Files
DS4Server/assets/models/qwen38-flash-next-bare-speed-tensors.tsv
2026-09-03 19:15:53 +02:00

342 KiB

1filenamedtypeshapequant_bitsgroup_sizequant_modedata_startdata_end
2model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine38010919503827306350
3model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine20185127502044727150
4model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine42467367504666167150
5model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine498077550524291950
6model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine524291950550506350
7model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine33816615503801091950
8model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine24903719502516586350
9model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine10223655501048579950
10model-00001-of-00017.safetensorslanguage_model.model.layers.0.mlp.switch_mlp.up_proj.weightU32512x640x320464affine20447271502464157550
11model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine15204391501546653550
12model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine24641575502490371950
13model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine15990823502018512750
14model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine15728679501599082350
15model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine14942247501520439150
16model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine29622311503381661550
17model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine29360167502962231150
18model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine10485799501074794350
19model-00001-of-00017.safetensorslanguage_model.model.layers.1.mlp.switch_mlp.up_proj.weightU32512x640x320464affine10747943501494224750
20model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine15466535501572867950
21model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine576720750602935150
22model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine38273063504246736750
23model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine471863150498077550
24model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine550506350576720750
25model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine25165863502936016750
26model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine419434350445648750
27model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine445648750471863150
28model-00001-of-00017.safetensorslanguage_model.model.layers.10.mlp.switch_mlp.up_proj.weightU32512x640x320464affine3950419434350
29model-00001-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine6029351501022365550
30model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine42729513124299165712
31model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine32243753123250589712
32model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine33030185123329232912
33model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine33554473123381661712
34model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine13893673121808797712
35model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine18350121121861226512
36model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine23593001122385514512
37model-00002-of-00017.safetensorslanguage_model.model.layers.11.mlp.switch_mlp.up_proj.weightU32512x640x320464affine38535209124272951312
38model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine32505897123276804112
39model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine33292329123355447312
40model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine23855145122804944912
41model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine32768041123303018512
42model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine23330857122359300112
43model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine18612265122280656912
44model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine18087977121835012112
45model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine23068713122333085712
46model-00002-of-00017.safetensorslanguage_model.model.layers.12.mlp.switch_mlp.up_proj.weightU32512x640x320464affine34340905123853520912
47model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine33816617123407876112
48model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine34078761123434090512
49model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine524292112943722512
50model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine22806569122306871312
51model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine498077712524292112
52model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine9699369121389367312
53model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine943722512969936912
54model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine471863312498077712
55model-00002-of-00017.safetensorslanguage_model.model.layers.13.mlp.switch_mlp.up_proj.weightU32512x640x320464affine28049449123224375312
56model-00002-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine445648912471863312
57model-00002-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine411226218512
58model-00002-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine26218512445648912
59model-00003-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine19922983682018512768
60model-00003-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine28835879682909802368
61model-00003-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine42467367684666167168
62model-00003-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine14155815681441795968
63model-00003-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine19398695681966083968
64model-00003-of-00017.safetensorslanguage_model.model.layers.14.mlp.switch_mlp.up_proj.weightU32512x640x320464affine498077568917507968
65model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine28573735682883587968
66model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine41943079684220522368
67model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine15204391681939869568
68model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine14417959681468010368
69model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine14680103681494224768
70model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine33554471683774877568
71model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine19660839681992298368
72model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine14942247681520439168
73model-00003-of-00017.safetensorslanguage_model.model.layers.15.mlp.switch_mlp.up_proj.weightU32512x640x320464affine20185127682437943168
74model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine917507968943722368
75model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine13893671681415581568
76model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine9437223681363152768
77model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine13631527681389367168
78model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine42205223684246736768
79model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine37748775684194307968
80model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine2621836852432768
81model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine471863168498077568
82model-00003-of-00017.safetensorslanguage_model.model.layers.16.mlp.switch_mlp.up_proj.weightU32512x640x320464affine29360167683355447168
83model-00003-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine29098023682936016768
84model-00003-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine396826218368
85model-00003-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine52432768471863168
86model-00003-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine24379431682857373568
87model-00004-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine37224489023748663302
88model-00004-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine42467369024272951302
89model-00004-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine27787305022804944902
90model-00004-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine42205225024246736902
91model-00004-of-00017.safetensorslanguage_model.model.layers.17.mlp.switch_mlp.up_proj.weightU32512x640x320464affine28049449023224375302
92model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine23068713022333085702
93model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine41680937024194308102
94model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine37486633024168093702
95model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine32243753023250589702
96model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine32505897023276804102
97model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine32768041023696234502
98model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine22806569022306871302
99model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine943722502969936902
100model-00004-of-00017.safetensorslanguage_model.model.layers.18.mlp.switch_mlp.up_proj.weightU32512x640x320464affine23330857022752516102
101model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine42729513024299165702
102model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine18350121021861226502
103model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine18612265022280656902
104model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine891293702917508102
105model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine917508102943722502
106model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine9961513021415581702
107model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine865079302891293702
108model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine969936902996151302
109model-00004-of-00017.safetensorslanguage_model.model.layers.19.mlp.switch_mlp.up_proj.weightU32512x640x320464affine14155817021835012102
110model-00004-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine27525161022778730502
111model-00004-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine41943081024220522502
112model-00004-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine445648902865079302
113model-00004-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine36962345023722448902
114model-00004-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine410226218502
115model-00004-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine26218502445648902
116model-00005-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine37486631693774877569
117model-00005-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine28311591692857373569
118model-00005-of-00017.safetensorslanguage_model.model.layers.2.mlp.switch_mlp.up_proj.weightU32512x640x320464affine37748775694194307969
119model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine46399527694666167169
120model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine46137383694639952769
121model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine23592999692778730369
122model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine28573735692883587969
123model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine33030183693329232769
124model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine9175079691336938369
125model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine27787303692804944769
126model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine14417959691468010369
127model-00005-of-00017.safetensorslanguage_model.model.layers.20.mlp.switch_mlp.up_proj.weightU32512x640x320464affine28835879693303018369
128model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine13893671691415581569
129model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine14680103691494224769
130model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine19136551692333085569
131model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine14155815691441795969
132model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine28049447692831159169
133model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine33292327693748663169
134model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine13369383691363152769
135model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine13631527691389367169
136model-00005-of-00017.safetensorslanguage_model.model.layers.21.mlp.switch_mlp.up_proj.weightU32512x640x320464affine41943079694613738369
137model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine891293569917507969
138model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine23330855692359299969
139model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine14942247691913655169
140model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine419434369445648769
141model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine445648769471863169
142model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine471863169891293569
143model-00005-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.up_proj.weightU32512x640x320464affine3969419434369
144model-00006-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine42467369084272951308
145model-00006-of-00017.safetensorslanguage_model.model.layers.22.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine42729513084299165708
146model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine37748777083801092108
147model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine33030185083329232908
148model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine38273065084246736908
149model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine13631529081389367308
150model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine26738729082700087308
151model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine22544425082673872908
152model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine28573737082883588108
153model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine27000873082726301708
154model-00006-of-00017.safetensorslanguage_model.model.layers.23.mlp.switch_mlp.up_proj.weightU32512x640x320464affine18350121082254442508
155model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine18087977081835012108
156model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine445648908471863308
157model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine13893673081808797708
158model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine28049449082831159308
159model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine28311593082857373708
160model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine28835881083303018508
161model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine917508108943722508
162model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine27525161082778730508
163model-00006-of-00017.safetensorslanguage_model.model.layers.24.mlp.switch_mlp.up_proj.weightU32512x640x320464affine9437225081363152908
164model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine471863308498077708
165model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine37486633083774877708
166model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine498077708917508108
167model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine27787305082804944908
168model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine27263017082752516108
169model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine33292329083748663308
170model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine38010921083827306508
171model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine410826218508
172model-00006-of-00017.safetensorslanguage_model.model.layers.25.mlp.switch_mlp.up_proj.weightU32512x640x320464affine26218508445648908
173model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine37748775683801091968
174model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine42205223684246736768
175model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine42467367684666167168
176model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine37224487683748663168
177model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine36962343683722448768
178model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine38010919684220522368
179model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine32505895683276803968
180model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine27525159682778730368
181model-00007-of-00017.safetensorslanguage_model.model.layers.26.mlp.switch_mlp.up_proj.weightU32512x640x320464affine13631527681782583168
182model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine27263015682752515968
183model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine28049447682831159168
184model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine28311591683250589568
185model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine27000871682726301568
186model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine22544423682280656768
187model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine22806567682700087168
188model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine17825831681808797568
189model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine471863168498077568
190model-00007-of-00017.safetensorslanguage_model.model.layers.27.mlp.switch_mlp.up_proj.weightU32512x640x320464affine18087975682228227968
191model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine22282279682254442368
192model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine917507968943722368
193model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine9437223681363152768
194model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine37486631683774877568
195model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine27787303682804944768
196model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine498077568917507968
197model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine396826218368
198model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine2621836852432768
199model-00007-of-00017.safetensorslanguage_model.model.layers.28.mlp.switch_mlp.up_proj.weightU32512x640x320464affine52432768471863168
200model-00007-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine32768039683696234368
201model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine36962344973722448897
202model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine23593000972385514497
203model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine498077697524292097
204model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine42467368974272951297
205model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine23855144972804944897
206model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine550506497576720897
207model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine37224488973748663297
208model-00008-of-00017.safetensorslanguage_model.model.layers.29.mlp.switch_mlp.up_proj.weightU32512x640x320464affine37486632974168093697
209model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine32243752973250589697
210model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine36700200973696234497
211model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine19398696972359300097
212model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine42205224974246736897
213model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine19136552971939869697
214model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine6029352971022365697
215model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine42729512974299165697
216model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine14417960971468010497
217model-00008-of-00017.safetensorslanguage_model.model.layers.3.mlp.switch_mlp.up_proj.weightU32512x640x320464affine32505896973670020097
218model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine14680104971494224897
219model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine41943080974220522497
220model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine14942248971913655297
221model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine524292097550506497
222model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine576720897602935297
223model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine10223656971441796097
224model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine2621849752432897
225model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine5243289778647297
226model-00008-of-00017.safetensorslanguage_model.model.layers.30.mlp.switch_mlp.up_proj.weightU32512x640x320464affine78647297498077697
227model-00008-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine409726218497
228model-00008-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine41680936974194308097
229model-00008-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine28049448973224375297
230model-00009-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine46137383624639952762
231model-00009-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine14680103621494224762
232model-00009-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine33030183623722448762
233model-00009-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine32505895623276803962
234model-00009-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine45875239624613738362
235model-00009-of-00017.safetensorslanguage_model.model.layers.31.mlp.switch_mlp.up_proj.weightU32512x640x320464affine37224487624141879162
236model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine23855143622411728762
237model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine45613095624587523962
238model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine24117287622831159162
239model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine32768039623303018362
240model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine46399527624666167162
241model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine19398695622359299962
242model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine14942247621520439162
243model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine524291962550506362
244model-00009-of-00017.safetensorslanguage_model.model.layers.32.mlp.switch_mlp.up_proj.weightU32512x640x320464affine15204391621939869562
245model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine23592999622385514362
246model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine9961511621022365562
247model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine10223655621441795962
248model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine14417959621468010362
249model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine498077562524291962
250model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine550506362969936762
251model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine969936762996151162
252model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine5243276278647162
253model-00009-of-00017.safetensorslanguage_model.model.layers.33.mlp.switch_mlp.up_proj.weightU32512x640x320464affine78647162498077562
254model-00009-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine396226218362
255model-00009-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine2621836252432762
256model-00009-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine28311591623250589562
257model-00009-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine41418791624561309562
258model-00010-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine24379433082464157708
259model-00010-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine18612265081887440908
260model-00010-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine34078761083434090508
261model-00010-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine33816617083407876108
262model-00010-of-00017.safetensorslanguage_model.model.layers.34.mlp.switch_mlp.up_proj.weightU32512x640x320464affine29622313083381661708
263model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine25165865082542800908
264model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine24641577082490372108
265model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine25428009082962231308
266model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine23855145082411728908
267model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine19136553081939869708
268model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine38535209084272951308
269model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine24117289082437943308
270model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine18874409081913655308
271model-00010-of-00017.safetensorslanguage_model.model.layers.35.mlp.switch_mlp.up_proj.weightU32512x640x320464affine19660841082385514508
272model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine24903721082516586508
273model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine19398697081966084108
274model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine34340905083853520908
275model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine943722508969936908
276model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine14155817081441796108
277model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine14417961081861226508
278model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine42729513084299165708
279model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine969936908996151308
280model-00010-of-00017.safetensorslanguage_model.model.layers.36.mlp.switch_mlp.up_proj.weightU32512x640x320464affine524292108943722508
281model-00010-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine445648908471863308
282model-00010-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine471863308498077708
283model-00010-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine9961513081415581708
284model-00010-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine498077708524292108
285model-00010-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine410826218508
286model-00010-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine26218508445648908
287model-00011-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine498077559524291959
288model-00011-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine42205223594246736759
289model-00011-of-00017.safetensorslanguage_model.model.layers.37.mlp.switch_mlp.up_proj.weightU32512x640x320464affine42467367594666167159
290model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine41680935594194307959
291model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine32243751593250589559
292model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine18350119592254442359
293model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine41943079594220522359
294model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine36700199593696234359
295model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine13631527591782583159
296model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine27263015592752515959
297model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine27525159592778730359
298model-00011-of-00017.safetensorslanguage_model.model.layers.38.mlp.switch_mlp.up_proj.weightU32512x640x320464affine32505895593670019959
299model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine18087975591835011959
300model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine27000871592726301559
301model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine37486631594168093559
302model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine36962343593722448759
303model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine37224487593748663159
304model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine9437223591363152759
305model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine471863159498077559
306model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine31981607593224375159
307model-00011-of-00017.safetensorslanguage_model.model.layers.39.mlp.switch_mlp.up_proj.weightU32512x640x320464affine524291959943722359
308model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine26738727592700087159
309model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine17825831591808797559
310model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine22544423592673872759
311model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine395926218359
312model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine2621835952432759
313model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine52432759471863159
314model-00011-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.up_proj.weightU32512x640x320464affine27787303593198160759
315model-00012-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine42467369064272951306
316model-00012-of-00017.safetensorslanguage_model.model.layers.4.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine42729513064299165706
317model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine18612265061887440906
318model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine36962345063722448906
319model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine38010921064220522506
320model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine27787305062804944906
321model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine37486633063774877706
322model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine28311593063250589706
323model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine23330857062359300106
324model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine37224489063748663306
325model-00012-of-00017.safetensorslanguage_model.model.layers.40.mlp.switch_mlp.up_proj.weightU32512x640x320464affine13631529061782583306
326model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine23068713062333085706
327model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine17825833061808797706
328model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine23593001062778730506
329model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine917508106943722506
330model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine18350121061861226506
331model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine18874409062306871306
332model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine36700201063696234506
333model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine18087977061835012106
334model-00012-of-00017.safetensorslanguage_model.model.layers.41.mlp.switch_mlp.up_proj.weightU32512x640x320464affine9437225061363152906
335model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine471863306498077706
336model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine28049449062831159306
337model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine498077706917508106
338model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine445648906471863306
339model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine37748777063801092106
340model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine32505897063670020106
341model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine42205225064246736906
342model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine410626218506
343model-00012-of-00017.safetensorslanguage_model.model.layers.42.mlp.switch_mlp.up_proj.weightU32512x640x320464affine26218506445648906
344model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine38010919743827306374
345model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine37748775743801091974
346model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine42467367744666167174
347model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine30933031743119517574
348model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine37486631743774877574
349model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine17825831742202013574
350model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine32243751743250589574
351model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine37224487743748663174
352model-00013-of-00017.safetensorslanguage_model.model.layers.43.mlp.switch_mlp.up_proj.weightU32512x640x320464affine38273063744246736774
353model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine31195175743145731974
354model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine31981607743224375174
355model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine32505895743670019974
356model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine31719463743198160774
357model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine36962343743722448774
358model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine26738727743093303174
359model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine31457319743171946374
360model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine22020135742228227974
361model-00013-of-00017.safetensorslanguage_model.model.layers.44.mlp.switch_mlp.up_proj.weightU32512x640x320464affine22544423742673872774
