← Back to Architecture

Partial RoPE

Architecture
Used in
335 PRs
Best BPB
0.0180
Avg BPB
1.0628

Submissions

PR #64by yesbhautik
1.1250
PR #175by anthony-maio
1.1229
PR #218by bopmite
1.1248
PR #315by jfprincz
1.1248
PR #327by Ananddna
1.1450
PR #330by bopmite
1.1609
PR #332by saml212
1.1320
PR #334by nathon-lee
1.2207
PR #344by aryanbhosale
1.1330
PR #351by sp00mm
1.1659
PR #352by sp00mm
1.1659
PR #356by sjp611
1.8338
PR #371by mrdavtan
1.1401
PR #374by unnirRECORD
1.1246
PR #376by anthony-maio
1.1399
PR #383by joelnishanth
1.1320
PR #388by ElliotSlusky
1.1231
PR #389by trasnake87
1.1466
PR #397by translatingthename
1.1364
PR #398by felipe-parodi
1.1213
PR #399by abaybektursun
1.1247
PR #400by chanwoo-park-official
1.1296
PR #401by newjordan
1.1243
PR #410by EthanYangTW
1.1216
PR #413by anantdgoel
1.4525
PR #414by signalrush
1.1233
PR #415by EthanYangTW
1.1216
PR #417by EthanYangTW
1.1227
PR #418by yashverms
1.1715
PR #434by parinzee
1.1370
PR #445by newjordan
1.1236
PR #452by ofirkris
1.1366
PR #453by Divyesh-Thirukonda
1.1248
PR #455by kasimte
1.1299
PR #458by ofirkris
1.1365
PR #461by Christopher-Lee-McClendon
1.1446
PR #462by JoeProAI
1.0672
PR #469by cmcdnd
1.1418
PR #473by abaybektursun
1.1214
PR #477by harsha-gouru
1.1522
PR #478by gowtham0992
1.1268
PR #481by mrdavtan
1.0970
PR #482by harsha-gouru
1.1522
PR #485by harsha-gouru
1.1522
PR #486by ndokutovich
1.1101
PR #487by anantdgoel
1.1720
PR #489by sofiabod
1.1327
PR #492by Divyesh-Thirukonda
1.1591
PR #493by parinzee
1.1309
PR #498by newjordan
1.1478
PR #499by newjordan
1.1478
PR #503by EthanYangTW
1.1195
PR #505by JoeProAI
1.1181
PR #507by skarakulak
1.1558
PR #508by newjordan
1.1215
PR #509by andrewbaggio1
1.1175
PR #516by Asukabot0
1.1428
PR #518by sofiabod
1.0622
PR #526by Christopher-Lee-McClendon
1.1425
PR #528by EthanYangTW
1.1195
PR #529by EthanYangTW
1.1195
PR #532by NotADevIAmaMeatPopsicle
1.0487
PR #533by newjordan
1.1207
PR #534by rarce
1.1804
PR #535by raahilshah
1.1204
PR #537by Christopher-Lee-McClendon
1.1387
PR #543by rarce
1.1804
PR #545by EthanYangTW
1.1179
PR #549by abaybektursunRECORD
1.1194
PR #564by sadeghja1070
1.1270
PR #573by Sarimsaljook
1.0523
PR #576by cmcdnd
1.1164
PR #577by newjordan
1.1207
PR #585by EthanYangTW
1.1179
PR #586by EaCognitive
1.1365
PR #592by Skytuhua
1.1476
PR #593by abaybektursun
1.1163
PR #598by Christopher-Lee-McClendon
1.1334
PR #601by anantdgoel
1.1418
PR #606by EthanYangTW
1.1162
PR #609by saml212
1.1154
PR #612by Christopher-Lee-McClendon
1.1079
PR #634by raahilshah
1.1171
PR #635by aryanbhosale
1.1330
PR #638by Asukabot0
1.1164
PR #642by minh-stakc
0.8173
PR #644by Christopher-Lee-McClendon
1.0944
PR #645by FlynnCruse
1.8990
PR #653by demirelo
1.1552
PR #657by anthony-maio
1.1234
PR #661by andrewbaggio1
1.1175
PR #668by Christopher-Lee-McClendon
1.0920
PR #672by andrewbaggio1
