Qwen2.5-7B-Instruct__trimm_vocab / qwen__1000__20000 /tokens_removed__alphabet.jsonl
tiendung's picture
update
4ecd5f0
raw
history blame
13.6 kB
[ " prze" , 30329, 997]
[ " fwd" , 91004, 989]
[ " werk" , 58618, 986]
[ " uw" , 37343, 986]
[ " btw" , 89857, 978]
[ " wyst" , 87564, 976]
[ " Wohn" , 52795, 976]
[ " sez" , 78472, 976]
[ " fsm" , 83138, 972]
[ " jspb" , 63770, 970]
[ " JAVA" , 85560, 967]
[ " clf" , 46079, 955]
[ " jdbc" , 85902, 951]
[ " zaj" , 81347, 950]
[ " jogo" , 66134, 948]
[ " kaz" , 90725, 947]
[ " vw" , 74086, 945]
[ " WX" , 77441, 937]
[ " awk" , 19976, 927]
[ " wei" , 83904, 921]
[ " jorn" , 71349, 903]
[ " JIT" , 96187, 901]
[ " wiel" , 63979, 897]
[ " zb" , 74355, 887]
[ " Deze" , 87836, 880]
[ " fert" , 21207, 879]
[ " jc" , 72818, 871]
[ " dzi" , 51026, 870]
[ " jsx" , 80095, 869]
[ " jm" , 95667, 863]
[ " PREF" , 98002, 860]
[ " juga" , 42369, 857]
[ " zach" , 96812, 844]
[ " zien" , 79407, 841]
[ " einf" , 31287, 838]
[ " Zahl" , 82745, 836]
[ " darf" , 87231, 834]
[ " pj" , 72613, 831]
[ " qw" , 41178, 822]
[ " csrf" , 35522, 819]
[ " jmp" , 90369, 819]
[ " jl" , 84710, 815]
[ " vrij" , 69605, 812]
[ " mz" , 95392, 809]
[ " zab" , 73071, 807]
[ " koji" , 59371, 804]
[ " wz" , 62920, 802]
[ " czy" , 35950, 798]
[ " blij" , 73280, 795]
[ " Utf" , 43432, 792]
[ " prez" , 79942, 784]
[ " gfx" , 39478, 783]
[ " kf" , 85580, 778]
[ " pz" , 97102, 777]
[ " Wich" , 76589, 763]
[ " zlib" , 81218, 761]
[ " intf" , 93706, 755]
[ " seja" , 52596, 740]
[ " wget" , 64508, 740]
[ " Zus" , 58485, 737]
[ " sdf" , 50157, 737]
[ " Dzi" , 134288, 737]
[ " jd" , 73376, 736]
[ " cljs" , 26284, 723]
[ " krij" , 69437, 721]
[ " rij" , 69345, 719]
[ " iw" , 72268, 714]
[ " filt" , 71854, 712]
[ " woll" , 73184, 710]
[ " CFG" , 46825, 704]
[ " rodz" , 79541, 697]
[ " seiz" , 33113, 696]
[ " WCS" , 98351, 687]
[ " afs" , 66713, 687]
[ " jb" , 87118, 681]
[ " nfs" , 77472, 673]
[ " Netz" , 92283, 673]
[ " wich" , 70367, 670]
[ " cpf" , 63976, 664]
[ " jint" , 52467, 658]
[ " fds" , 93734, 655]
[ " Zust" , 93716, 653]
[ " JNI" , 70829, 651]
[ " bfs" , 66564, 648]
[ " lz" , 95982, 640]
[ " feas" , 31892, 630]
[ " JMP" , 88251, 628]
[ " Fauc" , 96362, 618]
[ " NRF" , 72010, 618]
[ " JAXB" , 60640, 615]
[ " ajud" , 86059, 614]
[ " FUNC" , 43352, 611]
[ " hdf" , 97045, 610]
[ " moz" , 95339, 608]
[ " hWnd" , 58579, 606]
[ " ucz" , 87426, 602]
[ " cj" , 90997, 601]
[ " hwnd" , 52832, 600]
[ " zx" , 71322, 597]
[ " dof" , 91760, 595]
[ " azi" , 74062, 594]
[ " Swal" , 59073, 586]
[ " wym" , 71241, 582]