362model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine36700199743696234374
363model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine17563687741782583174
364model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine13369383741756368774
365model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine865079174891293574
366model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine891293574917507974
367model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine9175079741336938374
368model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine22282279742254442374
369model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine419434374445648774
370model-00013-of-00017.safetensorslanguage_model.model.layers.45.mlp.switch_mlp.up_proj.weightU32512x640x320464affine445648774865079174
371model-00013-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine3974419434374
372model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine14155817041441796104
373model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine14417961041468010504
374model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine41680937044194308104
375model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine42729513044299165704
376model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine32505897043670020104
377model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine19136553041939869704
378model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine28049449042831159304
379model-00014-of-00017.safetensorslanguage_model.model.layers.46.mlp.switch_mlp.up_proj.weightU32512x640x320464affine36962345044115664904
380model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine42205225044246736904
381model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine41943081044220522504
382model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine28311593043250589704
383model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine27787305042804944904
384model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine14680105041494224904
385model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine23593001042778730504
386model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine13893673041415581704
387model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine41418793044168093704
388model-00014-of-00017.safetensorslanguage_model.model.layers.47.mlp.switch_mlp.up_proj.weightU32512x640x320464affine19398697042359300104
389model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine36700201043696234504
390model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine917508104943722504
391model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine9437225041363152904
392model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine41156649044141879304
393model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine865079304891293704
394model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine14942249041913655304
395model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine42467369044272951304
396model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine419434504445648904
397model-00014-of-00017.safetensorslanguage_model.model.layers.5.mlp.switch_mlp.up_proj.weightU32512x640x320464affine445648904865079304
398model-00014-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine13631529041389367304
399model-00014-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine891293704917508104
400model-00014-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine4104419434504
401model-00015-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine27787303462804944746
402model-00015-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine42205223464246736746
403model-00015-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine23592999462778730346
404model-00015-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine28311591462857373546
405model-00015-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine28573735462883587946
406model-00015-of-00017.safetensorslanguage_model.model.layers.6.mlp.switch_mlp.up_proj.weightU32512x640x320464affine37748775464194307946
407model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine23330855462359299946
408model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine28049447462831159146
409model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine42467367464666167146
410model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine22806567462306871146
411model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine23068711462333085546
412model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine33554471463774877546
413model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine28835879462909802346
414model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine29098023462936016746
415model-00015-of-00017.safetensorslanguage_model.model.layers.7.mlp.switch_mlp.up_proj.weightU32512x640x320464affine18612263462280656746
416model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine13369383461363152746
417model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine13893671461415581546
418model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine14155815461835011946
419model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine41943079464220522346
420model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine891293546917507946
421model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine9175079461336938346
422model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine419434346445648746
423model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine13631527461389367146
424model-00015-of-00017.safetensorslanguage_model.model.layers.8.mlp.switch_mlp.up_proj.weightU32512x640x320464affine471863146891293546
425model-00015-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.down_proj.biasesBF16512x2560x10464affine18350119461861226346
426model-00015-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.down_proj.scalesBF16512x2560x10464affine445648746471863146
427model-00015-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.down_proj.weightU32512x2560x80464affine3946419434346
428model-00015-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.gate_proj.weightU32512x640x320464affine29360167463355447146
429model-00016-of-00017.safetensorslanguage_model.lm_head.biasesBF16248320x40464affine16131063481632971948
430model-00016-of-00017.safetensorslanguage_model.lm_head.scalesBF16248320x40464affine858405156878270756
431model-00016-of-00017.safetensorslanguage_model.lm_head.weightU32248320x320464affine31274260763445275676
432model-00016-of-00017.safetensorslanguage_model.model.embed_tokens.biasesBF16248320x40464affine25828307962602696396
433model-00016-of-00017.safetensorslanguage_model.model.embed_tokens.scalesBF16248320x40464affine24543823322474247932
434model-00016-of-00017.safetensorslanguage_model.model.embed_tokens.weightU32248320x320464affine26263876602944237260
435model-00016-of-00017.safetensorslanguage_model.model.hyper_connection_mixer.hc_norm.weightBF161024020355951642035615644
436model-00016-of-00017.safetensorslanguage_model.model.hyper_connection_mixer.input_mix_weight_down.weightBF16320x1024034901834523496737052
437model-00016-of-00017.safetensorslanguage_model.model.hyper_connection_mixer.input_mix_weight_up.weightBF1610240x32029442782202950831820
438model-00016-of-00017.safetensorslanguage_model.model.layers.0.attn_hyper_connection.block_inject_weight.weightBF164x1024023393751802339457100
439model-00016-of-00017.safetensorslanguage_model.model.layers.0.attn_hyper_connection.hc_norm.weightBF161024012323679481232388428
440model-00016-of-00017.safetensorslanguage_model.model.layers.0.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024025236396602530193260
441model-00016-of-00017.safetensorslanguage_model.model.layers.0.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32042562962844262849884
442model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.A_logBF164837969497563796949852
443model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.conv1d.weightBF1610240x4x137529133243752995244
444model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.dt_biasBF1648443286612443286708
445model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_a.biasesBF1648x40464affine23008714202300875260
446model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_a.scalesBF1648x40464affine26263019002626305740
447model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_a.weightU3248x320464affine42826028444282664284
448model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_b.biasesBF1648x40464affine24271873722427191212
449model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_b.scalesBF1648x40464affine16012611321601264972
450model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_b.weightU3248x320464affine11163993321116460772
451model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_qkv.biasesBF1610240x40464affine35725200443573339244
452model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_qkv.scalesBF1610240x40464affine34523207963453139996
453model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_qkv.weightU3210240x320464affine10199125801033019780
454model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_z.biasesBF166144x40464affine38069958043807487324
455model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_z.scalesBF166144x40464affine37758407643776332284
456model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.in_proj_z.weightU326144x320464affine37882047963796069116
457model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.norm.weightBF1612837864803803786480636
458model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.out_proj.biasesBF162560x96464affine35272167643527708284
459model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.out_proj.scalesBF162560x96464affine36202298363620721356
460model-00016-of-00017.safetensorslanguage_model.model.layers.0.linear_attn.out_proj.weightU322560x768464affine34625303323470394652
461model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.gate.biasesBF16512x40864affine17577777721757818732
462model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.gate.scalesBF16512x40864affine35261313243526172284
463model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.gate.weightU32512x640864affine11648625401166173260
464model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.down_proj.biasesBF162560x10464affine23599923962360043596
465model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.down_proj.scalesBF162560x10464affine29508318202950883020
466model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.down_proj.weightU322560x80464affine21030637242103882924
467model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.gate_proj.biasesBF16640x40464affine35733802043573431404
468model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.gate_proj.scalesBF16640x40464affine35549302843554981484
469model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.gate_proj.weightU32640x320464affine24825640922483383292
470model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.up_proj.biasesBF16640x40464affine30849388603084990060
471model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.up_proj.scalesBF16640x40464affine22612245402261275740
472model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert.up_proj.weightU32640x320464affine30016406363002459836
473model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert_gate.biasesBF161x40464affine15405410201540541100
474model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert_gate.scalesBF161x40464affine29865352762986535356
475model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp.shared_expert_gate.weightU321x320464affine15811915161581192796
476model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp_hyper_connection.block_inject_weight.weightBF164x1024026261687802626250700
477model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp_hyper_connection.hc_norm.weightBF161024037529952443753015724
478model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024017193444921725898092
479model-00016-of-00017.safetensorslanguage_model.model.layers.0.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320824597204831150804
480model-00016-of-00017.safetensorslanguage_model.model.layers.1.attn_hyper_connection.block_inject_weight.weightBF164x1024035547971643554879084
481model-00016-of-00017.safetensorslanguage_model.model.layers.1.attn_hyper_connection.hc_norm.weightBF161024014053249081405345388
482model-00016-of-00017.safetensorslanguage_model.model.layers.1.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024025146795642521233164
483model-00016-of-00017.safetensorslanguage_model.model.layers.1.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32042629420444269495644
484model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.A_logBF164835227584283522758524
485model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.conv1d.weightBF1610240x4x120604995322060581452
486model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.dt_biasBF164822522401242252240220
487model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_a.biasesBF1648x40464affine677817204677821044
488model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_a.scalesBF1648x40464affine602640484602644324
489model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_a.weightU3248x320464affine37254823963725543836
490model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_b.biasesBF1648x40464affine18131550041813158844
491model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_b.scalesBF1648x40464affine12249384921224942332
492model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_b.weightU3248x320464affine36383355643638397004
493model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_qkv.biasesBF1610240x40464affine18131588441813978044
494model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_qkv.scalesBF1610240x40464affine37264142363727233436
495model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_qkv.weightU3210240x320464affine18902234201903330620
496model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_z.biasesBF166144x40464affine36689366043669428124
497model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_z.scalesBF166144x40464affine30189708123019462332
498model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.in_proj_z.weightU326144x320464affine16973353241705199644
499model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.norm.weightBF1612836852079643685208220
500model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.out_proj.biasesBF162560x96464affine30942778203094769340
501model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.out_proj.scalesBF162560x96464affine36368802043637371724
502model-00016-of-00017.safetensorslanguage_model.model.layers.1.linear_attn.out_proj.weightU322560x768464affine36469820443654846364
503model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.gate.biasesBF16512x40864affine21236947642123735724
504model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.gate.scalesBF16512x40864affine25137682042513809164
505model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.gate.weightU32512x640864affine30194623323020773052
506model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.down_proj.biasesBF162560x10464affine640473604640524804
507model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.down_proj.scalesBF162560x10464affine35548790843554930284
508model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.down_proj.weightU322560x80464affine35886582843589477484
509model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.gate_proj.biasesBF16640x40464affine30964077403096458940
510model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.gate_proj.scalesBF16640x40464affine36384174843638468684
511model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.gate_proj.weightU32640x320464affine37961305563796949756
512model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.up_proj.biasesBF16640x40464affine37969498523797001052
513model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.up_proj.scalesBF16640x40464affine36468796443646930844
514model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert.up_proj.weightU32640x320464affine37514794683752298668
515model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert_gate.biasesBF161x40464affine36450261243645026204
516model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert_gate.scalesBF161x40464affine17785752121778575292
517model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp.shared_expert_gate.weightU321x320464affine36106643963610665676
518model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp_hyper_connection.block_inject_weight.weightBF164x1024020441370362044218956
519model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp_hyper_connection.hc_norm.weightBF161024019280719961928092476
520model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024019286454361935199036
521model-00016-of-00017.safetensorslanguage_model.model.layers.1.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32034835850523490138652
522model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.conv_weightBF1610240x4x118177976601817879580
523model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.key_proj.weightBF1610240x2560755216516807645316
524model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.norm_conv.weightBF161024036374434043637463884
525model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.norm_key.weightBF161024036373717243637392204
526model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.norm_query.weightBF161024012323884281232408908
527model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.ple_embedding.layer_multipliersI64311600700201160070044
528model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.ple_embedding.ngram_heads_offsetsI641636207213563620721484
529model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.ple_embedding.ngram_heads_vocab_sizesI641614469771321446977260
530model-00016-of-00017.safetensorslanguage_model.model.layers.1.ple.value_proj.weightBF162560x2560973500548986607748
531model-00016-of-00017.safetensorslanguage_model.model.layers.10.attn_hyper_connection.block_inject_weight.weightBF164x1024022983829402298464860
532model-00016-of-00017.safetensorslanguage_model.model.layers.10.attn_hyper_connection.hc_norm.weightBF161024013731773561373197836
533model-00016-of-00017.safetensorslanguage_model.model.layers.10.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024035162048283522758428
534model-00016-of-00017.safetensorslanguage_model.model.layers.10.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32021567635642163317164
535model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.A_logBF164836027792443602779340
536model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.conv1d.weightBF1610240x4x120363055642036387484
537model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.dt_biasBF164818836697241883669820
538model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_a.biasesBF1648x40464affine12638458681263849708
539model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_a.scalesBF1648x40464affine34968189723496822812
540model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_a.weightU3248x320464affine30165231963016584636
541model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_b.biasesBF1648x40464affine20771623962077166236
542model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_b.scalesBF1648x40464affine35886544443588658284
543model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_b.weightU3248x320464affine22145657242214627164
544model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_qkv.biasesBF1610240x40464affine927303716928122916
545model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_qkv.scalesBF1610240x40464affine35562960443557115244
546model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_qkv.weightU3210240x320464affine35754512443588558444
547model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_z.biasesBF166144x40464affine727544100728035620
548model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_z.scalesBF166144x40464affine35720285243572520044
549model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.in_proj_z.weightU326144x320464affine24983388122506203132
550model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.norm.weightBF1612816012608761601261132
551model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.out_proj.biasesBF162560x96464affine17076034841708095004
552model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.out_proj.scalesBF162560x96464affine35549853243555476844
553model-00016-of-00017.safetensorslanguage_model.model.layers.10.linear_attn.out_proj.weightU322560x768464affine35576067643565471084
554model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.gate.biasesBF16512x40864affine20858541082085895068
555model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.gate.scalesBF16512x40864affine23288075002328848460
556model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.gate.weightU32512x640864affine30674649723068775692
557model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.down_proj.biasesBF162560x10464affine35246874843524738684
558model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.down_proj.scalesBF162560x10464affine22679317402267982940
559model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.down_proj.weightU322560x80464affine18042935641805112764
560model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.gate_proj.biasesBF16640x40464affine23142052602314256460
561model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.gate_proj.scalesBF16640x40464affine22387130042238764204
562model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.gate_proj.weightU32640x320464affine35135757083514394908
563model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.up_proj.biasesBF16640x40464affine36382843643638335564
564model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.up_proj.scalesBF16640x40464affine34537953563453846556
565model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert.up_proj.weightU32640x320464affine36107271163611546316
566model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert_gate.biasesBF161x40464affine34538465563453846636
567model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert_gate.scalesBF161x40464affine20672067322067206812
568model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp.shared_expert_gate.weightU321x320464affine26037517882603753068
569model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp_hyper_connection.block_inject_weight.weightBF164x1024034835031323483585052
570model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp_hyper_connection.hc_norm.weightBF161024016011481561601168636
571model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024030525925723059146172
572model-00016-of-00017.safetensorslanguage_model.model.layers.10.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32034538466363460400236
573model-00016-of-00017.safetensorslanguage_model.model.layers.11.attn_hyper_connection.block_inject_weight.weightBF164x1024035236801243523762044
574model-00016-of-00017.safetensorslanguage_model.model.layers.11.attn_hyper_connection.hc_norm.weightBF161024034536315163453651996
575model-00016-of-00017.safetensorslanguage_model.model.layers.11.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240669184276675737876
576model-00016-of-00017.safetensorslanguage_model.model.layers.11.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32030858092603092362860
577model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.gate.biasesBF16512x40864affine30314981723031539132
578model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.gate.scalesBF16512x40864affine25227385402522779500
579model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.gate.weightU32512x640864affine35247386843526049404
580model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.down_proj.biasesBF162560x10464affine37255438363725595036
581model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.down_proj.scalesBF162560x10464affine34536519963453703196
582model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.down_proj.weightU322560x80464affine24111309562411950156
583model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.gate_proj.biasesBF16640x40464affine24834652122483516412
584model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.gate_proj.scalesBF16640x40464affine20438191642043870364
585model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.gate_proj.weightU32640x320464affine13572112281358030428
586model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.up_proj.biasesBF16640x40464affine34537031963453754396
587model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.up_proj.scalesBF16640x40464affine17502168121750268012
588model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert.up_proj.weightU32640x320464affine31257876763126606876
589model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert_gate.biasesBF161x40464affine43006671644300667244
590model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert_gate.scalesBF161x40464affine22795749722279575052
591model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp.shared_expert_gate.weightU321x320464affine20524521722052453452
592model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp_hyper_connection.block_inject_weight.weightBF164x1024025221036602522185580
593model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp_hyper_connection.hc_norm.weightBF161024036383970043638417484
594model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024030773469243083900524
595model-00016-of-00017.safetensorslanguage_model.model.layers.11.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32031110006043117554204
596model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine16335557241633606924
597model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine30924448603092496060
598model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.indexer.index_qk_proj.weightU32640x640864affine30926394203094277820
599model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.indexer.k_layernorm.weightBF1612830848874043084887660
600model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.indexer.q_layernorm.weightBF1612838061760923806176348
601model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.k_norm.weightBF1625642919314844291931996
602model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.k_proj.biasesBF16512x40464affine34537543963453795356
603model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.k_proj.scalesBF16512x40464affine17184829561718523916
604model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.k_proj.weightU32512x320464affine17785752921779230652
605model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.o_proj.biasesBF162560x96464affine912390436912881956
606model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.o_proj.scalesBF162560x96464affine34531399963453631516
607model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.o_proj.weightU322560x768464affine24119501562419814476
608model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.q_norm.weightBF1625612249175001224918012
609model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.q_proj.biasesBF1612288x40464affine36458966043646879644
610model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.q_proj.scalesBF1612288x40464affine14979802361498963276
611model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.q_proj.weightU3212288x320464affine11266336201142362260
612model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.v_proj.biasesBF16512x40464affine30520396123052080572
613model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.v_proj.scalesBF16512x40464affine11172838121117324772
614model-00016-of-00017.safetensorslanguage_model.model.layers.11.self_attn.v_proj.weightU32512x320464affine30694822523070137612
615model-00016-of-00017.safetensorslanguage_model.model.layers.12.attn_hyper_connection.block_inject_weight.weightBF164x1024035364430843536525004
616model-00016-of-00017.safetensorslanguage_model.model.layers.12.attn_hyper_connection.hc_norm.weightBF161024030380927323038113212
617model-00016-of-00017.safetensorslanguage_model.model.layers.12.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024030315391323038092732
618model-00016-of-00017.safetensorslanguage_model.model.layers.12.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32031183734043124927004
619model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.A_logBF164834625302363462530332
620model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.conv1d.weightBF1610240x4x118659772921866059212
621model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.dt_biasBF164843006670684300667164
622model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_a.biasesBF1648x40464affine30309823323030986172
623model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_a.scalesBF1648x40464affine18833176441883321484
624model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_a.weightU3248x320464affine928122916928184356
625model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_b.biasesBF1648x40464affine36450222843645026124
626model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_b.scalesBF1648x40464affine508816404508820244
627model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_b.weightU3248x320464affine19280924761928153916
628model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_qkv.biasesBF1610240x40464affine12961383961296957596
629model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_qkv.scalesBF1610240x40464affine10844050281085224228
630model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_qkv.weightU3210240x320464affine408606132421713332
631model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_z.biasesBF166144x40464affine30226264923023118012
632model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_z.scalesBF166144x40464affine30688371323069328652
633model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.in_proj_z.weightU326144x320464affine30231180123030982332
634model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.norm.weightBF1612810984338281098434084
635model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.out_proj.biasesBF162560x96464affine37970010523797492572
636model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.out_proj.scalesBF162560x96464affine30221349723022626492
637model-00016-of-00017.safetensorslanguage_model.model.layers.12.linear_attn.out_proj.weightU322560x768464affine36215611643629425484
638model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.gate.biasesBF16512x40864affine30189298523018970812
639model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.gate.scalesBF16512x40864affine16010252761601066236
640model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.gate.weightU32512x640864affine30207730523022083772
641model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.down_proj.biasesBF162560x10464affine43007798844300831084
642model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.down_proj.scalesBF162560x10464affine35363918843536443084
643model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.down_proj.weightU322560x80464affine30181103963018929596
644model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.gate_proj.biasesBF16640x40464affine30164719963016523196
645model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.gate_proj.scalesBF16640x40464affine703831924703883124
646model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.gate_proj.weightU32640x320464affine20525763322053395532
647model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.up_proj.biasesBF16640x40464affine17087650361708816236
648model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.up_proj.scalesBF16640x40464affine30015894363001640636
649model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert.up_proj.weightU32640x320464affine30024598363003279036
650model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert_gate.biasesBF161x40464affine29785889562978589036
651model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert_gate.scalesBF161x40464affine22521990842252199164
652model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp.shared_expert_gate.weightU321x320464affine30007075163000708796
653model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp_hyper_connection.block_inject_weight.weightBF164x1024015811966361581278556
654model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp_hyper_connection.hc_norm.weightBF161024029508830202950903500
655model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024026122421242618795724
656model-00016-of-00017.safetensorslanguage_model.model.layers.12.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32030608499323067403532
657model-00016-of-00017.safetensorslanguage_model.model.layers.13.attn_hyper_connection.block_inject_weight.weightBF164x1024035227790043522860924