1.0781
PR #682by gthgomez
1.1233
PR #685by andrewbaggio1
1.0366
PR #688by RoyiRa
1.0745
PR #690by EthanYangTW
1.1186
PR #692by EthanYangTW
1.1186
PR #693by EthanYangTW
1.1186
PR #695by 0xNoramiya
1.1360
PR #698by hesong0222-dev
1.1642
PR #703by Gusanidas
1.1176
PR #710by Dhruba531
1.1240
PR #714by Upsalla
1.1187
PR #715by Asukabot0
1.0337
PR #720by agalimova
1.1078
PR #726by DeepReinforce
1.1147
PR #727by Asukabot0
0.9674
PR #728by abaybektursun
1.1142
PR #734by Robby955
1.1198
PR #740by resouer
1.0909
PR #741by andrewbaggio1
0.9850
PR #752by Naazimsnh02
1.1182
PR #754by aryanbhosale
1.1253
PR #761by Asukabot0
0.9581
PR #768by mradassaad
1.1201
PR #770by minh-stakc
0.6672
PR #774by travispchen
0.9370
PR #778by raahilshah
0.9605
PR #779by deanbrr
0.6683
PR #786by shinegami-2002
0.8128
PR #794by jeremyschied
1.3346
PR #796by Robby955
0.6567
PR #802by Bortlesboat
0.9123
PR #808by Naazimsnh02
0.6364
PR #809by AayushBaniya2006
0.2952
PR #816by jimliu741523
1.1194
PR #826by himanshudongre
0.2951
PR #827by Programmerryoki
1.3999
PR #828by bigbag
0.9076
PR #832by jfprincz
1.1903
PR #836by autocode-rayes
1.1219
PR #838by aryanbhosale
1.1215
PR #841by someone114514
1.1157
PR #849by dttdrv
1.1105
PR #857by aruniyer
1.1093
PR #864by aryanbhosale
0.2841
PR #865by aryanbhosale
0.2841
PR #871by greqone
0.8004
PR #872by gowtham0992
1.0467
PR #876by Bortlesboat
0.5863
PR #887by anthony-maio
0.9642
PR #889by anthony-maio
0.9642
PR #890by sofiabod
0.4405
PR #891by robbiebusinessacc
1.1428
PR #892by robbiebusinessacc
1.1428
PR #893by aryanbhosale
0.1310
PR #896by MVPandey
1.1896
PR #908by albertorkive
1.1734
PR #909by sunnypatneedi
0.8609
PR #912by Bortlesboat
0.3461
PR #915by anthony-maio
0.9642
PR #916by Bortlesboat
0.3461
PR #918by haikosys
0.1653
PR #921by TimPietrusky
0.0939
PR #922by greqone
0.0972
PR #926by NandhuRajRK
0.8705
PR #932by anthony-maio
1.1580
PR #937by mihir-s-05
1.4457
PR #941by aptsalt
1.3620
PR #945by TimPietrusky
0.0274
PR #952by FlashyFlash3011
1.1144
PR #953by dexhunter
1.0722
PR #961by callithyia
0.0881
PR #963by sunnypatneedi
0.8609
PR #964by vivekvar-dl
1.3900
PR #967by dexhunter
1.0450
PR #974by anthony-maio
1.6542
PR #975by Abhishek8108
1.1216
PR #986by sofiabod
0.0830
PR #991by ibarrajo
1.1145
PR #995by dexhunter
1.0362
PR #1004by ibarrajo
1.1182
PR #1005by OnlyJundong
1.0853
PR #1006by NewyorkDev
1.1085
PR #1007by dillon-blake
1.2252
PR #1008by monkeyKingProgrammer
1.1538
PR #1033by Naazimsnh02
0.4311
PR #1037by TimPietruskyRunPod
1.1179
PR #1039by yufengli-oai
1.1184
PR #1043by okezue
1.1261
PR #1051by tejas-goyal
1.2826
PR #1056by sofiabod
0.0180
PR #1062by yaowubarbara
1.4508
PR #1066by adityakm24
1.1259
PR #1069by manfromnowhere143
1.1190
PR #1070by manfromnowhere143
1.1190
PR #1072by vimeto
1.1170
PR #1077by malc3om
1.1130
PR #1081by michaelwinczuk
1.1220
