |
+
"SGAir0282": 50579,
|
435 |
+
"SII": 50732,
|
436 |
+
"SK": 50564,
|
437 |
+
"SNU WT2": 50793,
|
438 |
+
"SOPE": 50320,
|
439 |
+
"SRCM103226": 50531,
|
440 |
+
"SS95": 50357,
|
441 |
+
"SWHEFF_49": 50752,
|
442 |
+
"Sakai substr. RIMD 0509952": 50780,
|
443 |
+
"Salmonella": 50515,
|
444 |
+
"Salmonella bongori": 50398,
|
445 |
+
"Salmonella enterica": 50258,
|
446 |
+
"Sample 167": 50400,
|
447 |
+
"Sb-24": 50641,
|
448 |
+
"Scandinavium": 50269,
|
449 |
+
"Scandinavium goeteborgense": 50544,
|
450 |
+
"Schneideria": 50448,
|
451 |
+
"Serratia": 50374,
|
452 |
+
"Serratia entomophila": 50661,
|
453 |
+
"Serratia ficaria": 50284,
|
454 |
+
"Serratia fonticola": 50549,
|
455 |
+
"Serratia inhibens": 50335,
|
456 |
+
"Serratia liquefaciens": 50581,
|
457 |
+
"Serratia nematodiphila": 50739,
|
458 |
+
"Serratia plymuthica": 50307,
|
459 |
+
"Serratia proteamaculans": 50662,
|
460 |
+
"Serratia quinivorans": 50761,
|
461 |
+
"Serratia rhizosphaerae": 50490,
|
462 |
+
"Serratia rubidaea": 50473,
|
463 |
+
"Serratia surfactantfaciens": 50526,
|
464 |
+
"Serratia symbiotica": 50763,
|
465 |
+
"Serratia ureilytica": 50353,
|
466 |
+
"Shigella": 50565,
|
467 |
+
"Shigella dysenteriae": 50456,
|
468 |
+
"Shigella flexneri": 50615,
|
469 |
+
"Shigella sonnei": 50410,
|
470 |
+
"Shimwellia": 50331,
|
471 |
+
"Shimwellia blattae": 50627,
|
472 |
+
"Siccibacter": 50539,
|
473 |
+
"Siccibacter colletis": 50577,
|
474 |
+
"Sodalis": 50657,
|
475 |
+
"Sodalis endosymbiont of Henestaris halophilus": 50709,
|
476 |
+
"Sodalis glossinidius": 50306,
|
477 |
+
"Sodalis praecaptivus": 50376,
|
478 |
+
"SyEd1": 50784,
|
479 |
+
"Symbiopectobacterium": 50749,
|
480 |
+
"Symbiopectobacterium purcellii": 50638,
|
481 |
+
"T6": 50296,
|
482 |
+
"TA9759": 50452,
|
483 |
+
"TBY01": 50271,
|
484 |
+
"THO-011": 50406,
|
485 |
+
"TTO1": 50329,
|
486 |
+
"Tachikawaea": 50434,
|
487 |
+
"Tatumella": 50718,
|
488 |
+
"Tatumella citrea": 50327,
|
489 |
+
"Trabulsiella": 50767,
|
490 |
+
"Trabulsiella odontotermitis": 50425,
|
491 |
+
"US": 50530,
|
492 |
+
"USDA": 50256,
|
493 |
+
"USDA-ARS-USMARC-60222": 50596,
|
494 |
+
"UwTKB": 50584,
|
495 |
+
"VKH10": 50632,
|
496 |
+
"W65": 50482,
|
497 |
+
"WCHECl-C4 = WCHECh050004": 50787,
|
498 |
+
"WCHKl090001": 50365,
|
499 |
+
"WCHPr000369": 50707,
|
500 |
+
"WPP14": 50764,
|
501 |
+
"Westeberhardia": 50336,
|
502 |
+
"Wigglesworthia": 50698,
|
503 |
+
"Wigglesworthia glossinidia": 50547,
|
504 |
+
"Winslowiella": 50458,
|
505 |
+
"Winslowiella toletana": 50772,
|
506 |
+
"XL123": 50283,
|
507 |
+
"XL95": 50358,
|
508 |
+
"Xenorhabdus": 50460,
|
509 |
+
"Xenorhabdus budapestensis": 50624,
|
510 |
+
"Xenorhabdus doucetiae": 50371,
|
511 |
+
"Xenorhabdus griffiniae": 50619,
|
512 |
+
"Xenorhabdus hominickii": 50352,
|
513 |
+
"Xenorhabdus nematophila": 50715,
|
514 |
+
"Xenorhabdus poinarii": 50317,
|
515 |
+
"YD25": 50437,
|
516 |
+
"YF8": 50735,
|
517 |
+
"YRA": 50480,
|
518 |
+
"YSD YN2": 50782,
|
519 |
+
"Y_sim_228": 50368,
|
520 |
+
"Yersinia": 50367,
|
521 |
+
"Yersinia aldovae": 50301,
|
522 |
+
"Yersinia alsatica": 50527,
|
523 |
+
"Yersinia canariae": 50765,
|
524 |
+
"Yersinia hibernica": 50611,
|
525 |
+
"Yersinia intermedia": 50789,
|
526 |
+
"Yersinia mollaretii": 50361,
|
527 |
+
"Yersinia pestis": 50597,
|
528 |
+
"Yersinia pseudotuberculosis": 50795,
|
529 |
+
"Yersinia rohdei": 50450,
|
530 |
+
"Yersinia ruckeri": 50308,
|
531 |
+
"Yersinia similis": 50459,
|
532 |
+
"Yersiniaceae": 50560,
|
533 |
+
"ZJ-FGZX1": 50607,
|
534 |
+
"ZN2": 50370,
|
535 |
+
"[Enterobacter] lignolyticus": 50631,
|
536 |
+
"[Pantoea] beijingensis": 50426,
|
537 |
+
"morsitans": 50686,
|
538 |
+
"obscurior": 50578,
|
539 |
+
"secondary endosymbiont of Ctenarytaina eucalypti": 50561,
|
540 |
+
"secondary endosymbiont of Heteropsylla cubana": 50592,
|
541 |
+
"secondary endosymbiont of Trabutina mannipara": 50583
|
542 |
+
}
|
merges.txt
CHANGED
@@ -1,4 +1,4 @@
|
|
1 |
-
#version: 0.2
|
2 |
G C
|
3 |
A A
|
4 |
U U
|
|
|
1 |
+
#version: 0.2
|
2 |
G C
|
3 |
A A
|
4 |
U U
|
tokenizer.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|
tokenizer_config.json
CHANGED
The diff for this file is too large to render.
See raw diff
|
|