658model-00016-of-00017.safetensorslanguage_model.model.layers.13.attn_hyper_connection.hc_norm.weightBF161024020439420442043962524
659model-00016-of-00017.safetensorslanguage_model.model.layers.13.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024026048693242611422924
660model-00016-of-00017.safetensorslanguage_model.model.layers.13.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32013360757721342629372
661model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.A_logBF164826038042682603804364
662model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.conv1d.weightBF1610240x4x126026969882602778908
663model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.dt_biasBF1648675758356675758452
664model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_a.biasesBF1648x40464affine25072105882507214428
665model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_a.scalesBF1648x40464affine25381599802538163820
666model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_a.weightU3248x320464affine25669997562567061196
667model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_b.biasesBF1648x40464affine35886506043588654444
668model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_b.scalesBF1648x40464affine14869223161486926156
669model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_b.weightU3248x320464affine16821798521682241292
670model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_qkv.biasesBF1610240x40464affine483632308484451508
671model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_qkv.scalesBF1610240x40464affine25138091642514628364
672model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_qkv.weightU3210240x320464affine23395121402352619340
673model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_z.biasesBF166144x40464affine25221855802522677100
674model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_z.scalesBF166144x40464affine675809652676301172
675model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.in_proj_z.weightU326144x320464affine443286708451151028
676model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.norm.weightBF16128849588100849588356
677model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.out_proj.biasesBF162560x96464affine23288996602329391180
678model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.out_proj.scalesBF162560x96464affine20534467322053938252
679model-00016-of-00017.safetensorslanguage_model.model.layers.13.linear_attn.out_proj.weightU322560x768464affine18666019321874466252
680model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.gate.biasesBF16512x40864affine928184356928225316
681model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.gate.scalesBF16512x40864affine25071695322507210492
682model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.gate.weightU32512x640864affine22756735322276984252
683model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.down_proj.biasesBF162560x10464affine25070773722507128572
684model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.down_proj.scalesBF162560x10464affine17330187321733069932
685model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.down_proj.weightU322560x80464affine11178572521118676452
686model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.gate_proj.biasesBF16640x40464affine35546947643554745964
687model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.gate_proj.scalesBF16640x40464affine25070261722507077372
688model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.gate_proj.weightU32640x320464affine36295074043630326604
689model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.up_proj.biasesBF16640x40464affine18480161561848067356
690model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.up_proj.scalesBF16640x40464affine24966645722496715772
691model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert.up_proj.weightU32640x320464affine25062069722507026172
692model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert_gate.biasesBF161x40464affine12428741881242874268
693model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert_gate.scalesBF161x40464affine30591461723059146252
694model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp.shared_expert_gate.weightU321x320464affine24817026522481703932
695model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp_hyper_connection.block_inject_weight.weightBF164x1024026263057402626387660
696model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp_hyper_connection.hc_norm.weightBF161024022966713242296691804
697model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024024743298522480883452
698model-00016-of-00017.safetensorslanguage_model.model.layers.13.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32036384686843645022284
699model-00016-of-00017.safetensorslanguage_model.model.layers.14.attn_hyper_connection.block_inject_weight.weightBF164x1024024742479322474329852
700model-00016-of-00017.safetensorslanguage_model.model.layers.14.attn_hyper_connection.hc_norm.weightBF161024030607884923060808972
701model-00016-of-00017.safetensorslanguage_model.model.layers.14.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024024478287322454382332
702model-00016-of-00017.safetensorslanguage_model.model.layers.14.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32024412751322447828732
703model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.A_logBF164818744662521874466348
704model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.conv1d.weightBF1610240x4x130006255963000707516
705model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.dt_biasBF164831110005083111000604
706model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_a.biasesBF1648x40464affine14955904761495594316
707model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_a.scalesBF1648x40464affine20539382522053942092
708model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_a.weightU3248x320464affine30771830843077244524
709model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_b.biasesBF1648x40464affine25062031322506206972
710model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_b.scalesBF1648x40464affine24271912122427195052
711model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_b.weightU3248x320464affine35266638043526725244
712model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_qkv.biasesBF1610240x40464affine19633180761964137276
713model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_qkv.scalesBF1610240x40464affine676403572677222772
714model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_qkv.weightU3210240x320464affine13734538361386561036
715model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_z.biasesBF166144x40464affine26038453242604336844
716model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_z.scalesBF166144x40464affine839016484839508004
717model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.in_proj_z.weightU326144x320464affine13966413881404505708
718model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.norm.weightBF1612817894337881789434044
719model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.out_proj.biasesBF162560x96464affine23955661562396057676
720model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.out_proj.scalesBF162560x96464affine42984859484298977468
721model-00016-of-00017.safetensorslanguage_model.model.layers.14.linear_attn.out_proj.weightU322560x768464affine24026112762410475596
722model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.gate.biasesBF16512x40864affine14470284601447069420
723model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.gate.scalesBF16512x40864affine35546538043554694764
724model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.gate.weightU32512x640864affine23941735162395484236
725model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.down_proj.biasesBF162560x10464affine23367639802336815180
726model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.down_proj.scalesBF162560x10464affine23394571002339508300
727model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.down_proj.weightU322560x80464affine23526193402353438540
728model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.gate_proj.biasesBF16640x40464affine20362505242036301724
729model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.gate_proj.scalesBF16640x40464affine23288484602328899660
730model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.gate_proj.weightU32640x320464affine24337998522434619052
731model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.up_proj.biasesBF16640x40464affine23142564602314307660
732model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.up_proj.scalesBF16640x40464affine22790322522279083452
733model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert.up_proj.weightU32640x320464affine34617110363462530236
734model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert_gate.biasesBF161x40464affine23142013402314201420
735model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert_gate.scalesBF161x40464affine10770244681077024548
736model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp.shared_expert_gate.weightU321x320464affine24973749722497376252
737model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp_hyper_connection.block_inject_weight.weightBF164x1024023140439002314125820
738model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp_hyper_connection.hc_norm.weightBF161024023009162202300936700
739model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024024346190522441172652
740model-00016-of-00017.safetensorslanguage_model.model.layers.14.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32022690789722275632572
741model-00016-of-00017.safetensorslanguage_model.model.layers.15.attn_hyper_connection.block_inject_weight.weightBF164x1024024833832922483465212
742model-00016-of-00017.safetensorslanguage_model.model.layers.15.attn_hyper_connection.hc_norm.weightBF161024036207214843620741964
743model-00016-of-00017.safetensorslanguage_model.model.layers.15.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024012116768441218230444
744model-00016-of-00017.safetensorslanguage_model.model.layers.15.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32023208612602327414860
745model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.gate.biasesBF16512x40864affine22145247642214565724
746model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.gate.scalesBF16512x40864affine20440960762044137036
747model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.gate.weightU32512x640864affine846925604848236324
748model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.down_proj.biasesBF162560x10464affine29510126362951063836
749model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.down_proj.scalesBF162560x10464affine23679079162367959116
750model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.down_proj.weightU322560x80464affine18471969561848016156
751model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.gate_proj.biasesBF16640x40464affine19788828761978934076
752model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.gate_proj.scalesBF16640x40464affine22999291802299980380
753model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.gate_proj.weightU32640x320464affine22999803802300799580
754model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.up_proj.biasesBF16640x40464affine703886964703938164
755model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.up_proj.scalesBF16640x40464affine36458454043645896604
756model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert.up_proj.weightU32640x320464affine22967442842297563484
757model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert_gate.biasesBF161x40464affine22958008442295800924
758model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert_gate.scalesBF161x40464affine29509600762950960156
759model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp.shared_expert_gate.weightU321x320464affine22957995642295800844
760model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp_hyper_connection.block_inject_weight.weightBF164x1024035260494043526131324
761model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp_hyper_connection.hc_norm.weightBF161024020605814522060601932
762model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024034452756763451829276
763model-00016-of-00017.safetensorslanguage_model.model.layers.15.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32024900700122496623612
764model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine18129770841813028284
765model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine26037530682603804268
766model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.indexer.index_qk_proj.weightU32640x640864affine22941611642295799564
767model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.indexer.k_layernorm.weightBF1612821021925562102192812
768model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.indexer.q_layernorm.weightBF1612822689045402268904796
769model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.k_norm.weightBF1625622810496122281050124
770model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.k_proj.biasesBF16512x40464affine23008752602300916220
771model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.k_proj.scalesBF16512x40464affine22985160602298557020
772model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.k_proj.weightU32512x320464affine22795750522280230412
773model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.o_proj.biasesBF162560x96464affine22790834522279574972
774model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.o_proj.scalesBF162560x96464affine29870268762987518396
775model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.o_proj.weightU322560x768464affine36027793403610643660
776model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.q_norm.weightBF1625612639521081263952620
777model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.q_proj.biasesBF1612288x40464affine22769842522277967292
778model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.q_proj.scalesBF1612288x40464affine22779672922278950332
779model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.q_proj.weightU3212288x320464affine17599998521775728492
780model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.v_proj.biasesBF16512x40464affine20355542042035595164
781model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.v_proj.scalesBF16512x40464affine22756325722275673532
782model-00016-of-00017.safetensorslanguage_model.model.layers.15.self_attn.v_proj.weightU32512x320464affine857606436858261796
783model-00016-of-00017.safetensorslanguage_model.model.layers.16.attn_hyper_connection.block_inject_weight.weightBF164x1024022689047962268986716
784model-00016-of-00017.safetensorslanguage_model.model.layers.16.attn_hyper_connection.hc_norm.weightBF161024021567430842156763564
785model-00016-of-00017.safetensorslanguage_model.model.layers.16.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024042694956444276049244
786model-00016-of-00017.safetensorslanguage_model.model.layers.16.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32026187957242625349324
787model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.A_logBF164816823539321682354028
788model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.conv1d.weightBF1610240x4x122387642042238846124
789model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.dt_biasBF164825072104922507210588
790model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_a.biasesBF1648x40464affine20363874842036391324
791model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_a.scalesBF1648x40464affine10602559561060259796
792model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_a.weightU3248x320464affine30923834203092444860
793model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_b.biasesBF1648x40464affine22612207002261224540
794model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_b.scalesBF1648x40464affine17075996441707603484
795model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_b.weightU3248x320464affine22679829402268044380
796model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_qkv.biasesBF1610240x40464affine15363065241537125724
797model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_qkv.scalesBF1610240x40464affine26114229242612242124
798model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_qkv.weightU3210240x320464affine729858340742965540
799model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_z.biasesBF166144x40464affine593842788594334308
800model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_z.scalesBF166144x40464affine30701376123070629132
801model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.in_proj_z.weightU326144x320464affine22430240442250888364
802model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.norm.weightBF1612831030330203103033276
803model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.out_proj.biasesBF162560x96464affine22403104442240801964
804model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.out_proj.scalesBF162560x96464affine22425325242243024044
805model-00016-of-00017.safetensorslanguage_model.model.layers.16.linear_attn.out_proj.weightU322560x768464affine37600608443767925164
806model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.gate.biasesBF16512x40864affine42629010844262942044
807model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.gate.scalesBF16512x40864affine17501233721750164332
808model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.gate.weightU32512x640864affine22389997242240310444
809model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.down_proj.biasesBF162560x10464affine35366069243536658124
810model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.down_proj.scalesBF162560x10464affine22388973242238948524
811model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.down_proj.weightU322560x80464affine718736340719555540
812model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.gate_proj.biasesBF16640x40464affine11600700441160121244
813model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.gate_proj.scalesBF16640x40464affine15408689561540920156
814model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.gate_proj.weightU32640x320464affine30591500923059969292
815model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.up_proj.biasesBF16640x40464affine21011364762101187676
816model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.up_proj.scalesBF16640x40464affine20606019322060653132
817model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert.up_proj.weightU32640x320464affine24808834522481702652
818model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert_gate.biasesBF161x40464affine22146271642214627244
819model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert_gate.scalesBF161x40464affine23008712602300871340
820model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp.shared_expert_gate.weightU321x320464affine22385274042238528684
821model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp_hyper_connection.block_inject_weight.weightBF164x10240625728004625809924
822model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp_hyper_connection.hc_norm.weightBF161024015408484761540868956
823model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024022066604442213214044
824model-00016-of-00017.safetensorslanguage_model.model.layers.16.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32036852082203691761820
825model-00016-of-00017.safetensorslanguage_model.model.layers.17.attn_hyper_connection.block_inject_weight.weightBF164x1024021855339642185615884
826model-00016-of-00017.safetensorslanguage_model.model.layers.17.attn_hyper_connection.hc_norm.weightBF161024018834034041883423884
827model-00016-of-00017.safetensorslanguage_model.model.layers.17.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024021789291642185482764
828model-00016-of-00017.safetensorslanguage_model.model.layers.17.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320952252292958805892
829model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.A_logBF164825137681082513768204
830model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.conv1d.weightBF1610240x4x117576446521757726572
831model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.dt_biasBF164821700197562170019852
832model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_a.biasesBF1648x40464affine21700120762170015916
833model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_a.scalesBF1648x40464affine21700159162170019756
834model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_a.weightU3248x320464affine30015279963001589436
835model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_b.biasesBF1648x40464affine21633171642163321004
836model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_b.scalesBF1648x40464affine21634546362163458476
837model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_b.weightU3248x320464affine22985570202298618460
838model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_qkv.biasesBF1610240x40464affine24974376922498256892
839model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_qkv.scalesBF1610240x40464affine13058049561306624156
840model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_qkv.weightU3210240x320464affine19798967321993003932
841model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_z.biasesBF166144x40464affine19117558361912247356
842model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_z.scalesBF166144x40464affine17179914361718482956
843model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.in_proj_z.weightU326144x320464affine18390766361846940956
844model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.norm.weightBF1612831257874203125787676
845model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.out_proj.biasesBF162560x96464affine21409082042141399724
846model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.out_proj.scalesBF162560x96464affine16630509401663542460
847model-00016-of-00017.safetensorslanguage_model.model.layers.17.linear_attn.out_proj.weightU322560x768464affine21414202042149284524
848model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.gate.biasesBF16512x40864affine21395565242139597484
849model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.gate.scalesBF16512x40864affine19033306201903371580
850model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.gate.weightU32512x640864affine21395974842140908204
851model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.down_proj.biasesBF162560x10464affine37272335163727284716
852model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.down_proj.scalesBF162560x10464affine14297729081429824108
853model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.down_proj.weightU322560x80464affine31175542043118373404
854model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.gate_proj.biasesBF16640x40464affine21038829242103934124
855model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.gate_proj.scalesBF16640x40464affine958887812958939012
856model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.gate_proj.weightU32640x320464affine17491300921749949292
857model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.up_proj.biasesBF16640x40464affine36469308443646982044
858model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.up_proj.scalesBF16640x40464affine21021933242102244524
859model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert.up_proj.weightU32640x320464affine21022445242103063724
860model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert_gate.biasesBF161x40464affine21021911962102191276
861model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert_gate.scalesBF161x40464affine12183638201218363900
862model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp.shared_expert_gate.weightU321x320464affine21021912762102192556
863model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp_hyper_connection.block_inject_weight.weightBF164x1024021021092762102191196
864model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp_hyper_connection.hc_norm.weightBF161024019351990361935219516
865model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024020945316762101085276
866model-00016-of-00017.safetensorslanguage_model.model.layers.17.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32023302103802336763980
867model-00016-of-00017.safetensorslanguage_model.model.layers.18.attn_hyper_connection.block_inject_weight.weightBF164x1024020440139802044095900
868model-00016-of-00017.safetensorslanguage_model.model.layers.18.attn_hyper_connection.hc_norm.weightBF161024021413997242141420204
869model-00016-of-00017.safetensorslanguage_model.model.layers.18.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024021039341242110487724
870model-00016-of-00017.safetensorslanguage_model.model.layers.18.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32020879780762094531676
871model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.A_logBF164820874247642087424860
872model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.conv1d.weightBF1610240x4x1678365044678446964
873model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.dt_biasBF164820867181082086718204
874model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_a.biasesBF1648x40464affine30591462523059150092
875model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_a.scalesBF1648x40464affine20858502682085854108
876model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_a.weightU3248x320464affine14870080761487069516
877model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_b.biasesBF1648x40464affine17877403481787744188
878model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_b.scalesBF1648x40464affine20539420922053945932
879model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_b.weightU3248x320464affine25226771002522738540
880model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_qkv.biasesBF1610240x40464affine20771662362077985436
881model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_qkv.scalesBF1610240x40464affine35554768443556296044
882model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_qkv.weightU3210240x320464affine29576174362970724636
883model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_z.biasesBF166144x40464affine20760564762076547996
884model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_z.scalesBF166144x40464affine20765889562077080476
885model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.in_proj_z.weightU326144x320464affine35277083643535572684
886model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.norm.weightBF16128602640228602640484
887model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.out_proj.biasesBF162560x96464affine20755649562076056476
888model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.out_proj.scalesBF162560x96464affine21784376442178929164
889model-00016-of-00017.safetensorslanguage_model.model.layers.18.linear_attn.out_proj.weightU322560x768464affine15732209561581085276
890model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.gate.biasesBF16512x40864affine20754419802075482940
891model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.gate.scalesBF16512x40864affine17500312121750072172
892model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.gate.weightU32512x640864affine37974925723798803292
893model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.down_proj.biasesBF162560x10464affine13733104761373361676
894model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.down_proj.scalesBF162560x10464affine20753907802075441980
895model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.down_proj.weightU322560x80464affine37855585243786377724
896model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.gate_proj.biasesBF16640x40464affine21170451642117096364
897model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.gate_proj.scalesBF16640x40464affine18660592121866110412
898model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.gate_proj.weightU32640x320464affine20745715802075390780
899model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.up_proj.biasesBF16640x40464affine29509088762950960076
900model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.up_proj.scalesBF16640x40464affine20673933402067444540
901model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert.up_proj.weightU32640x320464affine17409380921741757292
902model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert_gate.biasesBF161x40464affine20673913882067391468
903model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert_gate.scalesBF161x40464affine20673919802067392060
904model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp.shared_expert_gate.weightU321x320464affine20673920602067393340
905model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp_hyper_connection.block_inject_weight.weightBF164x1024020673092122067391132
906model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp_hyper_connection.hc_norm.weightBF161024020672887322067309212
907model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240553066772559620372
908model-00016-of-00017.safetensorslanguage_model.model.layers.18.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32019567644761963318076
909model-00016-of-00017.safetensorslanguage_model.model.layers.19.attn_hyper_connection.block_inject_weight.weightBF164x1024020672068122067288732
910model-00016-of-00017.safetensorslanguage_model.model.layers.19.attn_hyper_connection.hc_norm.weightBF161024036106436603610664140
911model-00016-of-00017.safetensorslanguage_model.model.layers.19.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024020606531322067206732
912model-00016-of-00017.safetensorslanguage_model.model.layers.19.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32020539459322060499532
913model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.gate.biasesBF16512x40864affine719637460719678420
914model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.gate.scalesBF16512x40864affine20525353722052576332
915model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.gate.weightU32512x640864affine742965540744276260
916model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.down_proj.biasesBF162560x10464affine26262507002626301900
917model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.down_proj.scalesBF162560x10464affine20429449242042996124
918model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.down_proj.weightU322560x80464affine35524379643553257164
919model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.gate_proj.biasesBF16640x40464affine37254311963725482396
920model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.gate_proj.scalesBF16640x40464affine17876891481787740348
921model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.gate_proj.weightU32640x320464affine36450262043645845404
922model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.up_proj.biasesBF16640x40464affine21010852762101136476
923model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.up_proj.scalesBF16640x40464affine20361993242036250524
924model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert.up_proj.weightU32640x320464affine20516329722052452172
925model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert_gate.biasesBF161x40464affine30923628603092362940
926model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert_gate.scalesBF161x40464affine20440959002044095980
927model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp.shared_expert_gate.weightU321x320464affine20253945882025395868
928model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp_hyper_connection.block_inject_weight.weightBF164x1024013581637241358245644
929model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp_hyper_connection.hc_norm.weightBF161024020439215642043942044
930model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024017510910521757644652
931model-00016-of-00017.safetensorslanguage_model.model.layers.19.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32020363913242042944924
932model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine662538516662589716
933model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine20356156442035666844
934model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.indexer.index_qk_proj.weightU32640x640864affine42990286684300667068
935model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.indexer.k_layernorm.weightBF1612820347347482034735004
936model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.indexer.q_layernorm.weightBF1612811128560361112856292
937model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.k_norm.weightBF16256509886484509886996
938model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.k_proj.biasesBF16512x40464affine20121542682012195228
939model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.k_proj.scalesBF16512x40464affine20253536282025394588