PR #1084by AnubhavBharadwaaj
1.1185
PR #1085by adityasasidhar
1.2831
PR #1086by Omrigotlieb
1.1349
PR #1087by Dhenenjay
1.1407
PR #1089by mikeapedia
1.1086
PR #1094by michaelwinczuk
0.4027
PR #1098by adityakm24
1.1187
PR #1099by Bortlesboat
1.1133
PR #1101by amrayach
1.1290
PR #1105by abaybektursun
1.2208
PR #1108by DbBested
1.1502
PR #1112by dillon-blake
1.2252
PR #1113by gowtham0992
1.3705
PR #1117by adityakm24
1.1187
PR #1118by adityakm24
1.1187
PR #1123by sisegod
1.1986
PR #1125by jainpranjal97
1.1946
PR #1126by AnirudhRahul
1.1091
PR #1127by dentity007
1.1311
PR #1128by AnubhavBharadwaaj
1.1154
PR #1129by EthanYangTW
1.1174
PR #1130by Gusanidas
1.1140
PR #1144by inFaaa
1.3572
PR #1148by aamodbhatt
1.1179
PR #1150by sahiee-dev
1.1151
PR #1166by Christopher-Lee-McClendon
1.1347
PR #1170by Christopher-Lee-McClendon
1.1199
PR #1171by EthanYangTW
1.1145
PR #1182by adityakm24
1.1227
PR #1184by icryo
0.9485
PR #1185by skoustav35
0.9641
PR #1209by andrewbaggio1
1.1064
PR #1216by SoHarshh
1.1574
PR #1221by amabito
1.1915
PR #1228by meinlebenswerk
1.1527
PR #1230by nestamidavaine
1.1163
PR #1231by nestamidavaine
1.1163
PR #1236by ibarrajo
1.1179
PR #1237by ibarrajo
1.1198
PR #1240by andrewbaggio1
1.1064
PR #1244by monkeyKingProgrammer
1.1443
PR #1246by deborahnelson8788726
0.9650
PR #1247by fahmitech
1.2208
PR #1252by ahmetdenizyilmaz
1.0713
PR #1269by Jtss-ux
1.1194
PR #1276by BiggerDABOSS
1.1100
PR #1278by GitGeeks
1.1147
PR #1284by tyrel-beede
1.1207
PR #1289by MatoTeziTanka
1.0819
PR #1296by aryanbhosale
1.0926
PR #1298by Omrigotlieb
1.1043
PR #1303by anthony-maio
0.9462
PR #1311by htrung1105
1.1303
PR #1313by anthony-maio
0.8637
PR #1318by renqianluo
1.0095
PR #1321by anthony-maio
0.7406
PR #1324by yahya010
0.8275
PR #1328by renqianluo
0.6361
PR #1329by renqianluo
0.6361
PR #1335by WeijieChen2017
1.1948
PR #1361by jorge-asenjo
1.1220
PR #1366by yunoshev
1.1371
PR #1368by JKSNS
0.8503
PR #1376by stukenov
0.7094
PR #1378by Rajat123456789
1.1711
PR #1386by Buld1n
1.1452
PR #1389by Rome-1
1.7270
PR #1399by AnubhavBharadwaaj
1.0898
PR #1405by anthony-maio
1.0856
PR #1408by aamodbhatt
1.0800
PR #1413by dexhunterRECORD
1.0828
PR #1414by Abhishek8108
0.7093
PR #1427by kjahan
1.2092
PR #1435by AbhayAnandUCSD
1.0980
PR #1437by dexhunter
1.0780
PR #1440by Mertyandimata
1.1026
PR #1444by hypnoastic
1.3081
PR #1446by LauraGomezjurado
1.0960
PR #1450by andrewbaggio1
1.0848
PR #1452by bsisduck
0.3509
PR #1454by bsisduck
0.3509
PR #1456by sisegod
1.1465
PR #1457by DilpreetBansi
1.1454
PR #1467by PhamPhuHoa-23
1.1056
PR #1472by trhgbao
1.2066
PR #1473by AVINASH0052
1.1156
PR #1492by bigbag
1.0810
PR #1493by bigbagRECORD
1.0810
PR #1499by dippatel1994
1.6323
PR #1512by Itssshikhar
1.1117
PR #1514by dexhunter
1.0798
PR #1515by dexhunter
1.0872
PR #1520by taka6745
1.0824
PR #1528by xiehuanyi
1.1104
PR #1536by dexhunter
