← Back to Architecture
Value Residual
ArchitectureUsed in
69 PRs
Best BPB
0.0235
Avg BPB
0.9650
Submissions
PR #344by aryanbhosale
1.1330PR #413by anantdgoel
1.4525PR #430by sahiee-dev
1.1428PR #474by joshuaswarren
1.1690PR #487by anantdgoel
1.1720PR #562by bigbag
1.1354PR #638by Asukabot0
1.1164PR #715by Asukabot0
1.0337PR #727by Asukabot0
0.9674PR #754by aryanbhosale
1.1253PR #758by hypery11
1.0465PR #761by Asukabot0
0.9581PR #763by hypery11
0.9917PR #788by hypery11
0.9059PR #795by hypery11
0.8881PR #813by hypery11
0.6671PR #828by bigbag
0.9076PR #838by aryanbhosale
1.1215PR #862by grim-hitman0XX
1.3036PR #864by aryanbhosale
0.2841PR #865by aryanbhosale
0.2841PR #871by greqone
0.8004PR #872by gowtham0992
1.0467PR #876by Bortlesboat
0.5863PR #893by aryanbhosale
0.1310PR #895by iverbovoy
1.0889PR #912by Bortlesboat
0.3461PR #916by Bortlesboat
0.3461PR #921by TimPietrusky
0.0939PR #922by greqone
0.0972PR #940by antaloaalonso
0.9581PR #952by FlashyFlash3011
1.1144PR #960by ADIITJ
1.1882PR #1001by ibarrajo
1.1188PR #1007by dillon-blake
1.2252PR #1015by shram86
1.2115PR #1016by ADIITJ
1.1269PR #1033by Naazimsnh02
0.4311PR #1045by Hilo-Hilo
1.1509PR #1112by dillon-blake
1.2252PR #1114by minh-stakc
0.0235PR #1117by adityakm24
1.1187PR #1123by sisegod
1.1986PR #1139by ivanontech
1.1801PR #1141by ivanontech
1.1801PR #1159by JDAppleseed
0.3693PR #1170by Christopher-Lee-McClendon
1.1199PR #1182by adityakm24
1.1227PR #1185by skoustav35
0.9641PR #1200by Mister2005
1.6768PR #1201by Mister2005
1.6371PR #1218by clarkkevRECORD
1.0978PR #1232by Christopher-Lee-McClendon
1.0929PR #1233by ibarrajo
1.1460PR #1287by dentity007
1.1048PR #1311by htrung1105
1.1303PR #1324by yahya010
0.8275PR #1396by erichroepke
1.1067PR #1452by bsisduck
0.3509PR #1454by bsisduck
0.3509PR #1456by sisegod
1.1465PR #1488by ndokutovich
0.8265PR #1499by dippatel1994
1.6323PR #1556by sidhanth97
1.4352PR #1573by shivangbaveja
1.1464PR #1602by SPThole
1.0744PR #1621by mrbese
1.1531PR #1666by mrbese
1.1531PR #1683by yunoshev
1.1280Hyperparameters Across PRs
| pr_number | parameters |
|---|---|
| 344 | — |
| 413 | {"layers":9,"learnable_scalars":18} |
| 430 | {"layers":10} |
| 474 | — |
| 487 | {"added_params":22} |
| 562 | — |
| 638 | — |
| 715 | — |
| 727 | — |
| 754 | — |
| 758 | — |
| 761 | — |
| 763 | — |
| 788 | — |
| 795 | — |
| 813 | — |
| 828 | — |
| 838 | — |
| 862 | {"layers":"1-8"} |
| 864 | — |
| 865 | — |
| 871 | — |
| 872 | — |
| 876 | — |
| 893 | — |
| 895 | {"tables":2} |
| 912 | — |
| 916 | — |
| 921 | {"value_embedding_layers":[8,9,10]} |
| 922 | — |
| 940 | — |
| 952 | {"lambda_init":[0.5,0.5]} |
| 960 | {"layers":11} |
| 1001 | — |
| 1007 | — |
| 1015 | {"layers":2,"dimension":128} |
| 1016 | {"layers":10} |
| 1033 | — |
| 1045 | — |
| 1112 | {"layers":[9,10]} |
| 1114 | — |
| 1117 | — |
| 1123 | — |
| 1139 | {"params":"31.5M"} |
| 1141 | {"parameters":31500000} |
| 1159 | {"enabled":0} |
| 1170 | — |
| 1182 | — |
| 1185 | — |
| 1200 | — |
| 1201 | — |
| 1218 | — |
| 1232 | — |
| 1233 | — |
| 1287 | — |
| 1311 | {"enabled":false} |
| 1324 | {"init":-1.5} |
| 1396 | {"layers":[9,10]} |
| 1452 | {"layers":"1-8"} |
| 1454 | {"layers":"1-8"} |
| 1456 | — |
| 1488 | — |
| 1499 | {"alpha":0.95} |
| 1556 | — |
| 1573 | — |
| 1602 | — |
| 1621 | {"dimension":128,"layers":[9,10]} |
| 1666 | {"dim":128,"layers":[9,10]} |
| 1683 | — |