940model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.k_proj.weightU32512x320464affine20332601882033915548
941model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.o_proj.biasesBF162560x96464affine20110544922011546012
942model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.o_proj.scalesBF162560x96464affine20116626682012154188
943model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.o_proj.weightU322560x768464affine20008554522008719772
944model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.q_norm.weightBF1625620673914682067391980
945model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.q_proj.biasesBF1612288x40464affine36548463643655829404
946model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.q_proj.scalesBF1612288x40464affine20092522522010235292
947model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.q_proj.weightU3212288x320464affine25670611962582789836
948model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.v_proj.biasesBF16512x40464affine20092112922009252252
949model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.v_proj.scalesBF16512x40464affine30608089723060849932
950model-00016-of-00017.safetensorslanguage_model.model.layers.19.self_attn.v_proj.weightU32512x320464affine624967604625622964
951model-00016-of-00017.safetensorslanguage_model.model.layers.2.attn_hyper_connection.block_inject_weight.weightBF164x1024024982568922498338812
952model-00016-of-00017.safetensorslanguage_model.model.layers.2.attn_hyper_connection.hc_norm.weightBF161024015527204761552740956
953model-00016-of-00017.safetensorslanguage_model.model.layers.2.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024019418550361948408636
954model-00016-of-00017.safetensorslanguage_model.model.layers.2.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32019942263322000779932
955model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.A_logBF164842984855964298485692
956model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.conv1d.weightBF1610240x4x135532573243553339244
957model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.dt_biasBF1648649208404649208500
958model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_a.biasesBF1648x40464affine19275766361927580476
959model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_a.scalesBF1648x40464affine16010009561601004796
960model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_a.weightU3248x320464affine19941648921994226332
961model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_b.biasesBF1648x40464affine20007799322000783772
962model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_b.scalesBF1648x40464affine19934954521993499292
963model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_b.weightU3248x320464affine19936119321993673372
964model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_qkv.biasesBF1610240x40464affine617574244618393444
965model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_qkv.scalesBF1610240x40464affine17051996441706018844
966model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_qkv.weightU3210240x320464affine19657756761978882876
967model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_z.biasesBF166144x40464affine19281539161928645436
968model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_z.scalesBF166144x40464affine13349966361335488156
969model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.in_proj_z.weightU326144x320464affine19489001561956764476
970model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.norm.weightBF1612810530569001053057156
971model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.out_proj.biasesBF162560x96464affine16808691321681360652
972model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.out_proj.scalesBF162560x96464affine19275804761928071996
973model-00016-of-00017.safetensorslanguage_model.model.layers.2.linear_attn.out_proj.weightU322560x768464affine21705733242178437644
974model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.gate.biasesBF16512x40864affine19051574361905198396
975model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.gate.scalesBF16512x40864affine19130665561913107516
976model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.gate.weightU32512x640864affine451151028452461748
977model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.down_proj.biasesBF162560x10464affine16645260121664577212
978model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.down_proj.scalesBF162560x10464affine30694105723069461772
979model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.down_proj.weightU322560x80464affine19043382361905157436
980model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.gate_proj.biasesBF16640x40464affine42918802844291931484
981model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.gate_proj.scalesBF16640x40464affine23008200602300871260
982model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.gate_proj.weightU32640x320464affine19035190361904338236
983model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.up_proj.biasesBF16640x40464affine19033754201903426620
984model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.up_proj.scalesBF16640x40464affine19034675801903518780
985model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert.up_proj.weightU32640x320464affine21321427642132961964
986model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert_gate.biasesBF161x40464affine20115499482011550028
987model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert_gate.scalesBF161x40464affine18835058041883505884
988model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp.shared_expert_gate.weightU321x320464affine11587157801158717060
989model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp_hyper_connection.block_inject_weight.weightBF164x1024018834238841883505804
990model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp_hyper_connection.hc_norm.weightBF161024020008349722000855452
991model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024018573960761863949676
992model-00016-of-00017.safetensorslanguage_model.model.layers.2.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32022810501242287603724
993model-00016-of-00017.safetensorslanguage_model.model.layers.20.attn_hyper_connection.block_inject_weight.weightBF164x1024018833214841883403404
994model-00016-of-00017.safetensorslanguage_model.model.layers.20.attn_hyper_connection.hc_norm.weightBF161024014639590201463979500
995model-00016-of-00017.safetensorslanguage_model.model.layers.20.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024037291419963735695596
996model-00016-of-00017.safetensorslanguage_model.model.layers.20.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32022613269402267880540
997model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.A_logBF164818832561081883256204
998model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.conv1d.weightBF1610240x4x119352195161935301436
999model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.dt_biasBF164820115498522011549948
1000model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_a.biasesBF1648x40464affine37282677563728271596
1001model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_a.scalesBF1648x40464affine35549814843554985324
1002model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_a.weightU3248x320464affine19797532761979814716
1003model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_b.biasesBF1648x40464affine18832522681883256108
1004model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_b.scalesBF1648x40464affine20363017242036305564
1005model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_b.weightU3248x320464affine20879166362087978076
1006model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_qkv.biasesBF1610240x40464affine18823306681883149868
1007model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_qkv.scalesBF1610240x40464affine987430788988249988
1008model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_qkv.weightU3210240x320464affine13074638361320571036
1009model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_z.biasesBF166144x40464affine38074873243807978844
1010model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_z.scalesBF166144x40464affine19930039321993495452
1011model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.in_proj_z.weightU326144x320464affine18481185561855982876
1012model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.norm.weightBF1612823534385402353438796
1013model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.out_proj.biasesBF162560x96464affine18654037561865895276
1014model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.out_proj.scalesBF162560x96464affine18661104121866601932
1015model-00016-of-00017.safetensorslanguage_model.model.layers.20.linear_attn.out_proj.weightU322560x768464affine18744663481882330668
1016model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.gate.biasesBF16512x40864affine25227795002522820460
1017model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.gate.scalesBF16512x40864affine35246465243524687484
1018model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.gate.weightU32512x640864affine18640520761865362796
1019model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.down_proj.biasesBF162560x10464affine18640008761864052076
1020model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.down_proj.scalesBF162560x10464affine22966201242296671324
1021model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.down_proj.weightU322560x80464affine30512204123052039612
1022model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.gate_proj.biasesBF16640x40464affine18639496761864000876
1023model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.gate_proj.scalesBF16640x40464affine20867182042086769404
1024model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.gate_proj.weightU32640x320464affine19122473561913066556
1025model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.up_proj.biasesBF16640x40464affine18480673561848118556
1026model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.up_proj.scalesBF16640x40464affine18573448761857396076
1027model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert.up_proj.weightU32640x320464affine15510820761551901276
1028model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert_gate.biasesBF161x40464affine26036902682603690348
1029model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert_gate.scalesBF161x40464affine25137680282513768108
1030model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp.shared_expert_gate.weightU321x320464affine625624324625625604
1031model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp_hyper_connection.block_inject_weight.weightBF164x1024018470331161847115036
1032model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp_hyper_connection.hc_norm.weightBF161024018325025561832523036
1033model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024018254574361832011036
1034model-00016-of-00017.safetensorslanguage_model.model.layers.20.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32025447175162551271116
1035model-00016-of-00017.safetensorslanguage_model.model.layers.21.attn_hyper_connection.block_inject_weight.weightBF164x1024020515510522051632972
1036model-00016-of-00017.safetensorslanguage_model.model.layers.21.attn_hyper_connection.hc_norm.weightBF161024030309861723031006652
1037model-00016-of-00017.safetensorslanguage_model.model.layers.21.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024018178795801824433180
1038model-00016-of-00017.safetensorslanguage_model.model.layers.21.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320840327204846880804
1039model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.A_logBF164818139780441813978140
1040model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.conv1d.weightBF1610240x4x121633210042163402924
1041model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.dt_biasBF164830706291323070629228
1042model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_a.biasesBF1648x40464affine18042897241804293564
1043model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_a.scalesBF1648x40464affine18130282841813032124
1044model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_a.weightU3248x320464affine18130321241813093564
1045model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_b.biasesBF1648x40464affine14735641401473567980
1046model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_b.scalesBF1648x40464affine704150740704154580
1047model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_b.weightU3248x320464affine15380693401538130780
1048model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_qkv.biasesBF1610240x40464affine17877441881788563388
1049model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_qkv.scalesBF1610240x40464affine19789340761979753276
1050model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_qkv.weightU3210240x320464affine17910801241804187324
1051model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_z.biasesBF166144x40464affine677273972677765492
1052model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_z.scalesBF166144x40464affine13354881561335979676
1053model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.in_proj_z.weightU326144x320464affine20779859482085850268
1054model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.norm.weightBF16128677765652677765908
1055model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.out_proj.biasesBF162560x96464affine17770392121777530732
1056model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.out_proj.scalesBF162560x96464affine17792309081779722428
1057model-00016-of-00017.safetensorslanguage_model.model.layers.21.linear_attn.out_proj.weightU322560x768464affine18051127641812977084
1058model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.gate.biasesBF16512x40864affine37528723643752913324
1059model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.gate.scalesBF16512x40864affine36026870843602728044
1060model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.gate.weightU32512x640864affine17757284921777039212
1061model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.down_proj.biasesBF162560x10464affine24412239322441275132
1062model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.down_proj.scalesBF162560x10464affine25381087802538159980
1063model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.down_proj.weightU322560x80464affine17591806521759999852
1064model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.gate_proj.biasesBF16640x40464affine17577265721757777772
1065model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.gate_proj.scalesBF16640x40464affine17069954841707046684
1066model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.gate_proj.weightU32640x320464affine22975637402298382940
1067model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.up_proj.biasesBF16640x40464affine17501656121750216812
1068model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.up_proj.scalesBF16640x40464affine728906020728957220
1069model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert.up_proj.weightU32640x320464affine11866622201187481420
1070model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert_gate.biasesBF161x40464affine648389124648389204
1071model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert_gate.scalesBF161x40464affine16541688441654168924
1072model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp.shared_expert_gate.weightU321x320464affine17501643321750165612
1073model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp_hyper_connection.block_inject_weight.weightBF164x1024017499492921750031212
1074model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp_hyper_connection.hc_norm.weightBF161024021020068762102027356
1075model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024023960576762402611276
1076model-00016-of-00017.safetensorslanguage_model.model.layers.21.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32017417572921748310892
1077model-00016-of-00017.safetensorslanguage_model.model.layers.22.attn_hyper_connection.block_inject_weight.weightBF164x1024030032828763003364796
1078model-00016-of-00017.safetensorslanguage_model.model.layers.22.attn_hyper_connection.hc_norm.weightBF161024017329982521733018732
1079model-00016-of-00017.safetensorslanguage_model.model.layers.22.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024017259492921732502892
1080model-00016-of-00017.safetensorslanguage_model.model.layers.22.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32013582456441364799244
1081model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.A_logBF164817193443961719344492
1082model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.conv1d.weightBF1610240x4x1500180148500262068
1083model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.dt_biasBF164819798556761979855772
1084model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_a.biasesBF1648x40464affine17894378841789441724
1085model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_a.scalesBF1648x40464affine20115460122011549852
1086model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_a.weightU3248x320464affine689024884689086324
1087model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_b.biasesBF1648x40464affine35654710843565474924
1088model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_b.scalesBF1648x40464affine16131025081613106348
1089model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_b.weightU3248x320464affine21700198522170081292
1090model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_qkv.biasesBF1610240x40464affine16112593081612078508
1091model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_qkv.scalesBF1610240x40464affine17185239161719343116
1092model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_qkv.weightU3210240x320464affine20121952282025302428
1093model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_z.biasesBF166144x40464affine17174999161717991436
1094model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_z.scalesBF166144x40464affine501638164502129684
1095model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.in_proj_z.weightU326144x320464affine29786709562986535276
1096model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.norm.weightBF1612817792306521779230908
1097model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.out_proj.biasesBF162560x96464affine34518292763452320796
1098model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.out_proj.scalesBF162560x96464affine17082735161708765036
1099model-00016-of-00017.safetensorslanguage_model.model.layers.22.linear_attn.out_proj.weightU322560x768464affine17096355961717499916
1100model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.gate.biasesBF16512x40864affine649318676649359636
1101model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.gate.scalesBF16512x40864affine20514279162051468876
1102model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.gate.weightU32512x640864affine35148941083516204828
1103model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.down_proj.biasesBF162560x10464affine14315044921431555692
1104model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.down_proj.scalesBF162560x10464affine17081359641708187164
1105model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.down_proj.weightU322560x80464affine26028301082603649308
1106model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.gate_proj.biasesBF16640x40464affine30220837723022134972
1107model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.gate_proj.scalesBF16640x40464affine30772445243077295724
1108model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.gate_proj.weightU32640x320464affine17061762841706995484
1109model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.up_proj.biasesBF16640x40464affine30924960603092547260
1110model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.up_proj.scalesBF16640x40464affine17060188441706070044
1111model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert.up_proj.weightU32640x320464affine30599692923060788492
1112model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert_gate.biasesBF161x40464affine16889281081688928188
1113model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert_gate.scalesBF161x40464affine17096355161709635596
1114model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp.shared_expert_gate.weightU321x320464affine29509075962950908876
1115model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp_hyper_connection.block_inject_weight.weightBF164x1024034977241883497806108
1116model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp_hyper_connection.hc_norm.weightBF161024016889076281688928108
1117model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024024206336762427187276
1118model-00016-of-00017.safetensorslanguage_model.model.layers.22.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32016823540281688907628
1119model-00016-of-00017.safetensorslanguage_model.model.layers.23.attn_hyper_connection.block_inject_weight.weightBF164x1024021020273562102109276
1120model-00016-of-00017.safetensorslanguage_model.model.layers.23.attn_hyper_connection.hc_norm.weightBF161024023141296602314150140
1121model-00016-of-00017.safetensorslanguage_model.model.layers.23.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024020442189562050772556
1122model-00016-of-00017.safetensorslanguage_model.model.layers.23.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32019052022361911755836
1123model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.gate.biasesBF16512x40864affine18653627961865403756
1124model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.gate.scalesBF16512x40864affine25827898362582830796
1125model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.gate.weightU32512x640864affine34604003163461711036
1126model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.down_proj.biasesBF162560x10464affine37757895643775840764
1127model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.down_proj.scalesBF162560x10464affine16823027321682353932
1128model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.down_proj.weightU322560x80464affine17502718521751091052
1129model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.gate_proj.biasesBF16640x40464affine16808179321680869132
1130model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.gate_proj.scalesBF16640x40464affine20439625242044013724
1131model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.gate_proj.weightU32640x320464affine16813606521682179852
1132model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.up_proj.biasesBF16640x40464affine16799475321679998732
1133model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.up_proj.scalesBF16640x40464affine10617562921061807492
1134model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert.up_proj.weightU32640x320464affine16799987321680817932
1135model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert_gate.biasesBF161x40464affine22066603642206660444
1136model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert_gate.scalesBF161x40464affine16798860121679886092
1137model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp.shared_expert_gate.weightU321x320464affine21934802042193481484
1138model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp_hyper_connection.block_inject_weight.weightBF164x1024020514688762051550796
1139model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp_hyper_connection.hc_norm.weightBF161024016720012121672021692
1140model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024036303266043636880204
1141model-00016-of-00017.safetensorslanguage_model.model.layers.23.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32016654476121672001212
1142model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine16653964121665447612
1143model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine22408429242240894124
1144model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.indexer.index_qk_proj.weightU32640x640864affine22408941242242532524
1145model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.indexer.k_layernorm.weightBF1612826261685242626168780
1146model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.indexer.q_layernorm.weightBF1612819035187801903519036
1147model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.k_norm.weightBF1625621700812922170081804
1148model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.k_proj.biasesBF16512x40464affine13733616761373402636
1149model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.k_proj.scalesBF16512x40464affine21171002042117141164
1150model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.k_proj.weightU32512x320464affine12109797561211635116
1151model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.o_proj.biasesBF162560x96464affine501081268501572788
1152model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.o_proj.scalesBF162560x96464affine37530157243753507244
1153model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.o_proj.weightU322560x768464affine36123655163620229836
1154model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.q_norm.weightBF1625616645255001664526012
1155model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.q_proj.biasesBF1612288x40464affine16620678041663050844
1156model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.q_proj.scalesBF1612288x40464affine16635424601664525500
1157model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.q_proj.weightU3212288x320464affine460858548476587188
1158model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.v_proj.biasesBF16512x40464affine16613202841661361244
1159model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.v_proj.scalesBF16512x40464affine22680443802268085340
1160model-00016-of-00017.safetensorslanguage_model.model.layers.23.self_attn.v_proj.weightU32512x320464affine16614124441662067804
1161model-00016-of-00017.safetensorslanguage_model.model.layers.24.attn_hyper_connection.block_inject_weight.weightBF164x1024020770804762077162396
1162model-00016-of-00017.safetensorslanguage_model.model.layers.24.attn_hyper_connection.hc_norm.weightBF161024016612998041661320284
1163model-00016-of-00017.safetensorslanguage_model.model.layers.24.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024037535072443760060844
1164model-00016-of-00017.safetensorslanguage_model.model.layers.24.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32016547462041661299804
1165model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.A_logBF164815380692441538069340
1166model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.conv1d.weightBF1610240x4x122385798842238661804
1167model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.dt_biasBF164812937933401293793436
1168model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_a.biasesBF1648x40464affine16546604441654664284
1169model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_a.scalesBF1648x40464affine17061724441706176284
1170model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_a.weightU3248x320464affine37960691163796130556
1171model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_b.biasesBF1648x40464affine35148902683514894108
1172model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_b.scalesBF1648x40464affine30032790363003282876
1173model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_b.weightU3248x320464affine35237620443523823484
1174model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_qkv.biasesBF1610240x40464affine36207419643621561164
1175model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_qkv.scalesBF1610240x40464affine16120785081612897708
1176model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_qkv.weightU3210240x320464affine16336888441646796044
1177model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_z.biasesBF166144x40464affine17071081241707599644
1178model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_z.scalesBF166144x40464affine16329719481633463468
1179model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.in_proj_z.weightU326144x320464affine19197123161927576636
1180model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.norm.weightBF1612820440137242044013980
1181model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.out_proj.biasesBF162560x96464affine14989840121499475532
1182model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.out_proj.scalesBF162560x96464affine18320110361832502556
1183model-00016-of-00017.safetensorslanguage_model.model.layers.24.linear_attn.out_proj.weightU322560x768464affine16894197081697284028
1184model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.gate.biasesBF16512x40864affine16130615481613102508
1185model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.gate.scalesBF16512x40864affine16334634681633504428
1186model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.gate.weightU32512x640864affine22132140442214524764
1187model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.down_proj.biasesBF162560x10464affine22612757402261326940
1188model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.down_proj.scalesBF162560x10464affine31108981083110949308
1189model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.down_proj.weightU322560x80464affine20429999642043819164
1190model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.gate_proj.biasesBF16640x40464affine30165846363016635836
1191model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.gate_proj.scalesBF16640x40464affine22966918042296743004
1192model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.gate_proj.weightU32640x320464affine16012650681602084268
1193model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.up_proj.biasesBF16640x40464affine20533955322053446732
1194model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.up_proj.scalesBF16640x40464affine16012096761601260876
1195model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert.up_proj.weightU32640x320464affine36115463163612365516
1196model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert_gate.biasesBF161x40464affine35532572443553257324
1197model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert_gate.scalesBF161x40464affine16011686361601168716
1198model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp.shared_expert_gate.weightU321x320464affine17193431161719344396
1199model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp_hyper_connection.block_inject_weight.weightBF164x1024016010662361601148156
1200model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp_hyper_connection.hc_norm.weightBF161024017060700441706090524
1201model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024021501894842156743084
1202model-00016-of-00017.safetensorslanguage_model.model.layers.24.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32021104915642117045164
1203model-00016-of-00017.safetensorslanguage_model.model.layers.25.attn_hyper_connection.block_inject_weight.weightBF164x1024037527904443752872364
1204model-00016-of-00017.safetensorslanguage_model.model.layers.25.attn_hyper_connection.hc_norm.weightBF161024016010047961601025276
1205model-00016-of-00017.safetensorslanguage_model.model.layers.25.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024015944473561601000956
1206model-00016-of-00017.safetensorslanguage_model.model.layers.25.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32015878937561594447356
1207model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.A_logBF164816972840281697284124
1208model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.conv1d.weightBF1610240x4x117081910841708273004
1209model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.dt_biasBF164837356955963735695692
1210model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_a.biasesBF1648x40464affine12031115961203115436
1211model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_a.scalesBF1648x40464affine15811927961581196636
1212model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_a.weightU3248x320464affine15812785561581339996
1213model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_b.biasesBF1648x40464affine15811671961581171036
1214model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_b.scalesBF1648x40464affine24967157722496719612
1215model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_b.weightU3248x320464affine10530571561053118596
1216model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_qkv.biasesBF1610240x40464affine21011876762102006876
1217model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_qkv.scalesBF1610240x40464affine15527409561553560156
1218model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_qkv.weightU3210240x320464affine15535601561566667356
1219model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_z.biasesBF166144x40464affine15505867161551078236