1.0775
PR #1538by davie2009kh
1.1180
PR #1539by translatingthename
1.0587
PR #1541by bigbag
1.0778
PR #1546by SPThole
1.0850
PR #1548by dljr-github
1.3220
PR #1549by dljr-github
1.3220
PR #1550by translatingthename
1.0587
PR #1555by andrewbaggio1
1.0764
PR #1559by adityasasidhar
1.2498
PR #1568by yuitokyouni
1.1639
PR #1573by shivangbaveja
1.1464
PR #1583by codemath3000
1.0801
PR #1584by codemath3000
1.0752
PR #1585by codemath3000
1.0639
PR #1586by dexhunter
1.0749
PR #1600by sayujshah
1.2781
PR #1602by SPThole
1.0744
PR #1612by seekerPrice
1.5096
PR #1616by Vickyrrrrrr
1.4100
PR #1617by adityasasidhar
1.2192
PR #1619by AVINASH0052
1.1156
PR #1621by mrbese
1.1531
PR #1628by yu314-coder
1.1921
PR #1630by KevinChunye
1.1412
PR #1639by kunwar-vikrant
1.0832
PR #1646by sergeevii123
1.0909
PR #1658by AVINASH0052
1.0810
PR #1661by anderamondarainh-stack
1.1444
PR #1666by mrbese
1.1531
PR #1667by MarioPaerle
1.0714
PR #1670by dexhunter
1.0597
PR #1672by andrewbaggio1
1.0119
PR #1676by aazizyan
1.0788
PR #1683by yunoshev
1.1280
PR #1688by Buld1n
1.0809
PR #1689by chris-colinsky
1.0822
PR #1693by dexhunter
1.0573
PR #1696by kings-crown
1.1224
PR #1714by Anakintano
1.0857
PR #1715by G3sparky
1.0809
PR #1716by himanshudongre
1.0788
PR #1720by kiyoaki
1.0818
PR #1722by deborahnelson8788726
0.6580
PR #1724by Unwindology
1.1803
PR #1728by mikeapedia
1.0771
PR #1731by Victory963
1.0785
PR #1737by sakthivarshans
1.0723
PR #1747by swapp1990
1.0820
PR #1755by OE-GOD
1.0746
PR #1759by yijieyuan
1.0799

Hyperparameters Across PRs

pr_numberparameters
64{"dimensions":16,"total_dimensions":64}
175{"train_length":null,"eval_length":null}
218{"dimensions":16,"total_dimensions":64}
315{"dimensions":16,"total_dimensions":64}
327{"fraction":0.5}
330{"dimensions":"16/64"}
332{"dimensions":16}
334{"dimensions":16,"total_head_dims":64}
344{"dimensions":"16/64"}
351{"dimensions":16,"total_dimensions":64}
352{"dimensions":16,"total_dimensions":64}
356{"dimensions":16,"total_dimensions":64}
371{"dimensions":16}
374{"dimensions":16,"total_dimensions":64}
376{"rope_dims":16,"total_dims":64,"base":50000}
383{"dimensions":16,"base_dimensions":64}
388{"dimensions":16,"total_dimensions":64}
389{"dimensions":16,"total_head_dims":64}
397{"dimensions":16}
398{"dimensions":16}
399{"dimensions":16}
400{"dimensions":16}
401{"dimensions":16,"total_dimensions":64}
410{"dimensions":"16/64"}
413
414{"dimensions":"16/64"}
415{"train_length":16,"eval_length":64}
417{"train_fraction":16,"total_fraction":64}
418{"dimensions":16,"total_dimensions":64}
434{"head_dims_rotary":16,"head_dims_total":64,"fraction":0.25}
445{"16/64":true}
452{"dimensions":"16/64"}
453{"dimensions":16,"total_dimensions":64}
455{"dimensions":16,"base_dimensions":64}
458{"dimensions":"16/64"}
461{"dimensions":16,"total_dimensions":64}
462{"dimensions":16}