[ " frei" , 83423, 577]
[ " FLAC" , 89099, 577]
[ " CPF" , 45450, 569]
[ " yaz" , 78114, 561]
[ " jt" , 91076, 550]
[ " koje" , 96499, 549]
[ " zmq" , 90740, 545]
[ " MILF" , 73298, 540]
[ " CSRF" , 78595, 531]
[ " zun" , 98175, 530]
[ " jede" , 94572, 525]
[ " BFS" , 90351, 515]
[ " vej" , 92460, 509]
[ " GFX" , 76155, 503]
[ " zg" , 92058, 499]
[ " zes" , 137584, 498]
[ " vfs" , 92941, 481]
[ " vaz" , 143854, 480]
[ " Frm" , 91995, 477]
[ " kz" , 80955, 460]
[ " wnd" , 80432, 459]
[ " zost" , 95926, 459]
[ " FLT" , 96061, 446]
[ " helf" , 74403, 444]
[ " newY" , 80384, 443]
[ " jit" , 84573, 442]
[ " azt" , 97894, 438]
[ " fz" , 92649, 436]
[ " wsp" , 62507, 435]
[ " pwm" , 64551, 434]
[ " fov" , 93473, 416]
[ " swal" , 49354, 412]
[ " CWE" , 50860, 409]
[ " newX" , 88803, 408]
[ " szy" , 91765, 396]
[ " hjem" , 66985, 393]
[ " dzie" , 49673, 390]
[ " licz" , 84521, 367]
[ " szcz" , 75573, 367]
[ " hoje" , 73158, 366]
[ " wsz" , 38391, 360]
[ " nije" , 86493, 356]
[ " zza" , 97649, 344]
[ " zend" , 78568, 340]
[ " wcs" , 96668, 337]
[ " Www" , 81210, 335]
[ " jika" , 70879, 332]
[ " lawy" , 11010, 328]
[ " MOZ" , 63744, 317]
[ " saja" , 78786, 305]
[ " fica" , 95127, 297]
[ " menj" , 41374, 295]
[ " HWND" , 60384, 285]
[ " zf" , 99048, 281]
[ " wlan" , 78353, 279]
[ " BUF" , 73178, 277]
[ " bfd" , 94047, 275]
[ " fark" , 129369, 274]
[ " znaj" , 67715, 266]
[ " fabs" , 40728, 248]
[ " EIF" , 27695, 246]
[ " rozp" , 140775, 238]
[ " zale" , 142463, 232]
[ " zoek" , 73800, 226]
[ " UIF" , 44404, 214]
[ " zob" , 128165, 203]
[ " ZEND" , 92370, 202]
[ " DWC" , 70259, 198]
[ " wyb" , 143557, 192]
[ " narz" , 140251, 152]
[ " pObj" , 59952, 142]
[ " milf" , 25399, 134]
[ " setw" , 50063, 133]
[ " szko" , 140013, 126]
[ " oczy" , 138959, 122]
[ " zwy" , 143597, 122]
[ " weap" , 6158, 119]
[ " wxT" , 74197, 113]
[ " bbw" , 40760, 105]
[ " frau" , 37031, 100]
[ " jaki" , 139537, 93]
[ " mpz" , 71228, 84]
[ " sprz" , 127977, 83]
[ " JADX" , 88508, 83]
[ " urz" , 143475, 76]
[ " fkk" , 60798, 71]
[ " atof" , 64957, 68]
[ " PdfP" , 76516, 59]
[ " ffm" , 75892, 54]
[ " jadx" , 57543, 54]
[ " Milf" , 51558, 52]
[ " mpfr" , 82214, 50]
[ " wyja" , 142442, 48]
[ " rfl" , 69335, 42]
[ " znal" , 141024, 40]
[ " zro" , 135396, 38]
[ " Wroc" , 139221, 37]
[ " Oczy" , 141295, 33]
[ " wygl" , 133563, 30]
[ " zwyk" , 143598, 30]
[ " Bbw" , 85597, 25]
[ " najb" , 143244, 22]
[ " ksz" , 141368, 22]
[ " nrw" , 76506, 15]
[ " uwag" , 134907, 12]
[ " wzgl" , 127904, 7]
[ " wida" , 142268, 5]
[ " RTVF" , 87578, 4]
[ " RTWF" , 62685, 1]