1220model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_z.scalesBF166144x40464affine16541689241654660444
1221model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.in_proj_z.weightU326144x320464affine29707246362978588956
1222model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.norm.weightBF1612837864801243786480380
1223model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.out_proj.biasesBF162560x96464affine15422308761542722396
1224model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.out_proj.scalesBF162560x96464affine18249659161825457436
1225model-00016-of-00017.safetensorslanguage_model.model.layers.25.linear_attn.out_proj.weightU322560x768464affine16720216921679886012
1226model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.gate.biasesBF16512x40864affine15408075161540848476
1227model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.gate.scalesBF16512x40864affine10983314281098372388
1228model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.gate.weightU32512x640864affine15409201561542230876
1229model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.down_proj.biasesBF162560x10464affine15406027161540653916
1230model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.down_proj.scalesBF162560x10464affine15407563161540807516
1231model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.down_proj.weightU322560x80464affine754229636755048836
1232model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.gate_proj.biasesBF16640x40464affine15382370201538288220
1233model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.gate_proj.scalesBF16640x40464affine15396501401539701340
1234model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.gate_proj.weightU32640x320464affine15397013401540520540
1235model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.up_proj.biasesBF16640x40464affine21854827642185533964
1236model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.up_proj.scalesBF16640x40464affine15381307801538181980
1237model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert.up_proj.weightU32640x320464affine21493702842150189484
1238model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert_gate.biasesBF161x40464affine15380678041538067884
1239model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert_gate.scalesBF161x40464affine15380678841538067964
1240model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp.shared_expert_gate.weightU321x320464affine15380679641538069244
1241model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp_hyper_connection.block_inject_weight.weightBF164x1024015371257241537207644
1242model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp_hyper_connection.hc_norm.weightBF161024015297119641529732444
1243model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024015226668441529220444
1244model-00016-of-00017.safetensorslanguage_model.model.layers.25.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32030964589403103012540
1245model-00016-of-00017.safetensorslanguage_model.model.layers.26.attn_hyper_connection.block_inject_weight.weightBF164x1024015225848441522666764
1246model-00016-of-00017.safetensorslanguage_model.model.layers.26.attn_hyper_connection.hc_norm.weightBF161024022065886842206609164
1247model-00016-of-00017.safetensorslanguage_model.model.layers.26.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024015145566841521110284
1248model-00016-of-00017.safetensorslanguage_model.model.layers.26.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32016467960441653349644
1249model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.A_logBF164815145565881514556684
1250model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.conv1d.weightBF1610240x4x134967370523496818972
1251model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.dt_biasBF164815145564921514556588
1252model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_a.biasesBF1648x40464affine35143949083514398748
1253model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_a.scalesBF1648x40464affine15138972921513901132
1254model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_a.weightU3248x320464affine704044500704105940
1255model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_b.biasesBF1648x40464affine15138934521513897292
1256model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_b.scalesBF1648x40464affine912881956912885796
1257model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_b.weightU3248x320464affine17070466841707108124
1258model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_qkv.biasesBF1610240x40464affine14999670521500786252
1259model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_qkv.scalesBF1610240x40464affine508902164509721364
1260model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_qkv.weightU3210240x320464affine15007862521513893452
1261model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_z.biasesBF166144x40464affine14994755321499967052
1262model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_z.scalesBF166144x40464affine20874251162087916636
1263model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.in_proj_z.weightU326144x320464affine14391128121446977132
1264model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.norm.weightBF1612814989837561498984012
1265model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.out_proj.biasesBF162560x96464affine14969971961497488716
1266model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.out_proj.scalesBF162560x96464affine14974887161497980236
1267model-00016-of-00017.safetensorslanguage_model.model.layers.26.linear_attn.out_proj.weightU322560x768464affine38290015643836865884
1268model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.gate.biasesBF16512x40864affine22690380122269078972
1269model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.gate.scalesBF16512x40864affine14955495161495590476
1270model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.gate.weightU32512x640864affine14955943161496905036
1271model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.down_proj.biasesBF162560x10464affine14945767161494627916
1272model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.down_proj.scalesBF162560x10464affine14946279161494679116
1273model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.down_proj.weightU322560x80464affine14947303161495549516
1274model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.gate_proj.biasesBF16640x40464affine18835673241883618524
1275model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.gate_proj.scalesBF16640x40464affine20253024282025353628
1276model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.gate_proj.weightU32640x320464affine23384535802339272780
1277model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.up_proj.biasesBF16640x40464affine35960822843596133484
1278model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.up_proj.scalesBF16640x40464affine14870695161487120716
1279model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert.up_proj.weightU32640x320464affine14871207161487939916
1280model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert_gate.biasesBF161x40464affine34604002363460400316
1281model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert_gate.scalesBF161x40464affine37679251643767925244
1282model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp.shared_expert_gate.weightU321x320464affine14868391161486840396
1283model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp_hyper_connection.block_inject_weight.weightBF164x1024014866751801486757100
1284model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp_hyper_connection.hc_norm.weightBF161024030694617723069482252
1285model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024014735679801480121580
1286model-00016-of-00017.safetensorslanguage_model.model.layers.26.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32014670105401473564140
1287model-00016-of-00017.safetensorslanguage_model.model.layers.27.attn_hyper_connection.block_inject_weight.weightBF164x1024014656179001465699820
1288model-00016-of-00017.safetensorslanguage_model.model.layers.27.attn_hyper_connection.hc_norm.weightBF161024014638873401463907820
1289model-00016-of-00017.safetensorslanguage_model.model.layers.27.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024014573094201463863020
1290model-00016-of-00017.safetensorslanguage_model.model.layers.27.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32030706294843077183084
1291model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.gate.biasesBF16512x40864affine14485439801448584940
1292model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.gate.scalesBF16512x40864affine14572684601457309420
1293model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.gate.weightU32512x640864affine23274148602328725580
1294model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.down_proj.biasesBF162560x10464affine16613612441661412444
1295model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.down_proj.scalesBF162560x10464affine14469772601447028460
1296model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.down_proj.weightU322560x80464affine14477247801448543980
1297model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.gate_proj.biasesBF16640x40464affine14390616121439112812
1298model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.gate_proj.scalesBF16640x40464affine20116114682011662668
1299model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.gate_proj.weightU32640x320464affine17483108921749130092
1300model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.up_proj.biasesBF16640x40464affine18572936761857344876
1301model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.up_proj.scalesBF16640x40464affine17797736281779824828
1302model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert.up_proj.weightU32640x320464affine14382424121439061612
1303model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert_gate.biasesBF161x40464affine23008713402300871420
1304model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert_gate.scalesBF161x40464affine24411726522441172732
1305model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp.shared_expert_gate.weightU321x320464affine14880218361488023116
1306model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp_hyper_connection.block_inject_weight.weightBF164x1024014381604921438242412
1307model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp_hyper_connection.hc_norm.weightBF161024025071285722507149052
1308model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024014316068921438160492
1309model-00016-of-00017.safetensorslanguage_model.model.layers.27.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32018836698201890223420
1310model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine22522402202252291420
1311model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine13581124441358163644
1312model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.indexer.index_qk_proj.weightU32640x640864affine14298660921431504492
1313model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.indexer.k_layernorm.weightBF1612814298658361429866092
1314model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.indexer.q_layernorm.weightBF1612814298655801429865836
1315model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.k_norm.weightBF1625614298650681429865580
1316model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.k_proj.biasesBF16512x40464affine12956059161295646876
1317model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.k_proj.scalesBF16512x40464affine14298241081429865068
1318model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.k_proj.weightU32512x320464affine24104755962411130956
1319model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.o_proj.biasesBF162560x96464affine14222362681422727788
1320model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.o_proj.scalesBF162560x96464affine14292813881429772908
1321model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.o_proj.weightU322560x768464affine22522914202260155740
1322model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.q_norm.weightBF1625621021928122102193324
1323model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.q_proj.biasesBF1612288x40464affine37272847163728267756
1324model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.q_proj.scalesBF1612288x40464affine14212532281422236268
1325model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.q_proj.weightU3212288x320464affine34978061083513534748
1326model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.v_proj.biasesBF16512x40464affine14194714681419512428
1327model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.v_proj.scalesBF16512x40464affine22408019642240842924
1328model-00016-of-00017.safetensorslanguage_model.model.layers.27.self_attn.v_proj.weightU32512x320464affine14197274681420382828
1329model-00016-of-00017.safetensorslanguage_model.model.layers.28.attn_hyper_connection.block_inject_weight.weightBF164x1024023954842362395566156
1330model-00016-of-00017.safetensorslanguage_model.model.layers.28.attn_hyper_connection.hc_norm.weightBF161024015811710361581191516
1331model-00016-of-00017.safetensorslanguage_model.model.layers.28.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024014129178681419471468
1332model-00016-of-00017.safetensorslanguage_model.model.layers.28.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32014063642681412917868
1333model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.A_logBF164822690379162269038012
1334model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.conv1d.weightBF1610240x4x114062375481406319468
1335model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.dt_biasBF164825212843642521284460
1336model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_a.biasesBF1648x40464affine14061684281406172268
1337model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_a.scalesBF1648x40464affine14061722681406176108
1338model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_a.weightU3248x320464affine14061761081406237548
1339model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_b.biasesBF1648x40464affine34901386523490142492
1340model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_b.scalesBF1648x40464affine14061645881406168428
1341model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_b.weightU3248x320464affine15406948761540756316
1342model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_qkv.biasesBF1610240x40464affine14045057081405324908
1343model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_qkv.scalesBF1610240x40464affine14053453881406164588
1344model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_qkv.weightU3210240x320464affine12718989401285006140
1345model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_z.biasesBF166144x40464affine831152084831643604
1346model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_z.scalesBF166144x40464affine16889281881689419708
1347model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.in_proj_z.weightU326144x320464affine31030332763110897596
1348model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.norm.weightBF1612813966411321396641388
1349model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.out_proj.biasesBF162560x96464affine677821044678312564
1350model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.out_proj.scalesBF162560x96464affine20675264602068017980
1351model-00016-of-00017.safetensorslanguage_model.model.layers.28.linear_attn.out_proj.weightU322560x768464affine13887768121396641132
1352model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.gate.biasesBF16512x40864affine13873802361387421196
1353model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.gate.scalesBF16512x40864affine13874212921387462252
1354model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.gate.weightU32512x640864affine13874622521388772972
1355model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.down_proj.biasesBF162560x10464affine13731978361373249036
1356model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.down_proj.scalesBF162560x10464affine13734026361373453836
1357model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.down_proj.weightU322560x80464affine13865610361387380236
1358model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.gate_proj.biasesBF16640x40464affine18169272601816978460
1359model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.gate_proj.scalesBF16640x40464affine649359636649410836
1360model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.gate_proj.weightU32640x320464affine35238234843524642684
1361model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.up_proj.biasesBF16640x40464affine13648829561364934156
1362model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.up_proj.scalesBF16640x40464affine13649341561364985356
1363model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert.up_proj.weightU32640x320464affine13658045561366623756
1364model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert_gate.biasesBF161x40464affine15405411001540541180
1365model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert_gate.scalesBF161x40464affine13581636441358163724
1366model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp.shared_expert_gate.weightU321x320464affine13647992441364800524
1367model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp_hyper_connection.block_inject_weight.weightBF164x1024013580304281358112348
1368model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp_hyper_connection.hc_norm.weightBF161024013571497881357170268
1369model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024013666237561373177356
1370model-00016-of-00017.safetensorslanguage_model.model.layers.28.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32037988032923805356892
1371model-00016-of-00017.safetensorslanguage_model.model.layers.29.attn_hyper_connection.block_inject_weight.weightBF164x1024013492035481349285468
1372model-00016-of-00017.safetensorslanguage_model.model.layers.29.attn_hyper_connection.hc_norm.weightBF161024013491830681349203548
1373model-00016-of-00017.safetensorslanguage_model.model.layers.29.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024035894774843596031084
1374model-00016-of-00017.safetensorslanguage_model.model.layers.29.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32013426294681349183068
1375model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.A_logBF164816630508441663050940
1376model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.conv1d.weightBF1610240x4x116336069241633688844
1377model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.dt_biasBF164813426293721342629468
1378model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_a.biasesBF1648x40464affine17502680121750271852
1379model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_a.scalesBF1648x40464affine13359796761335983516
1380model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_a.weightU3248x320464affine18832562041883317644
1381model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_b.biasesBF1648x40464affine13344974361334501276
1382model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_b.scalesBF1648x40464affine13345012761334505116
1383model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_b.weightU3248x320464affine18130935641813155004
1384model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_qkv.biasesBF1610240x40464affine13066446361307463836
1385model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_qkv.scalesBF1610240x40464affine13205710361321390236
1386model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_qkv.weightU3210240x320464affine13213902361334497436
1387model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_z.biasesBF166144x40464affine12974491161297940636
1388model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_z.scalesBF166144x40464affine30310066523031498172
1389model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.in_proj_z.weightU326144x320464affine12979406361305804956
1390model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.norm.weightBF1612820673911322067391388
1391model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.out_proj.biasesBF162560x96464affine12956468761296138396
1392model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.out_proj.scalesBF162560x96464affine12969575961297449116
1393model-00016-of-00017.safetensorslanguage_model.model.layers.29.linear_attn.out_proj.weightU322560x768464affine14494041401457268460
1394model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.gate.biasesBF16512x40864affine12954830361295523996
1395model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.gate.scalesBF16512x40864affine16011687161601209676
1396model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.gate.weightU32512x640864affine35533430843554653804
1397model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.down_proj.biasesBF162560x10464affine12937421401293793340
1398model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.down_proj.scalesBF162560x10464affine12937934361293844636
1399model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.down_proj.weightU322560x80464affine12938446361294663836
1400model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.gate_proj.biasesBF16640x40464affine42628498844262901084
1401model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.gate_proj.scalesBF16640x40464affine37763322843776383484
1402model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.gate_proj.weightU32640x320464affine30007087963001527996
1403model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.up_proj.biasesBF16640x40464affine12850074201285058620
1404model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.up_proj.scalesBF16640x40464affine31109493083111000508
1405model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert.up_proj.weightU32640x320464affine12929229401293742140
1406model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert_gate.biasesBF161x40464affine17096354361709635516
1407model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert_gate.scalesBF161x40464affine12718988601271898940
1408model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp.shared_expert_gate.weightU321x320464affine12850061401285007420
1409model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp_hyper_connection.block_inject_weight.weightBF164x1024022151187642215200684
1410model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp_hyper_connection.hc_norm.weightBF161024012639526201263973100
1411model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024015666673561573220956
1412model-00016-of-00017.safetensorslanguage_model.model.layers.29.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32021171411642123694764
1413model-00016-of-00017.safetensorslanguage_model.model.layers.3.attn_hyper_connection.block_inject_weight.weightBF164x1024012638701881263952108
1414model-00016-of-00017.safetensorslanguage_model.model.layers.3.attn_hyper_connection.hc_norm.weightBF161024012638497081263870188
1415model-00016-of-00017.safetensorslanguage_model.model.layers.3.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024012572922681263845868
1416model-00016-of-00017.safetensorslanguage_model.model.layers.3.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32012428742681249427868
1417model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.gate.biasesBF16512x40864affine35886096443588650604
1418model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.gate.scalesBF16512x40864affine12428332281242874188
1419model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.gate.weightU32512x640864affine37842478043785558524
1420model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.down_proj.biasesBF162560x10464affine12410924281241143628
1421model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.down_proj.scalesBF162560x10464affine12411436281241194828
1422model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.down_proj.weightU322560x80464affine12411948281242014028
1423model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.gate_proj.biasesBF16640x40464affine343788804343840004
1424model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.gate_proj.scalesBF16640x40464affine20007837722000834972
1425model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.gate_proj.weightU32640x320464affine12324089081233228108
1426model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.up_proj.biasesBF16640x40464affine12249439481224995148
1427model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.up_proj.scalesBF16640x40464affine43006672444300718444
1428model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert.up_proj.weightU32640x320464affine12249951481225814348
1429model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert_gate.biasesBF161x40464affine12249424121224942492
1430model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert_gate.scalesBF161x40464affine12249425881224942668
1431model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp.shared_expert_gate.weightU321x320464affine12249426681224943948
1432model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp_hyper_connection.block_inject_weight.weightBF164x1024037253492763725431196
1433model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp_hyper_connection.hc_norm.weightBF161024012249180121224938492
1434model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024012183639001224917500
1435model-00016-of-00017.safetensorslanguage_model.model.layers.3.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32023143076602320861260
1436model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine678312564678363764
1437model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine12183126201218363820
1438model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.indexer.index_qk_proj.weightU32640x640864affine30947693403096407740
1439model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.indexer.k_layernorm.weightBF1612812183123641218312620
1440model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.indexer.q_layernorm.weightBF1612812116765881211676844
1441model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.k_norm.weightBF1625612116351161211635628
1442model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.k_proj.biasesBF16512x40464affine18249249561824965916
1443model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.k_proj.scalesBF16512x40464affine24817039322481744892
1444model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.k_proj.weightU32512x320464affine20507725562051427916
1445model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.o_proj.biasesBF162560x96464affine12016370361202128556
1446model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.o_proj.scalesBF162560x96464affine12026200761203111596
1447model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.o_proj.weightU322560x768464affine12031154361210979756
1448model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.q_norm.weightBF1625613648005241364801036
1449model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.q_proj.biasesBF1612288x40464affine17775921721778575212
1450model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.q_proj.scalesBF1612288x40464affine12006539961201637036
1451model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.q_proj.weightU3212288x320464affine35366581243552386764
1452model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.v_proj.biasesBF16512x40464affine704105940704146900
1453model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.v_proj.scalesBF16512x40464affine19034266201903467580
1454model-00016-of-00017.safetensorslanguage_model.model.layers.3.self_attn.v_proj.weightU32512x320464affine10610790761061734436
1455model-00016-of-00017.safetensorslanguage_model.model.layers.30.attn_hyper_connection.block_inject_weight.weightBF164x1024014868403961486922316
1456model-00016-of-00017.safetensorslanguage_model.model.layers.30.attn_hyper_connection.hc_norm.weightBF161024030520805723052101052
1457model-00016-of-00017.safetensorslanguage_model.model.layers.30.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240912885796919439396
1458model-00016-of-00017.safetensorslanguage_model.model.layers.30.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32010778437481084397348
1459model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.A_logBF164811875467001187546796
1460model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.conv1d.weightBF1610240x4x114195943481419676268
1461model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.dt_biasBF164812249424921224942588
1462model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_a.biasesBF1648x40464affine11874814201187485260
1463model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_a.scalesBF1648x40464affine29509035002950907340
1464model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_a.weightU3248x320464affine11874852601187546700
1465model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_b.biasesBF1648x40464affine11866583801186662220
1466model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_b.scalesBF1648x40464affine37514756283751479468
1467model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_b.weightU3248x320464affine37881395163788200956
1468model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_qkv.biasesBF1610240x40464affine11635313401164350540
1469model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_qkv.scalesBF1610240x40464affine11661732601166992460
1470model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_qkv.weightU3210240x320464affine11669963001180103500
1471model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_z.biasesBF166144x40464affine22146272442215118764
1472model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_z.scalesBF166144x40464affine11619645241162456044
1473model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.in_proj_z.weightU326144x320464affine15427223961550586716
1474model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.norm.weightBF1612842984856924298485948
1475model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.out_proj.biasesBF162560x96464affine11625483001163039820
1476model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.out_proj.scalesBF162560x96464affine11630398201163531340
1477model-00016-of-00017.safetensorslanguage_model.model.layers.30.linear_attn.out_proj.weightU322560x768464affine42826642844290528604
1478model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.gate.biasesBF16512x40864affine11625073401162548300
1479model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.gate.scalesBF16512x40864affine18469921561847033116
1480model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.gate.weightU32512x640864affine14656998201467010540
1481model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.down_proj.biasesBF162560x10464affine11619133241161964524
1482model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.down_proj.scalesBF162560x10464affine11624560441162507244
1483model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.down_proj.weightU322560x80464affine10602597961061078996
1484model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.gate_proj.biasesBF16640x40464affine21320915642132142764
1485model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.gate_proj.scalesBF16640x40464affine11618621241161913324
1486model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.gate_proj.weightU32640x320464affine23293911802330210380
1487model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.up_proj.biasesBF16640x40464affine11609405241160991724
1488model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.up_proj.scalesBF16640x40464affine22678805402267931740
1489model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert.up_proj.weightU32640x320464affine11609917241161810924
1490model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert_gate.biasesBF161x40464affine434988212434988292
1491model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert_gate.scalesBF161x40464affine11601212441160121324
1492model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp.shared_expert_gate.weightU321x320464affine35734314043573432684
1493model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp_hyper_connection.block_inject_weight.weightBF164x1024011590037801159085700
1494model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp_hyper_connection.hc_norm.weightBF161024011589321001158952580
1495model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240632936964639490564
1496model-00016-of-00017.safetensorslanguage_model.model.layers.30.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32015297529241536306524
1497model-00016-of-00017.safetensorslanguage_model.model.layers.31.attn_hyper_connection.block_inject_weight.weightBF164x1024011588501801158932100
1498model-00016-of-00017.safetensorslanguage_model.model.layers.31.attn_hyper_connection.hc_norm.weightBF161024010617344361061754916