469{"dimensions":"16/64"}
473{"dimensions":16,"base":64}
477{"dimensions":16,"total_dimensions":64}
478{"dimensions":16,"total_dimensions":64}
481{"dimensions":"16/64"}
482{"dimensions":16,"total_dimensions":64}
485{"dimensions":16,"total_dimensions":64}
486{"dimensions":"16/64"}
487{"dimensions":16}
489{"rotary_dims":16,"total_dims":64}
492{"head_dims":"16/64"}
493{"dims_used":16,"total_dims":64}
498{"rope_dims":16,"total_dims":64}
499{"rope_dims":16,"total_dims":64}
503{"dimensions":"16/64"}
505{"dimensions":16}
507{"percentage":25}
508{"dimensions":16,"base_dimensions":64}
509{"dimensions":16}
516{"dimensions":"16/64"}
518{"dimensions":16,"total_dimensions":64}
526{"dimensions":16,"total_dimensions":64}
528{"dimensions":"16/64"}
529{"dimensions":"16/64"}
532{"dimensions":"16/64"}
533{"numerator":16,"denominator":64}
534{"dimensions":16,"total_dimensions":64}
535{"dimensions":"16/64"}
537{"dimensions":"16/64"}
543{"rotary_dims":16,"total_dims":64,"position_free_ratio":0.75}
545{"train_length":null,"eval_length":null}
549{"dimensions":16}
564{"dimensions":16,"total_dimensions":64}
573{"dimensions":16,"total_head_dims":64}
576{"ratio":"16/64"}
577{"scaling":"16/64"}
585{"ratio":"16/64"}
586{"dimensions":16}
592{"dimensions":16}
593{"dimensions":16,"total_dimensions":64}
598{"dims":16,"total_dims":64,"train_seq_len":1024}
601{"dimensions":16}
606{"partial_rope":"16/64"}
609{"partial_rope":"16/64"}
612{"dims":"16/64","train_seq":2048}
634{"dimensions":"16/64"}
635{"dimensions":"16/64"}
638{"train_dims":16,"total_dims":64}
642{"dimensions":"16/64"}
644{"dims":"16/64","train_seq":2048}
645
653{"dims":"16/64"}
657{"dimensions":"16/64"}
661{"dimensions":16}
668{"dimensions":16}
672{"dimensions":16}
682{"dimensions":16}
685
688{"dimensions":"16/64"}
690{"train_length":16,"eval_length":64}
692{"train_length":16,"eval_length":64}
693{"dimensions":"16/64"}
695{"dimensions":"16/64"}
698{"dimensions":16}
703{"dimensions":16}
710{"dimensions":16,"total_dimensions":64}
714{"dimensions":16,"total_dimensions":64}
715{"dimensions":"16/64"}
720{"dimensions":16,"total_dimensions":64}
726{"dimensions":"16/64"}
727{"dimensions":"16/64"}
728{"dimensions":16,"base_dimensions":64}
734{"dimensions":"16/64"}
740{"percentage":25}
741
752{"dimensions":16,"total_dimensions":64}
754{"dimensions":"16/64"}
761{"dimensions":16,"total_dimensions":64}
768{"dimensions":[16,64]}
770{"train_length":null,"eval_length":null}
774{"dimensions":16}
778{"train_or_eval":null,"dimensions":"16/64"}
779{"dimensions":"16/64"}
786{"dimensions":16}
794{"dimensions":"16/64"}
796{"rope_dims":16,"total_dims":64}
802{"fraction":"16/64"}
808{"dimensions":16}
809{"dims":"16/64"}
816{"dimensions":"16/64"}
826{"dims":"16/64"}
827{"dimensions":16,"total_dimensions":64}
828{"dimensions":"16/64"}
832{"dimensions":16}
836{"dimensions":"16/64"}
838{"dimensions":"16/64"}