1499model-00016-of-00017.safetensorslanguage_model.model.layers.31.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240453813428460367028
1500model-00016-of-00017.safetensorslanguage_model.model.layers.31.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32011521621801158715780
1501model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.gate.biasesBF16512x40864affine10331055401033146500
1502model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.gate.scalesBF16512x40864affine11508105001150851460
1503model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.gate.weightU32512x640864affine11508514601152162180
1504model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.down_proj.biasesBF162560x10464affine37863777243786428924
1505model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.down_proj.scalesBF162560x10464affine537682452537733652
1506model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.down_proj.weightU322560x80464affine11499913001150810500
1507model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.gate_proj.biasesBF16640x40464affine13360244761336075676
1508model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.gate_proj.scalesBF16640x40464affine11499400201149991220
1509model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.gate_proj.weightU32640x320464affine365587556366406756
1510model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.up_proj.biasesBF16640x40464affine15391074201539158620
1511model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.up_proj.scalesBF16640x40464affine11490696201149120820
1512model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert.up_proj.weightU32640x320464affine11491208201149940020
1513model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert_gate.biasesBF161x40464affine11490489801149049060
1514model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert_gate.scalesBF161x40464affine11490490601149049140
1515model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp.shared_expert_gate.weightU321x320464affine29510113562951012636
1516model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp_hyper_connection.block_inject_weight.weightBF164x1024034968230683496904988
1517model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp_hyper_connection.hc_norm.weightBF161024022522196442252240124
1518model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024011424134601148967060
1519model-00016-of-00017.safetensorslanguage_model.model.layers.31.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32010698664521076420052
1520model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine11265824201126633620
1521model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine11423622601142413460
1522model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.indexer.index_qk_proj.weightU32640x640864affine17894417241791080124
1523model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.indexer.k_layernorm.weightBF1612811265820841126582340
1524model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.indexer.q_layernorm.weightBF1612811257216681125721924
1525model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.k_norm.weightBF16256988290948988291460
1526model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.k_proj.biasesBF16512x40464affine30925984603092639420
1527model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.k_proj.scalesBF16512x40464affine11178162921117857252
1528model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.k_proj.weightU32512x320464affine30174550363018110396
1529model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.o_proj.biasesBF162560x96464affine11049916201105483140
1530model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.o_proj.scalesBF162560x96464affine11173247721117816292
1531model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.o_proj.weightU322560x768464affine38211372443829001564
1532model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.q_norm.weightBF1625631108975963110898108
1533model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.q_proj.biasesBF1612288x40464affine11136140521114597092
1534model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.q_proj.scalesBF1612288x40464affine11145970921115580132
1535model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.q_proj.weightU3212288x320464affine25512711162566999756
1536model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.v_proj.biasesBF16512x40464affine552349972552390932
1537model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.v_proj.scalesBF16512x40464affine14969050361496945996
1538model-00016-of-00017.safetensorslanguage_model.model.layers.31.self_attn.v_proj.weightU32512x320464affine11129586921113614052
1539model-00016-of-00017.safetensorslanguage_model.model.layers.32.attn_hyper_connection.block_inject_weight.weightBF164x1024011128767721112958692
1540model-00016-of-00017.safetensorslanguage_model.model.layers.32.attn_hyper_connection.hc_norm.weightBF161024011128562921112876772
1541model-00016-of-00017.safetensorslanguage_model.model.layers.32.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240626383364632936964
1542model-00016-of-00017.safetensorslanguage_model.model.layers.32.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32011063024361112856036
1543model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.A_logBF164811063023401106302436
1544model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.conv1d.weightBF1610240x4x122601557402260237660
1545model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.dt_biasBF164811049915241104991620
1546model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_a.biasesBF1648x40464affine10984340841098437924
1547model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_a.scalesBF1648x40464affine20429961242042999964
1548model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_a.weightU3248x320464affine18831908281883252268
1549model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_b.biasesBF1648x40464affine10843973481084401188
1550model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_b.scalesBF1648x40464affine10844011881084405028
1551model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_b.weightU3248x320464affine10983723881098433828
1552model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_qkv.biasesBF1610240x40464affine10770245481077843748
1553model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_qkv.scalesBF1610240x40464affine26253493242626168524
1554model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_qkv.weightU3210240x320464affine23009367002314043900
1555model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_z.biasesBF166144x40464affine10765329481077024468
1556model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_z.scalesBF166144x40464affine10063138601006805380
1557model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.in_proj_z.weightU326144x320464affine21856158842193480204
1558model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.norm.weightBF1612810764712521076471508
1559model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.out_proj.biasesBF162560x96464affine18568020761857293596
1560model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.out_proj.scalesBF162560x96464affine35267252443527216764
1561model-00016-of-00017.safetensorslanguage_model.model.layers.32.linear_attn.out_proj.weightU322560x768464affine12850586201292922940
1562model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.gate.biasesBF16512x40864affine24966236122496664572
1563model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.gate.scalesBF16512x40864affine35733392443573380204
1564model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.gate.weightU32512x640864affine18147973401816108060
1565model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.down_proj.biasesBF162560x10464affine10764200521076471252
1566model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.down_proj.scalesBF162560x10464affine14315556921431606892
1567model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.down_proj.weightU322560x80464affine18139781401814797340
1568model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.gate_proj.biasesBF16640x40464affine22389485242238999724
1569model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.gate_proj.scalesBF16640x40464affine10618587721061909972
1570model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.gate_proj.weightU32640x320464affine10685147721069333972
1571model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.up_proj.biasesBF16640x40464affine22066091642206660364
1572model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.up_proj.scalesBF16640x40464affine10618074921061858692
1573model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert.up_proj.weightU32640x320464affine35228609243523680124
1574model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert_gate.biasesBF161x40464affine10597233961059723476
1575model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert_gate.scalesBF161x40464affine10610789961061079076
1576model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp.shared_expert_gate.weightU321x320464affine10617549161061756196
1577model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp_hyper_connection.block_inject_weight.weightBF164x1024030693286523069410572
1578model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp_hyper_connection.hc_norm.weightBF161024035227585243522779004
1579model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024010531185961059672196
1580model-00016-of-00017.safetensorslanguage_model.model.layers.32.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32010465033001053056900
1581model-00016-of-00017.safetensorslanguage_model.model.layers.33.attn_hyper_connection.block_inject_weight.weightBF164x1024010330197801033101700
1582model-00016-of-00017.safetensorslanguage_model.model.layers.33.attn_hyper_connection.hc_norm.weightBF161024010464316201046452100
1583model-00016-of-00017.safetensorslanguage_model.model.layers.33.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024010398268201046380420
1584model-00016-of-00017.safetensorslanguage_model.model.layers.33.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32022876075642294161164
1585model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.A_logBF164810617561961061756292
1586model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.conv1d.weightBF1610240x4x1386733236386815156
1587model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.dt_biasBF164816335556281633555724
1588model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_a.biasesBF1648x40464affine17894340441789437884
1589model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_a.scalesBF1648x40464affine21493664442149370284
1590model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_a.weightU3248x320464affine10332079401033269380
1591model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_b.biasesBF1648x40464affine10331017001033105540
1592model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_b.scalesBF1648x40464affine37882009563788204796
1593model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_b.weightU3248x320464affine10331465001033207940
1594model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_qkv.biasesBF1610240x40464affine23368151802337634380
1595model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_qkv.scalesBF1610240x40464affine24817448922482564092
1596model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_qkv.weightU3210240x320464affine10068053801019912580
1597model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_z.biasesBF166144x40464affine10058223401006313860
1598model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_z.scalesBF166144x40464affine15391586201539650140
1599model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.in_proj_z.weightU326144x320464affine12640140601271878380
1600model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.norm.weightBF1612818249247001824924956
1601model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.out_proj.biasesBF162560x96464affine10597234761060214996
1602model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.out_proj.scalesBF162560x96464affine997466500997958020
1603model-00016-of-00017.safetensorslanguage_model.model.layers.33.linear_attn.out_proj.weightU322560x768464affine9979580201005822340
1604model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.gate.biasesBF16512x40864affine988249988988290948
1605model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.gate.scalesBF16512x40864affine35135347483513575708
1606model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.gate.weightU32512x640864affine988291460989602180
1607model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.down_proj.biasesBF162560x10464affine19934992921993550492
1608model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.down_proj.scalesBF162560x10464affine30848876603084938860
1609model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.down_proj.weightU322560x80464affine34969049883497724188
1610model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.gate_proj.biasesBF16640x40464affine973449348973500548
1611model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.gate_proj.scalesBF16640x40464affine30925472603092598460
1612model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.gate_proj.weightU32640x320464affine986611588987430788
1613model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.up_proj.biasesBF16640x40464affine18042385241804289724
1614model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.up_proj.scalesBF16640x40464affine973398148973449348
1615model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert.up_proj.weightU32640x320464affine35355726843536391884
1616model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert_gate.biasesBF161x40464affine973377412973377492
1617model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert_gate.scalesBF161x40464affine973397972973398052
1618model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp.shared_expert_gate.weightU321x320464affine11590857001159086980
1619model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp_hyper_connection.block_inject_weight.weightBF164x1024018658953721865977292
1620model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp_hyper_connection.hc_norm.weightBF1610240973356932973377412
1621model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024024835164122490070012
1622model-00016-of-00017.safetensorslanguage_model.model.layers.33.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320966803332973356932
1623model-00016-of-00017.safetensorslanguage_model.model.layers.34.attn_hyper_connection.block_inject_weight.weightBF164x1024029785890362978670956
1624model-00016-of-00017.safetensorslanguage_model.model.layers.34.attn_hyper_connection.hc_norm.weightBF1610240973377492973397972
1625model-00016-of-00017.safetensorslanguage_model.model.layers.34.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240958939012965492612
1626model-00016-of-00017.safetensorslanguage_model.model.layers.34.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32011801047801186658380
1627model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.A_logBF164811625072441162507340
1628model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.conv1d.weightBF1610240x4x1958805892958887812
1629model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.dt_biasBF1648952252196952252292
1630model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_a.biasesBF1648x40464affine986607748986611588
1631model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_a.scalesBF1648x40464affine952248356952252196
1632model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_a.weightU3248x320464affine43007184444300779884
1633model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_b.biasesBF1648x40464affine846880804846884644
1634model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_b.scalesBF1648x40464affine10398229801039826820
1635model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_b.weightU3248x320464affine536258836536320276
1636model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_qkv.biasesBF1610240x40464affine928716836929536036
1637model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_qkv.scalesBF1610240x40464affine929587236930406436
1638model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_qkv.weightU3210240x320464affine930457636943564836
1639model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_z.biasesBF166144x40464affine11643505401164842060
1640model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_z.scalesBF166144x40464affine928225316928716836
1641model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.in_proj_z.weightU326144x320464affine20253958682033260188
1642model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.norm.weightBF1612822975634842297563740
1643model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.out_proj.biasesBF162560x96464affine12021285561202620076
1644model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.out_proj.scalesBF162560x96464affine15292204441529711964
1645model-00016-of-00017.safetensorslanguage_model.model.layers.34.linear_attn.out_proj.weightU322560x768464affine919439396927303716
1646model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.gate.biasesBF16512x40864affine858364196858405156
1647model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.gate.scalesBF16512x40864affine878270756878311716
1648model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.gate.weightU32512x640864affine878311716879622436
1649model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.down_proj.biasesBF162560x10464affine858261796858312996
1650model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.down_proj.scalesBF162560x10464affine858312996858364196
1651model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.down_proj.weightU322560x80464affine11601213241160940524
1652model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.gate_proj.biasesBF16640x40464affine17258980921725949292
1653model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.gate_proj.scalesBF16640x40464affine21634029242163454124
1654model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.gate_proj.weightU32640x320464affine25212844602522103660
1655model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.up_proj.biasesBF16640x40464affine14969459961496997196
1656model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.up_proj.scalesBF16640x40464affine17885633881788614588
1657model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert.up_proj.weightU32640x320464affine856787236857606436
1658model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert_gate.biasesBF161x40464affine849690756849690836
1659model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert_gate.scalesBF161x40464affine849690836849690916
1660model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp.shared_expert_gate.weightU321x320464affine35747946043574795884
1661model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp_hyper_connection.block_inject_weight.weightBF164x1024020754830362075564956
1662model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp_hyper_connection.hc_norm.weightBF1610240849670276849690756
1663model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024024271950522433748652
1664model-00016-of-00017.safetensorslanguage_model.model.layers.34.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32011186765481125230148
1665model-00016-of-00017.safetensorslanguage_model.model.layers.35.attn_hyper_connection.block_inject_weight.weightBF164x10240849588356849670276
1666model-00016-of-00017.safetensorslanguage_model.model.layers.35.attn_hyper_connection.hc_norm.weightBF161024023393547002339375180
1667model-00016-of-00017.safetensorslanguage_model.model.layers.35.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240719679700726233300
1668model-00016-of-00017.safetensorslanguage_model.model.layers.35.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32025381639162544717516
1669model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.gate.biasesBF16512x40864affine846884644846925604
1670model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.gate.scalesBF16512x40864affine848236420848277380
1671model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.gate.weightU32512x640864affine848277380849588100
1672model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.down_proj.biasesBF162560x10464affine35885584443588609644
1673model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.down_proj.scalesBF162560x10464affine36851567643685207964
1674model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.down_proj.weightU322560x80464affine839508004840327204
1675model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.gate_proj.biasesBF16640x40464affine36027280443602779244
1676model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.gate_proj.scalesBF16640x40464affine16335044281633555628
1677model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.gate_proj.weightU32640x320464affine831643604832462804
1678model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.up_proj.biasesBF16640x40464affine18836185241883669724
1679model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.up_proj.scalesBF16640x40464affine11587170601158768260
1680model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert.up_proj.weightU32640x320464affine13649853561365804556
1681model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert_gate.biasesBF161x40464affine824105604824105684
1682model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert_gate.scalesBF161x40464affine35277082843527708364
1683model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp.shared_expert_gate.weightU321x320464affine831150804831152084
1684model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp_hyper_connection.block_inject_weight.weightBF164x1024012182304441218312364
1685model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp_hyper_connection.hc_norm.weightBF161024014989632761498983756
1686model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240817500804824054404
1687model-00016-of-00017.safetensorslanguage_model.model.layers.35.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32010619099721068463572
1688model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine816087684816138884
1689model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine817449604817500804
1690model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.indexer.index_qk_proj.weightU32640x640864affine14639795001465617900
1691model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.indexer.k_layernorm.weightBF1612829509073402950907596
1692model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.indexer.q_layernorm.weightBF16128816001668816001924
1693model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.k_norm.weightBF1625626026963962602696908
1694model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.k_proj.biasesBF16512x40464affine14879808761488021836
1695model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.k_proj.scalesBF16512x40464affine14063233081406364268
1696model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.k_proj.weightU32512x320464affine35747958843575451244
1697model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.o_proj.biasesBF162560x96464affine807645828808137348
1698model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.o_proj.scalesBF162560x96464affine19936733721994164892
1699model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.o_proj.weightU322560x768464affine808137348816001668
1700model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.q_norm.weightBF16256807645316807645828
1701model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.q_proj.biasesBF1612288x40464affine22602376602261220700
1702model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.q_proj.scalesBF1612288x40464affine30839043643084887404
1703model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.q_proj.weightU3212288x320464affine22217542842237482924
1704model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.v_proj.biasesBF16512x40464affine26043368442604377804
1705model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.v_proj.scalesBF16512x40464affine26036493082603690268
1706model-00016-of-00017.safetensorslanguage_model.model.layers.35.self_attn.v_proj.weightU32512x320464affine14470694201447724780
1707model-00016-of-00017.safetensorslanguage_model.model.layers.36.attn_hyper_connection.block_inject_weight.weightBF164x10240755052676755134596
1708model-00016-of-00017.safetensorslanguage_model.model.layers.36.attn_hyper_connection.hc_norm.weightBF1610240754209156754229636
1709model-00016-of-00017.safetensorslanguage_model.model.layers.36.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024025072144282513768028
1710model-00016-of-00017.safetensorslanguage_model.model.layers.36.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32042919319964298485596
1711model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.A_logBF164837357468923735746988
1712model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.conv1d.weightBF1610240x4x135365250043536606924
1713model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.dt_biasBF164816012649721601265068
1714model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_a.biasesBF1648x40464affine23141258202314129660
1715model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_a.scalesBF1648x40464affine19051983961905202236
1716model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_a.weightU3248x320464affine30687756923068837132
1717model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_b.biasesBF1648x40464affine442463572442467412
1718model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_b.scalesBF1648x40464affine17081872441708191084
1719model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_b.weightU3248x320464affine508840724508902164
1720model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_qkv.biasesBF1610240x40464affine18559828761856802076
1721model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_qkv.scalesBF1610240x40464affine728998180729817380
1722model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_qkv.weightU3210240x320464affine38079788443821086044
1723model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_z.biasesBF166144x40464affine753174916753666436
1724model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_z.scalesBF166144x40464affine753666436754157956
1725model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.in_proj_z.weightU326144x320464affine603156324611020644
1726model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.norm.weightBF1612820874248602087425116
1727model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.out_proj.biasesBF162560x96464affine752191876752683396
1728model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.out_proj.scalesBF162560x96464affine752683396753174916
1729model-00016-of-00017.safetensorslanguage_model.model.layers.36.linear_attn.out_proj.weightU322560x768464affine989602180997466500
1730model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.gate.biasesBF16512x40864affine728957220728998180
1731model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.gate.scalesBF16512x40864affine729817380729858340
1732model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.gate.weightU32512x640864affine16099485881611259308
1733model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.down_proj.biasesBF162560x10464affine15381858201538237020
1734model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.down_proj.scalesBF162560x10464affine18469409561846992156
1735model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.down_proj.weightU322560x80464affine35739242043574743404
1736model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.gate_proj.biasesBF16640x40464affine509938196509989396
1737model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.gate_proj.scalesBF16640x40464affine728854820728906020
1738model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.gate_proj.weightU32640x320464affine22680853402268904540
1739model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.up_proj.biasesBF16640x40464affine10463804201046431620
1740model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.up_proj.scalesBF16640x40464affine754157956754209156
1741model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert.up_proj.weightU32640x320464affine728035620728854820
1742model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert_gate.biasesBF161x40464affine726233300726233380
1743model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert_gate.scalesBF161x40464affine17081871641708187244
1744model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp.shared_expert_gate.weightU321x320464affine719678420719679700
1745model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp_hyper_connection.block_inject_weight.weightBF164x10240719555540719637460
1746model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp_hyper_connection.hc_norm.weightBF161024022521991642252219644
1747model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240712182740718736340
1748model-00016-of-00017.safetensorslanguage_model.model.layers.36.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320704154580710708180
1749model-00016-of-00017.safetensorslanguage_model.model.layers.37.attn_hyper_connection.block_inject_weight.weightBF164x10240703962580704044500
1750model-00016-of-00017.safetensorslanguage_model.model.layers.37.attn_hyper_connection.hc_norm.weightBF1610240703942100703962580
1751model-00016-of-00017.safetensorslanguage_model.model.layers.37.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240905836836912390436
1752model-00016-of-00017.safetensorslanguage_model.model.layers.37.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32015813401561587893756
1753model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.A_logBF164820440959802044096076
1754model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.conv1d.weightBF1610240x4x114869261561487008076
1755model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.dt_biasBF1648703942004703942100
1756model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_a.biasesBF1648x40464affine17409342521740938092
1757model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_a.scalesBF1648x40464affine703938164703942004
1758model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_a.weightU3248x320464affine20115500282011611468
1759model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_b.biasesBF1648x40464affine704146900704150740
1760model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_b.scalesBF1648x40464affine755048836755052676
1761model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_b.weightU3248x320464affine10764715081076532948
1762model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_qkv.biasesBF1610240x40464affine689086324689905524
1763model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_qkv.scalesBF1610240x40464affine689905524690724724
1764model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_qkv.weightU3210240x320464affine690724724703831924
1765model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_z.biasesBF166144x40464affine17325067321732998252
1766model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_z.scalesBF166144x40464affine680669044681160564
1767model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.in_proj_z.weightU326144x320464affine681160564689024884
1768model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.norm.weightBF1612820515507962051551052
1769model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.out_proj.biasesBF162560x96464affine15220933241522584844
1770model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.out_proj.scalesBF162560x96464affine21237357242124227244
1771model-00016-of-00017.safetensorslanguage_model.model.layers.37.linear_attn.out_proj.weightU322560x768464affine23600435962367907916
1772model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.gate.biasesBF16512x40864affine13359835161336024476
1773model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.gate.scalesBF16512x40864affine679317364679358324
1774model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.gate.weightU32512x640864affine679358324680669044
1775model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.down_proj.biasesBF162560x10464affine24411727322441223932
1776model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.down_proj.scalesBF162560x10464affine856244516856295716
1777model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.down_proj.weightU322560x80464affine678498164679317364
1778model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.gate_proj.biasesBF16640x40464affine14639078201463959020
1779model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.gate_proj.scalesBF16640x40464affine36373922043637443404
1780model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.gate_proj.weightU32640x320464affine17088162361709635436
1781model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.up_proj.biasesBF16640x40464affine678446964678498164
1782model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.up_proj.scalesBF16640x40464affine929536036929587236
1783model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert.up_proj.weightU32640x320464affine16645772121665396412
1784model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert_gate.biasesBF161x40464affine677765492677765572
1785model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert_gate.scalesBF161x40464affine677765572677765652
1786model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp.shared_expert_gate.weightU321x320464affine678363764678365044
1787model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp_hyper_connection.block_inject_weight.weightBF164x10240676321652676403572
1788model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp_hyper_connection.hc_norm.weightBF1610240675737876675758356
1789model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024010332693801039822980
1790model-00016-of-00017.safetensorslanguage_model.model.layers.37.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320662630676669184276
1791model-00016-of-00017.safetensorslanguage_model.model.layers.38.attn_hyper_connection.block_inject_weight.weightBF164x10240755134596755216516
1792model-00016-of-00017.safetensorslanguage_model.model.layers.38.attn_hyper_connection.hc_norm.weightBF1610240655964436655984916
1793model-00016-of-00017.safetensorslanguage_model.model.layers.38.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024022152006842221754284
1794model-00016-of-00017.safetensorslanguage_model.model.layers.38.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320649410836655964436
1795model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.A_logBF1648649267380649267476
1796model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.conv1d.weightBF1610240x4x114867571961486839116
1797model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.dt_biasBF164824271872762427187372
1798model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_a.biasesBF1648x40464affine649212340649216180
1799model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_a.scalesBF1648x40464affine19033715801903375420
1800model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_a.weightU3248x320464affine16798860921679947532
1801model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_b.biasesBF1648x40464affine649208500649212340
1802model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_b.scalesBF1648x40464affine20867142682086718108
1803model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_b.weightU3248x320464affine30674035323067464972
1804model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_qkv.biasesBF1610240x40464affine648389204649208404
1805model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_qkv.scalesBF1610240x40464affine25228204602523639660
1806model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_qkv.weightU3210240x320464affine30381132123051220412
1807model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_z.biasesBF166144x40464affine639490564639982084
1808model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_z.scalesBF166144x40464affine639982084640473604
1809model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.in_proj_z.weightU326144x320464affine640524804648389124
1810model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.norm.weightBF1612838061763483806176604
1811model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.out_proj.biasesBF162560x96464affine18244331801824924700
1812model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.out_proj.scalesBF162560x96464affine625891844626383364
1813model-00016-of-00017.safetensorslanguage_model.model.layers.38.linear_attn.out_proj.weightU322560x768464affine13492854681357149788
1814model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.gate.biasesBF16512x40864affine625809924625850884
1815model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.gate.scalesBF16512x40864affine625850884625891844
1816model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.gate.weightU32512x640864affine22986184602299929180
1817model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.down_proj.biasesBF162560x10464affine25380575802538108780
1818model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.down_proj.scalesBF162560x10464affine14946791161494730316
1819model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.down_proj.weightU322560x80464affine20102352922011054492
1820model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.gate_proj.biasesBF16640x40464affine625676804625728004
1821model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.gate_proj.scalesBF16640x40464affine22386618042238713004
1822model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.gate_proj.weightU32640x320464affine31266068763127426076
1823model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.up_proj.biasesBF16640x40464affine10684635721068514772
1824model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.up_proj.scalesBF16640x40464affine625625604625676804
1825model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert.up_proj.weightU32640x320464affine14204340281421253228
1826model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert_gate.biasesBF161x40464affine624967524624967604
1827model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert_gate.scalesBF161x40464affine625622964625623044
1828model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp.shared_expert_gate.weightU321x320464affine625623044625624324
1829model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp_hyper_connection.block_inject_weight.weightBF164x1024016129796281613061548
1830model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp_hyper_connection.hc_norm.weightBF1610240624947044624967524
1831model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240618393444624947044
1832model-00016-of-00017.safetensorslanguage_model.model.layers.38.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320611020644617574244
1833model-00016-of-00017.safetensorslanguage_model.model.layers.39.attn_hyper_connection.block_inject_weight.weightBF164x1024022789503322279032252
1834model-00016-of-00017.safetensorslanguage_model.model.layers.39.attn_hyper_connection.hc_norm.weightBF1610240602644324602664804
1835model-00016-of-00017.safetensorslanguage_model.model.layers.39.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240596086628602640228
1836model-00016-of-00017.safetensorslanguage_model.model.layers.39.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32021634584762170012076
1837model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.gate.biasesBF16512x40864affine662589716662630676
1838model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.gate.scalesBF16512x40864affine596045668596086628
1839model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.gate.weightU32512x640864affine17578699321759180652
1840model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.down_proj.biasesBF162560x10464affine675758452675809652
1841model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.down_proj.scalesBF162560x10464affine595994468596045668
1842model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.down_proj.weightU322560x80464affine595154788595973988
1843model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.gate_proj.biasesBF16640x40464affine10596721961059723396
1844model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.gate_proj.scalesBF16640x40464affine35960310843596082284
1845model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.gate_proj.weightU32640x320464affine594335588595154788
1846model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.up_proj.biasesBF16640x40464affine677222772677273972
1847model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.up_proj.scalesBF16640x40464affine11618109241161862124
1848model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert.up_proj.weightU32640x320464affine20339155482034734748
1849model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert_gate.biasesBF161x40464affine11499912201149991300
1850model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert_gate.scalesBF161x40464affine593842708593842788
1851model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp.shared_expert_gate.weightU321x320464affine594334308594335588
1852model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp_hyper_connection.block_inject_weight.weightBF164x1024011587682601158850180
1853model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp_hyper_connection.hc_norm.weightBF161024037864806363786501116
1854model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024017811355481787689148
1855model-00016-of-00017.safetensorslanguage_model.model.layers.39.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320587289108593842708
1856model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine585548308585599508
1857model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine585599508585650708
1858model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.indexer.index_qk_proj.weightU32640x640864affine585650708587289108
1859model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.indexer.k_layernorm.weightBF16128585548052585548308
1860model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.indexer.q_layernorm.weightBF1612831257871643125787420
1861model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.k_norm.weightBF1625620779854362077985948
1862model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.k_proj.biasesBF16512x40464affine19798557721979896732
1863model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.k_proj.scalesBF16512x40464affine585507092585548052
1864model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.k_proj.weightU32512x320464affine20867694042087424764
1865model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.o_proj.biasesBF162560x96464affine577151252577642772
1866model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.o_proj.scalesBF162560x96464affine29865353562987026876
1867model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.o_proj.weightU322560x768464affine577642772585507092
1868model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.q_norm.weightBF1625617082730041708273516
1869model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.q_proj.biasesBF1612288x40464affine559620372560603412
1870model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.q_proj.scalesBF1612288x40464affine11590869801160070020
1871model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.q_proj.weightU3212288x320464affine560603412576332052
1872model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.v_proj.biasesBF16512x40464affine20765479962076588956
1873model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.v_proj.scalesBF16512x40464affine13571702681357211228
1874model-00016-of-00017.safetensorslanguage_model.model.layers.39.self_attn.v_proj.weightU32512x320464affine552411412553066772
1875model-00016-of-00017.safetensorslanguage_model.model.layers.4.attn_hyper_connection.block_inject_weight.weightBF164x1024014195124281419594348
1876model-00016-of-00017.safetensorslanguage_model.model.layers.4.attn_hyper_connection.hc_norm.weightBF1610240552390932552411412
1877model-00016-of-00017.safetensorslanguage_model.model.layers.4.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240832462804839016404
1878model-00016-of-00017.safetensorslanguage_model.model.layers.4.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320545796372552349972
1879model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.A_logBF1648973398052973398148
1880model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.conv1d.weightBF1610240x4x1537798932537880852
1881model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.dt_biasBF1648744276260744276356
1882model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_a.biasesBF1648x40464affine703883124703886964
1883model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_a.scalesBF1648x40464affine537733652537737492
1884model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_a.weightU3248x320464affine537737492537798932
1885model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_b.biasesBF1648x40464affine22876037242287607564
1886model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_b.scalesBF1648x40464affine30839005243083904364
1887model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_b.weightU3248x320464affine18835058841883567324
1888model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_qkv.biasesBF1610240x40464affine11054831401106302340
1889model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_qkv.scalesBF1610240x40464affine11155801321116399332
1890model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_qkv.weightU3210240x320464affine36558294043668936604
1891model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_z.biasesBF166144x40464affine35734326843573924204
1892model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_z.scalesBF166144x40464affine20357078042036199324
1893model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.in_proj_z.weightU326144x320464affine357063940364928260
1894model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.norm.weightBF16128537682196537682452
1895model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.out_proj.biasesBF162560x96464affine35571152443557606764
1896model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.out_proj.scalesBF162560x96464affine537190676537682196
1897model-00016-of-00017.safetensorslanguage_model.model.layers.4.linear_attn.out_proj.weightU322560x768464affine12494279481257292268
1898model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.gate.biasesBF16512x40864affine15406539161540694876
1899model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.gate.scalesBF16512x40864affine11257219241125762884
1900model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.gate.weightU32512x640864affine816138884817449604
1901model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.down_proj.biasesBF162560x10464affine11589525801159003780
1902model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.down_proj.scalesBF162560x10464affine536320276536371476
1903model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.down_proj.weightU322560x80464affine11257628841126582084
1904model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.gate_proj.biasesBF16640x40464affine677766004677817204
1905model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.gate_proj.scalesBF16640x40464affine536207636536258836
1906model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.gate_proj.weightU32640x320464affine18169784601817797660
1907model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.up_proj.biasesBF16640x40464affine10464521001046503300
1908model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.up_proj.scalesBF16640x40464affine509886996509938196
1909model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert.up_proj.weightU32640x320464affine37255950363726414236
1910model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert_gate.biasesBF161x40464affine15226667641522666844
1911model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert_gate.scalesBF161x40464affine12249423321224942412
1912model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp.shared_expert_gate.weightU321x320464affine509885204509886484
1913model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp_hyper_connection.block_inject_weight.weightBF164x10240509803284509885204
1914model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp_hyper_connection.hc_norm.weightBF161024013066241561306644636
1915model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024019131075161919661116
1916model-00016-of-00017.safetensorslanguage_model.model.layers.4.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32014227277881429281388
1917model-00016-of-00017.safetensorslanguage_model.model.layers.40.attn_hyper_connection.block_inject_weight.weightBF164x10240509721364509803284
1918model-00016-of-00017.safetensorslanguage_model.model.layers.40.attn_hyper_connection.hc_norm.weightBF1610240508820244508840724
1919model-00016-of-00017.safetensorslanguage_model.model.layers.40.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240502211604508765204
1920model-00016-of-00017.safetensorslanguage_model.model.layers.40.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320655984916662538516
1921model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.A_logBF164813581123481358112444
1922model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.conv1d.weightBF1610240x4x1502129684502211604
1923model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.dt_biasBF1648501638068501638164
1924model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_a.biasesBF1648x40464affine501634228501638068
1925model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_a.scalesBF1648x40464affine15381819801538185820
1926model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_a.weightU3248x320464affine36106656763610727116
1927model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_b.biasesBF1648x40464affine23395083002339512140
1928model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_b.scalesBF1648x40464affine35533392443553343084
1929model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_b.weightU3248x320464affine501572788501634228
1930model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_qkv.biasesBF1610240x40464affine500262068501081268
1931model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_qkv.scalesBF1610240x40464affine30166358363017455036
1932model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_qkv.weightU3210240x320464affine10852242281098331428
1933model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_z.biasesBF166144x40464affine856295716856787236
1934model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_z.scalesBF166144x40464affine21700818042170573324
1935model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.in_proj_z.weightU326144x320464affine492315828500180148
1936model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.norm.weightBF1612837527901883752790444
1937model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.out_proj.biasesBF162560x96464affine460367028460858548
1938model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.out_proj.scalesBF162560x96464affine476587188477078708
1939model-00016-of-00017.safetensorslanguage_model.model.layers.40.linear_attn.out_proj.weightU322560x768464affine484451508492315828
1940model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.gate.biasesBF16512x40864affine452461748452502708
1941model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.gate.scalesBF16512x40864affine15372076441537248604
1942model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.gate.weightU32512x640864affine452502708453813428
1943model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.down_proj.biasesBF162560x10464affine442412372442463572
1944model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.down_proj.scalesBF162560x10464affine37864289243786480124
1945model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.down_proj.weightU322560x80464affine442467412443286612
1946model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.gate_proj.biasesBF16640x40464affine17500721721750123372
1947model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.gate_proj.scalesBF16640x40464affine25146283642514679564
1948model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.gate_proj.weightU32640x320464affine441593172442412372
1949model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.up_proj.biasesBF16640x40464affine441541972441593172
1950model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.up_proj.scalesBF16640x40464affine752140676752191876
1951model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert.up_proj.weightU32640x320464affine576332052577151252
1952model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert_gate.biasesBF161x40464affine441541892441541972
1953model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert_gate.scalesBF161x40464affine15813400761581340156
1954model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp.shared_expert_gate.weightU321x320464affine34835018523483503132
1955model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp_hyper_connection.block_inject_weight.weightBF164x10240816005764816087684
1956model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp_hyper_connection.hc_norm.weightBF161024030923629403092383420
1957model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024014801215801486675180
1958model-00016-of-00017.safetensorslanguage_model.model.layers.40.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320434988292441541892
1959model-00016-of-00017.safetensorslanguage_model.model.layers.41.attn_hyper_connection.block_inject_weight.weightBF164x10240434906292434988212
1960model-00016-of-00017.safetensorslanguage_model.model.layers.41.attn_hyper_connection.hc_norm.weightBF1610240434885812434906292
1961model-00016-of-00017.safetensorslanguage_model.model.layers.41.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240428332212434885812
1962model-00016-of-00017.safetensorslanguage_model.model.layers.41.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320421778612428332212
1963model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.A_logBF1648677765908677766004
1964model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.conv1d.weightBF1610240x4x120674445402067526460
1965model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.dt_biasBF164811186764521118676548
1966model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_a.biasesBF1648x40464affine13887729721388776812
1967model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_a.scalesBF1648x40464affine421713332421717172
1968model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_a.weightU3248x320464affine421717172421778612
1969model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_b.biasesBF1648x40464affine14063194681406323308
1970model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_b.scalesBF1648x40464affine11164607721116464612
1971model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_b.weightU3248x320464affine24973762522497437692
1972model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_qkv.biasesBF1610240x40464affine394679476395498676
1973model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_qkv.scalesBF1610240x40464affine31249679643125787164
1974model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_qkv.weightU3210240x320464affine395498676408605876
1975model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_z.biasesBF166144x40464affine35261722843526663804
1976model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_z.scalesBF166144x40464affine711691220712182740
1977model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.in_proj_z.weightU326144x320464affine386815156394679476
1978model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.norm.weightBF1612830706292283070629484
1979model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.out_proj.biasesBF162560x96464affine11252301481125721668
1980model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.out_proj.scalesBF162560x96464affine37522986683752790188
1981model-00016-of-00017.safetensorslanguage_model.model.layers.41.linear_attn.out_proj.weightU322560x768464affine944384036952248356
1982model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.gate.biasesBF16512x40864affine386692276386733236
1983model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.gate.scalesBF16512x40864affine20356668442035707804
1984model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.gate.weightU32512x640864affine17798248281781135548
1985model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.down_proj.biasesBF162560x10464affine17578187321757869932
1986model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.down_proj.scalesBF162560x10464affine25212331642521284364
1987model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.down_proj.weightU322560x80464affine20858950682086714268
1988model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.gate_proj.biasesBF16640x40464affine35547459643554797164
1989model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.gate_proj.scalesBF16640x40464affine37290907963729141996
1990model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.gate_proj.weightU32640x320464affine37245298203725349020
1991model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.up_proj.biasesBF16640x40464affine386641076386692276
1992model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.up_proj.scalesBF16640x40464affine38210860443821137244
1993model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert.up_proj.weightU32640x320464affine36374651643638284364
1994model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert_gate.biasesBF161x40464affine20121541882012154268
1995model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert_gate.scalesBF161x40464affine386640996386641076
1996model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp.shared_expert_gate.weightU321x320464affine36374638843637465164
1997model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp_hyper_connection.block_inject_weight.weightBF164x1024011489670601149048980
1998model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp_hyper_connection.hc_norm.weightBF161024015297324441529752924
1999model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240380087396386640996
2000model-00016-of-00017.safetensorslanguage_model.model.layers.41.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320373533796380087396
2001model-00016-of-00017.safetensorslanguage_model.model.layers.42.attn_hyper_connection.block_inject_weight.weightBF164x10240372960356373042276
2002model-00016-of-00017.safetensorslanguage_model.model.layers.42.attn_hyper_connection.hc_norm.weightBF1610240676301172676321652
2003model-00016-of-00017.safetensorslanguage_model.model.layers.42.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024029510638362957617436
2004model-00016-of-00017.safetensorslanguage_model.model.layers.42.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320366406756372960356
2005model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.A_logBF1648848236324848236420
2006model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.conv1d.weightBF1610240x4x121492845242149366444
2007model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.dt_biasBF1648365587460365587556
2008model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_a.biasesBF1648x40464affine357060100357063940
2009model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_a.scalesBF1648x40464affine364928260364932100
2010model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_a.weightU3248x320464affine13732490361373310476
2011model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_b.biasesBF1648x40464affine509989396509993236
2012model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_b.scalesBF1648x40464affine21104877242110491564
2013model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_b.weightU3248x320464affine356998404357059844
2014model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_qkv.biasesBF1610240x40464affine15372486041538067804
2015model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_qkv.scalesBF1610240x40464affine18161080601816927260
2016model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_qkv.weightU3210240x320464affine343840004356947204
2017model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_z.biasesBF166144x40464affine373042276373533796
2018model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_z.scalesBF166144x40464affine602664804603156324
2019model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.in_proj_z.weightU326144x320464affine12332281081241092428
2020model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.norm.weightBF16128343788548343788804
2021model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.out_proj.biasesBF162560x96464affine334941188335432708
2022model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.out_proj.scalesBF162560x96464affine335432708335924228
2023model-00016-of-00017.safetensorslanguage_model.model.layers.42.linear_attn.out_proj.weightU322560x768464affine335924228343788548
2024model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.gate.biasesBF16512x40864affine333548548333589508
2025model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.gate.scalesBF16512x40864affine333589508333630468
2026model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.gate.weightU32512x640864affine333630468334941188
2027model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.down_proj.biasesBF162560x10464affine332626948332678148
2028model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.down_proj.scalesBF162560x10464affine332678148332729348
2029model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.down_proj.weightU322560x80464affine332729348333548548
2030model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.gate_proj.biasesBF16640x40464affine332524548332575748
2031model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.gate_proj.scalesBF16640x40464affine332575748332626948
2032model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.gate_proj.weightU32640x320464affine15519012761552720476
2033model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.up_proj.biasesBF16640x40464affine35523867643552437964
2034model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.up_proj.scalesBF16640x40464affine332473348332524548
2035model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert.up_proj.weightU32640x320464affine38061766043806995804
2036model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert_gate.biasesBF161x40464affine12494278681249427948
2037model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert_gate.scalesBF161x40464affine18572935961857293676
2038model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp.shared_expert_gate.weightU321x320464affine332420868332422148
2039model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp_hyper_connection.block_inject_weight.weightBF164x10240332338948332420868
2040model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp_hyper_connection.hc_norm.weightBF1610240332318468332338948
2041model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024023534387962359992396
2042model-00016-of-00017.safetensorslanguage_model.model.layers.42.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32020680179802074571580
2043model-00016-of-00017.safetensorslanguage_model.model.layers.43.attn_hyper_connection.block_inject_weight.weightBF164x10240332236548332318468
2044model-00016-of-00017.safetensorslanguage_model.model.layers.43.attn_hyper_connection.hc_norm.weightBF161024022385069242238527404
2045model-00016-of-00017.safetensorslanguage_model.model.layers.43.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240325682948332236548
2046model-00016-of-00017.safetensorslanguage_model.model.layers.43.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320319129348325682948
2047model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.gate.biasesBF16512x40864affine34901424923490183452
2048model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.gate.scalesBF16512x40864affine317777668317818628
2049model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.gate.weightU32512x640864affine317818628319129348
2050model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.down_proj.biasesBF162560x10464affine26027789082602830108
2051model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.down_proj.scalesBF162560x10464affine316907268316958468
2052model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.down_proj.weightU322560x80464affine316958468317777668
2053model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.gate_proj.biasesBF16640x40464affine42989774684299028668
2054model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.gate_proj.scalesBF16640x40464affine316856068316907268
2055model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.gate_proj.weightU32640x320464affine22958009242296620124
2056model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.up_proj.biasesBF16640x40464affine16972841241697335324
2057model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.up_proj.scalesBF16640x40464affine315985668316036868
2058model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert.up_proj.weightU32640x320464affine316036868316856068
2059model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert_gate.biasesBF161x40464affine315984228315984308
2060model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert_gate.scalesBF161x40464affine315984308315984388