841
849{"dimensions":"16/64"}
857{"train":16,"total":64}
864{"dimensions":"16/64"}
865{"dimensions":"16/64"}
871{"train":16,"total":64}
872{"dimensions":16,"total_dimensions":64}
876
887{"train_length":16,"eval_length":64}
889{"train":16,"eval":64}
890{"dimensions":"16/64"}
891{"dimensions":"16/64"}
892{"dimensions":"16/64"}
893{"16/64":true}
896
908{"dimensions":16}
909{"dimensions":"16/64"}
912
915{"dimensions":"16/64"}
916{"ratio":"16/64"}
918{"dimensions":16}
921{"dimensions":64}
922{"train_eval_ratio":"16/64"}
926
932{"train_length":64,"eval_length":16}
937{"dimensions":32}
941{"dimensions":16,"total_dimensions":64}
945{"dimensions":16}
952{"dimensions":"16/64"}
953{"dimensions":"16/64"}
961{"numerator":16,"denominator":64}
963{"dimensions":"16/64"}
964{"train":"16/64"}
967{"dimensions":"16/64"}
974
975{"dimensions":16,"base_dimensions":64}
986{"fraction":"16/64"}
991{"dimensions":16}
995
1004{"dimensions":16}
1005{"dimensions":16,"total_dimensions":64}
1006{"dimensions":16}
1007{"dimensions":16,"total_dimensions":64}
1008{"dimensions":"16/64"}
1033{"dimensions":16}
1037{"dimensions":16}
1039{"dimensions":16}
1043{"dimensions":16,"total_dimensions":64}
1051
1056{"dimensions":"16/64"}
1062{"range":"16/64"}
1066{"dimensions":16}
1069{"partial":"16/64"}
1070{"head_dims":16,"total_head_dims":64}
1072{"dimensions":"16/64"}
1077{"rope_dims":16,"total_dims":64}
1081
1084{"dimensions":16}
1085{"dimensions":16}
1086{"rotated_dims":16,"total_dims":64}
1087{"dimensions":16,"total_dimensions":64}
1089{"dimensions":16}
1094
1098{"rope_dims":16}
1099{"dimensions":16}
1101{"rotated_dims":16,"total_dims":64}
1105{"partial":"16/64"}
1108{"dimensions":16}
1112{"dimensions":16,"total_dimensions":64}
1113{"dimensions":"16/64"}
1117{"rope_dims":16}
1118{"dimensions":16}
1123{"dimensions":16}
1125{"dimensions":"16/64"}
1126{"dimensions":16,"total_dimensions":64}
1127{"dimensions":"16/64"}
1128{"dimensions":16}
1129{"train_fraction":16,"total_fraction":64}
1130{"dimensions":"16/64"}
1144{"dimensions":16,"total_dimensions":64,"fraction":0.25}
1148{"dimensions":16}
1150{"rope_dims":16}
1166{"dimensions":16}
1170{"dimensions":16,"base":10000}
1171{"fraction":"16/64"}
1182{"dimensions":16}
1184{"dimensions":16}
1185{"dimensions":"16/64"}
1209{"dimensions":16}
1216{"dimensions":"16/64"}
1221{"dimensions":16}
1228
1230{"dimensions":16}
1231{"dimensions":"16/64"}
1236{"dimensions":16}
1237{"dimensions":"16/64"}
1240{"dimensions":16}
1244{"rope_dims":16,"total_dims":64}
1246{"dimensions":16,"total_dimensions":96}
1247{"dimensions":16}
1252
1269{"dimensions":16,"total_dimensions":64}
1276{"dimensions":16}
1278
1284{"dims":"16/64"}
1289{"dimensions":16}
1296{"dimensions":16}
1298{"dimensions":16}
1303{"train_fraction":16,"total_fraction":64}
1311{"dimensions":16,"total_dimensions":64}
1313{"train_eval_ratio":"16/64"}
1318{"dimensions":16}
1321{"partial":"16/64"}
1324{"train":16,"eval":64}
1328{"dimensions":16}
1329{"dimensions":16}
1335{"dimensions":"16/64"}
1361{"rotary_dims":16,"head_dims":64}
1366{"percent":25}
1368{"dimensions":16,"total_dimensions":64}
1376{"partial":"16/64"}
1378{"dimensions":16,"total_dimensions":64}
1386{"dimensions":16}
1389{"dimensions":"16/64"}
1399{"dimensions":16}
1405{"numerator":16,"denominator":64}
1408{"dimensions":16}
1413{"dimensions":16}
1414{"dimensions":16,"base":64}
1427{"dimensions":16,"head_dimensions":64}
1435{"dims":"16/64"}
1437{"dimensions":16,"total_dimensions":64}
1440{"dimensions":16}
1444{"ratio":"16/64"}
1446{"dims":"16/64"}
1450{"dimensions":16,"total_dimensions":64}
1452{"dimensions":"16/64"}
1454{"dimensions":16,"total_dimensions":64}
1456{"rope_dims":16,"head_dims":64}
1457{"dimensions":16}
1467{"dimensions":16,"base_dimensions":64}
1472{"dimensions":16,"total_dimensions":64}
1473{"dimensions":16,"total_dimensions":64}
1492{"dimensions":"16/64"}
1493{"dimensions":"16/64"}
1499{"dimensions":16}
1512{"offset":1}
1514{"dimensions":16}
1515{"dimensions":"16/64"}
1520{"dimensions":16,"base_dimensions":64}
1528{"dimensions":16,"denominator":64}
1536{"dimensions":16,"base_dimensions":64}
1538{"dimensions":16,"total_dimensions":64}
1539{"dimensions":16,"total_dimensions":64}
1541{"dimensions":"16/64"}
1546{"dimensions":"16/64"}
1548{"dimensions":16}
1549{"dimensions":16}
1550{"dimensions":"16/64"}
1555{"dimensions":"16/64"}
1559{"dimensions":32}
1568{"dimensions":16}
1573{"dimensions":16,"total_dimensions":64}
1583{"dimensions":16,"total_dimensions":64}
1584{"dimensions":"16/64"}
1585{"partial_ratio":"16/64"}
1586{"dimensions":"16/64"}
1600{"dimensions":16}
1602{"rope_dims":16,"head_dims":64}
1612{"dimensions":16}
1616{"dimensions":16,"total_dimensions":64}
1617{"dimensions":32}
1619{"head_dims":16,"total_head_dims":64}
1621{"dimensions":16}
1628{"dimensions":16,"total_dimensions":64}
1630{"dimensions":16,"total_dimensions":64}
1639{"layers":"16/64"}
1646{"ratio":"16/64"}
1658{"dimensions":16,"total_dimensions":64}
1661{"dimensions":16,"total_dimensions":64}
1666{"dimensions":16}
1667{"dimensions":"16/64"}
1670{"dimensions":"16/64"}
1672{"dimensions":"16/64"}
1676{"dimensions":16,"total_dimensions":64}
1683{"ratio":0.25}
1688{"dimensions":"16/64"}
1689{"dimensions":16,"total_dimensions":64}
1693{"dimensions":16,"total_dimensions":64}
1696{"dimensions":"16/64"}
1714{"dimensions":16}
1715{"dimensions":16,"total_dimensions":64}
1716{"dimensions":"16/64"}
1720{"dimensions":"16/64"}
1722{"dimensions":"16/64"}
1724
1728{"layers":[4,9,10],"rope_dims":16,"head_dim":64}
1731{"dimensions":16}
1737{"dimensions":16,"total_dimensions":64}
1747{"dimensions":16,"head_dim":64}
1755{"dimensions":16,"total_dimensions":64}
1759{"dimensions":16,"total_dimensions":64}