2061model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp.shared_expert_gate.weightU321x320464affine315984388315985668
2062model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp_hyper_connection.block_inject_weight.weightBF164x1024012955239961295605916
2063model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp_hyper_connection.hc_norm.weightBF161024011648420601164862540
2064model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240309430628315984228
2065model-00016-of-00017.safetensorslanguage_model.model.layers.43.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320302877028309430628
2066model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine302733668302784868
2067model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine302784868302836068
2068model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.indexer.index_qk_proj.weightU32640x640864affine19641372761965775676
2069model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.indexer.k_layernorm.weightBF16128357059844357060100
2070model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.indexer.q_layernorm.weightBF16128302733412302733668
2071model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.k_norm.weightBF16256296179300296179812
2072model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.k_proj.biasesBF16512x40464affine21395155642139556524
2073model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.k_proj.scalesBF16512x40464affine296138340296179300
2074model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.k_proj.weightU32512x320464affine24967196122497374972
2075model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.o_proj.biasesBF162560x96464affine287782500288274020
2076model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.o_proj.scalesBF162560x96464affine13345051161334996636
2077model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.o_proj.weightU322560x768464affine288274020296138340
2078model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.q_norm.weightBF16256287730788287731300
2079model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.q_proj.biasesBF1612288x40464affine15211102841522093324
2080model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.q_proj.scalesBF1612288x40464affine286747748287730788
2081model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.q_proj.weightU3212288x320464affine37357469883751475628
2082model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.v_proj.biasesBF16512x40464affine22384659642238506924
2083model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.v_proj.scalesBF16512x40464affine12116356281211676588
2084model-00016-of-00017.safetensorslanguage_model.model.layers.43.self_attn.v_proj.weightU32512x320464affine15139011321514556492
2085model-00016-of-00017.safetensorslanguage_model.model.layers.44.attn_hyper_connection.block_inject_weight.weightBF164x1024020524534522052535372
2086model-00016-of-00017.safetensorslanguage_model.model.layers.44.attn_hyper_connection.hc_norm.weightBF1610240286727268286747748
2087model-00016-of-00017.safetensorslanguage_model.model.layers.44.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024019353014361941855036
2088model-00016-of-00017.safetensorslanguage_model.model.layers.44.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320477078708483632308
2089model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.A_logBF1648286727172286727268
2090model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.conv1d.weightBF1610240x4x1286645252286727172
2091model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.dt_biasBF1648286645156286645252
2092model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_a.biasesBF1648x40464affine286637476286641316
2093model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_a.scalesBF1648x40464affine286641316286645156
2094model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_a.weightU3248x320464affine17775307321777592172
2095model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_b.biasesBF1648x40464affine11669924601166996300
2096model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_b.scalesBF1648x40464affine286572196286576036
2097model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_b.weightU3248x320464affine286576036286637476
2098model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_qkv.biasesBF1610240x40464affine12420140281242833228
2099model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_qkv.scalesBF1610240x40464affine272645796273464996
2100model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_qkv.weightU3210240x320464affine273464996286572196
2101model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_z.biasesBF166144x40464affine270843556271335076
2102model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_z.scalesBF166144x40464affine272154276272645796
2103model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.in_proj_z.weightU326144x320464affine37679252443775789564
2104model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.norm.weightBF1612834968228123496823068
2105model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.out_proj.biasesBF162560x96464affine262487716262979236
2106model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.out_proj.scalesBF162560x96464affine10693749321069866452
2107model-00016-of-00017.safetensorslanguage_model.model.layers.44.linear_attn.out_proj.weightU322560x768464affine262979236270843556
2108model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.gate.biasesBF16512x40864affine262405796262446756
2109model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.gate.scalesBF16512x40864affine262446756262487716
2110model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.gate.weightU32512x640864affine726233380727544100
2111model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.down_proj.biasesBF162560x10464affine262354596262405796
2112model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.down_proj.scalesBF162560x10464affine14203828281420434028
2113model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.down_proj.weightU322560x80464affine12946638361295483036
2114model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.gate_proj.biasesBF16640x40464affine22984648602298516060
2115model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.gate_proj.scalesBF16640x40464affine19196611161919712316
2116model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.gate_proj.weightU32640x320464affine17886145881789433788
2117model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.up_proj.biasesBF16640x40464affine23141501402314201340
2118model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.up_proj.scalesBF16640x40464affine261484196261535396
2119model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert.up_proj.weightU32640x320464affine261535396262354596
2120model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert_gate.biasesBF161x40464affine11265823401126582420
2121model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert_gate.scalesBF161x40464affine261482836261482916
2122model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp.shared_expert_gate.weightU321x320464affine261482916261484196
2123model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp_hyper_connection.block_inject_weight.weightBF164x1024016128977081612979628
2124model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp_hyper_connection.hc_norm.weightBF161024014638668601463887340
2125model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240254929236261482836
2126model-00016-of-00017.safetensorslanguage_model.model.layers.44.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320248375636254929236
2127model-00016-of-00017.safetensorslanguage_model.model.layers.45.attn_hyper_connection.block_inject_weight.weightBF164x1024036294254843629507404
2128model-00016-of-00017.safetensorslanguage_model.model.layers.45.attn_hyper_connection.hc_norm.weightBF161024031030125403103033020
2129model-00016-of-00017.safetensorslanguage_model.model.layers.45.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240241822036248375636
2130model-00016-of-00017.safetensorslanguage_model.model.layers.45.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320235268436241822036
2131model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.A_logBF164813874211961387421292
2132model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.conv1d.weightBF1610240x4x1235186516235268436
2133model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.dt_biasBF1648235186420235186516
2134model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_a.biasesBF1648x40464affine235178740235182580
2135model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_a.scalesBF1648x40464affine235182580235186420
2136model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_a.weightU3248x320464affine15405412761540602716
2137model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_b.biasesBF1648x40464affine235174900235178740
2138model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_b.scalesBF1648x40464affine816001924816005764
2139model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_b.weightU3248x320464affine19935504921993611932
2140model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_qkv.biasesBF1610240x40464affine30849900603085809260
2141model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_qkv.scalesBF1610240x40464affine38053568923806176092
2142model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_qkv.weightU3210240x320464affine29875183963000625596
2143model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_z.biasesBF166144x40464affine234683380235174900
2144model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_z.scalesBF166144x40464affine824105684824597204
2145model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.in_proj_z.weightU326144x320464affine25301932602538057580
2146model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.norm.weightBF16128234683124234683380
2147model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.out_proj.biasesBF162560x96464affine35143987483514890268
2148model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.out_proj.scalesBF162560x96464affine19484086361948900156
2149model-00016-of-00017.safetensorslanguage_model.model.layers.45.linear_attn.out_proj.weightU322560x768464affine37763834843784247804
2150model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.gate.biasesBF16512x40864affine26038043642603845324
2151model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.gate.scalesBF16512x40864affine12639731001264014060
2152model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.gate.weightU32512x640864affine965492612966803332
2153model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.down_proj.biasesBF162560x10464affine233812724233863924
2154model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.down_proj.scalesBF162560x10464affine18041873241804238524
2155model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.down_proj.weightU322560x80464affine233863924234683124
2156model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.gate_proj.biasesBF16640x40464affine232942324232993524
2157model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.gate_proj.scalesBF16640x40464affine287731300287782500
2158model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.gate_proj.weightU32640x320464affine232993524233812724
2159model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.up_proj.biasesBF16640x40464affine649267476649318676
2160model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.up_proj.scalesBF16640x40464affine232891124232942324
2161model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert.up_proj.weightU32640x320464affine24198144762420633676
2162model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert_gate.biasesBF161x40464affine35532571643553257244
2163model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert_gate.scalesBF161x40464affine15813399961581340076
2164model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp.shared_expert_gate.weightU321x320464affine232889844232891124
2165model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp_hyper_connection.block_inject_weight.weightBF164x1024013648010361364882956
2166model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp_hyper_connection.hc_norm.weightBF161024011490491401149069620
2167model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240226336244232889844
2168model-00016-of-00017.safetensorslanguage_model.model.layers.45.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320219782644226336244
2169model-00016-of-00017.safetensorslanguage_model.model.layers.46.attn_hyper_connection.block_inject_weight.weightBF164x1024018471150361847196956
2170model-00016-of-00017.safetensorslanguage_model.model.layers.46.attn_hyper_connection.hc_norm.weightBF1610240219762164219782644
2171model-00016-of-00017.safetensorslanguage_model.model.layers.46.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240213208564219762164
2172model-00016-of-00017.safetensorslanguage_model.model.layers.46.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32036917618203698315420
2173model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.A_logBF164818658952761865895372
2174model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.conv1d.weightBF1610240x4x1213126644213208564
2175model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.dt_biasBF1648213126548213126644
2176model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_a.biasesBF1648x40464affine213118868213122708
2177model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_a.scalesBF1648x40464affine213122708213126548
2178model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_a.weightU3248x320464affine16822412921682302732
2179model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_b.biasesBF1648x40464affine35246426843524646524
2180model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_b.scalesBF1648x40464affine213053588213057428
2181model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_b.weightU3248x320464affine213057428213118868
2182model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_qkv.biasesBF1610240x40464affine16533496441654168844
2183model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_qkv.scalesBF1610240x40464affine192573588193392788
2184model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_qkv.weightU3210240x320464affine193392788206499988
2185model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_z.biasesBF166144x40464affine183726228184217748
2186model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_z.scalesBF166144x40464affine184217748184709268
2187model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.in_proj_z.weightU326144x320464affine184709268192573588
2188model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.norm.weightBF16128183725972183726228
2189model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.out_proj.biasesBF162560x96464affine182742932183234452
2190model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.out_proj.scalesBF162560x96464affine183234452183725972
2191model-00016-of-00017.safetensorslanguage_model.model.layers.46.linear_attn.out_proj.weightU322560x768464affine17330699321740934252
2192model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.gate.biasesBF16512x40864affine10602149961060255956
2193model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.gate.scalesBF16512x40864affine182701972182742932
2194model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.gate.weightU32512x640864affine22508883642252199084
2195model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.down_proj.biasesBF162560x10464affine182650772182701972
2196model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.down_proj.scalesBF162560x10464affine356947204356998404
2197model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.down_proj.weightU322560x80464affine15382882201539107420
2198model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.gate_proj.biasesBF16640x40464affine649216180649267380
2199model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.gate_proj.scalesBF16640x40464affine29509601562951011356
2200model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.gate_proj.weightU32640x320464affine271335076272154276
2201model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.up_proj.biasesBF16640x40464affine508765204508816404
2202model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.up_proj.scalesBF16640x40464affine181780372181831572
2203model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert.up_proj.weightU32640x320464affine181831572182650772
2204model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert_gate.biasesBF161x40464affine181779012181779092
2205model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert_gate.scalesBF161x40464affine839016404839016484
2206model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp.shared_expert_gate.weightU321x320464affine181779092181780372
2207model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp_hyper_connection.block_inject_weight.weightBF164x10240181697092181779012
2208model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp_hyper_connection.hc_norm.weightBF1610240181676612181697092
2209model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240175123012181676612
2210model-00016-of-00017.safetensorslanguage_model.model.layers.46.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320168569412175123012
2211model-00016-of-00017.safetensorslanguage_model.model.layers.47.attn_hyper_connection.block_inject_weight.weightBF164x10240160623172160705092
2212model-00016-of-00017.safetensorslanguage_model.model.layers.47.attn_hyper_connection.hc_norm.weightBF161024015405205401540541020
2213model-00016-of-00017.safetensorslanguage_model.model.layers.47.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024010984379241104991524
2214model-00016-of-00017.safetensorslanguage_model.model.layers.47.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320154069572160623172
2215model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.gate.biasesBF16512x40864affine152717892152758852
2216model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.gate.scalesBF16512x40864affine302836068302877028
2217model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.gate.weightU32512x640864affine152758852154069572
2218model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.down_proj.biasesBF162560x10464affine151796292151847492
2219model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.down_proj.scalesBF162560x10464affine151847492151898692
2220model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.down_proj.weightU322560x80464affine151898692152717892
2221model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.gate_proj.biasesBF16640x40464affine150925892150977092
2222model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.gate_proj.scalesBF16640x40464affine545745172545796372
2223model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.gate_proj.weightU32640x320464affine150977092151796292
2224model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.up_proj.biasesBF16640x40464affine150004292150055492
2225model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.up_proj.scalesBF16640x40464affine150055492150106692
2226model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert.up_proj.weightU32640x320464affine150106692150925892
2227model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert_gate.biasesBF161x40464affine150002852150002932
2228model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert_gate.scalesBF161x40464affine150002932150003012
2229model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp.shared_expert_gate.weightU321x320464affine150003012150004292
2230model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp_hyper_connection.block_inject_weight.weightBF164x10240149920932150002852
2231model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp_hyper_connection.hc_norm.weightBF1610240149900452149920932
2232model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240143346852149900452
2233model-00016-of-00017.safetensorslanguage_model.model.layers.47.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320130239652136793252
2234model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine130137252130188452
2235model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine130188452130239652
2236model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.indexer.index_qk_proj.weightU32640x640864affine37865011163788139516
2237model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.indexer.k_layernorm.weightBF1612837253490203725349276
2238model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.indexer.q_layernorm.weightBF1612830189295963018929852
2239model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.k_norm.weightBF16256130094500130095012
2240model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.k_proj.biasesBF16512x40464affine29442372602944278220
2241model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.k_proj.scalesBF16512x40464affine10693339721069374932
2242model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.k_proj.weightU32512x320464affine129439140130094500
2243model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.o_proj.biasesBF162560x96464affine128456100128947620
2244model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.o_proj.scalesBF162560x96464affine128947620129439140
2245model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.o_proj.weightU322560x768464affine160705092168569412
2246model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.q_norm.weightBF1625621634541242163454636
2247model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.q_proj.biasesBF1612288x40464affine127473060128456100
2248model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.q_proj.scalesBF1612288x40464affine22374829242238465964
2249model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.q_proj.weightU3212288x320464affine36694281243685156764
2250model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.v_proj.biasesBF16512x40464affine127432100127473060
2251model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.v_proj.scalesBF16512x40464affine14879399161487980876
2252model-00016-of-00017.safetensorslanguage_model.model.layers.47.self_attn.v_proj.weightU32512x320464affine126776740127432100
2253model-00016-of-00017.safetensorslanguage_model.model.layers.5.attn_hyper_connection.block_inject_weight.weightBF164x10240126694820126776740
2254model-00016-of-00017.safetensorslanguage_model.model.layers.5.attn_hyper_connection.hc_norm.weightBF1610240126674340126694820
2255model-00016-of-00017.safetensorslanguage_model.model.layers.5.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024035654749243572028524
2256model-00016-of-00017.safetensorslanguage_model.model.layers.5.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320136793252143346852
2257model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.A_logBF1648126674244126674340
2258model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.conv1d.weightBF1610240x4x1126592324126674244
2259model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.dt_biasBF164815405411801540541276
2260model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_a.biasesBF1648x40464affine126522948126526788
2261model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_a.scalesBF1648x40464affine126527044126530884
2262model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_a.weightU3248x320464affine126530884126592324
2263model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_b.biasesBF1648x40464affine14638630201463866860
2264model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_b.scalesBF1648x40464affine23142014202314205260
2265model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_b.weightU3248x320464affine126461508126522948
2266model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_qkv.biasesBF1610240x40464affine125642308126461508
2267model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_qkv.scalesBF1610240x40464affine14485849401449404140
2268model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_qkv.weightU3210240x320464affine34703946523483501852
2269model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_z.biasesBF166144x40464affine20087197722009211292
2270model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_z.scalesBF166144x40464affine117286468117777988
2271model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.in_proj_z.weightU326144x320464affine117777988125642308
2272model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.norm.weightBF16128117286212117286468
2273model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.out_proj.biasesBF162560x96464affine108438852108930372
2274model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.out_proj.scalesBF162560x96464affine108930372109421892
2275model-00016-of-00017.safetensorslanguage_model.model.layers.5.linear_attn.out_proj.weightU322560x768464affine109421892117286212
2276model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.gate.biasesBF16512x40864affine31249270043124967964
2277model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.gate.scalesBF16512x40864affine108397892108438852
2278model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.gate.weightU32512x640864affine42905695644291880284
2279model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.down_proj.biasesBF162560x10464affine107527492107578692
2280model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.down_proj.scalesBF162560x10464affine30772957243077346924
2281model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.down_proj.weightU322560x80464affine107578692108397892
2282model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.gate_proj.biasesBF16640x40464affine17797224281779773628
2283model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.gate_proj.scalesBF16640x40464affine106657092106708292
2284model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.gate_proj.weightU32640x320464affine106708292107527492
2285model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.up_proj.biasesBF16640x40464affine105786692105837892
2286model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.up_proj.scalesBF16640x40464affine22689867162269037916
2287model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert.up_proj.weightU32640x320464affine105837892106657092
2288model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert_gate.biasesBF161x40464affine105786612105786692
2289model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert_gate.scalesBF161x40464affine37272334363727233516
2290model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp.shared_expert_gate.weightU321x320464affine130135972130137252
2291model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp_hyper_connection.block_inject_weight.weightBF164x1024023287255802328807500
2292model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp_hyper_connection.hc_norm.weightBF161024025071490522507169532
2293model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024099212532105766132
2294model-00016-of-00017.safetensorslanguage_model.model.layers.5.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32012258143481232367948
2295model-00016-of-00017.safetensorslanguage_model.model.layers.6.attn_hyper_connection.block_inject_weight.weightBF164x1024023392727802339354700
2296model-00016-of-00017.safetensorslanguage_model.model.layers.6.attn_hyper_connection.hc_norm.weightBF1610240105766132105786612
2297model-00016-of-00017.safetensorslanguage_model.model.layers.6.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024042760492444282602844
2298model-00016-of-00017.safetensorslanguage_model.model.layers.6.attn_hyper_connection.input_mix_weight_up.weightBF1610240x32014880231161494576716
2299model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.A_logBF16489921243699212532
2300model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.conv1d.weightBF1610240x4x116546642841654746204
2301model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.dt_biasBF16489921234099212436
2302model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_a.biasesBF1648x40464affine9914322099147060
2303model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_a.scalesBF1648x40464affine9914706099150900
2304model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_a.weightU3248x320464affine9915090099212340
2305model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_b.biasesBF1648x40464affine9907794099081780
2306model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_b.scalesBF1648x40464affine21170963642117100204
2307model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_b.weightU3248x320464affine9908178099143220
2308model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_qkv.biasesBF1610240x40464affine9743954098258740
2309model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_qkv.scalesBF1610240x40464affine9825874099077940
2310model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_qkv.weightU3210240x320464affine21934814842206588684
2311model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_z.biasesBF166144x40464affine9645650096948020
2312model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_z.scalesBF166144x40464affine9694802097439540
2313model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.in_proj_z.weightU326144x320464affine744276356752140676
2314model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.norm.weightBF161289645624496456500
2315model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.out_proj.biasesBF162560x96464affine8760888488100404
2316model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.out_proj.scalesBF162560x96464affine8810040488591924
2317model-00016-of-00017.safetensorslanguage_model.model.layers.6.linear_attn.out_proj.weightU322560x768464affine8859192496456244
2318model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.gate.biasesBF16512x40864affine19798147161979855676
2319model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.gate.scalesBF16512x40864affine42905286044290569564
2320model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.gate.weightU32512x640864affine8629816487608884
2321model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.down_proj.biasesBF162560x10464affine24337486522433799852
2322model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.down_proj.scalesBF162560x10464affine8542776485478964
2323model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.down_proj.weightU322560x80464affine8547896486298164
2324model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.gate_proj.biasesBF16640x40464affine22385286842238579884
2325model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.gate_proj.scalesBF16640x40464affine22388461242238897324
2326model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.gate_proj.weightU32640x320464affine8460856485427764
2327model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.up_proj.biasesBF16640x40464affine8455736484608564
2328model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.up_proj.scalesBF16640x40464affine14196762681419727468
2329model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert.up_proj.weightU32640x320464affine943564836944384036
2330model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert_gate.biasesBF161x40464affine8455720484557284
2331model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert_gate.scalesBF161x40464affine8455728484557364
2332model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp.shared_expert_gate.weightU321x320464affine22967430042296744284
2333model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp_hyper_connection.block_inject_weight.weightBF164x102408447528484557204
2334model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp_hyper_connection.hc_norm.weightBF1610240595973988595994468
2335model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp_hyper_connection.input_mix_weight_down.weightBF16320x1024035961334843602687084
2336model-00016-of-00017.safetensorslanguage_model.model.layers.6.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x3207792168484475284
2337model-00016-of-00017.safetensorslanguage_model.model.layers.7.attn_hyper_connection.block_inject_weight.weightBF164x102407783976477921684
2338model-00016-of-00017.safetensorslanguage_model.model.layers.7.attn_hyper_connection.hc_norm.weightBF16102407781928477839764
2339model-00016-of-00017.safetensorslanguage_model.model.layers.7.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024018325230361839076636
2340model-00016-of-00017.safetensorslanguage_model.model.layers.7.attn_hyper_connection.input_mix_weight_up.weightBF1610240x3207126568477819284
2341model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.gate.biasesBF16512x40864affine18831498681883190828
2342model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.gate.scalesBF16512x40864affine6991400469954964
2343model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.gate.weightU32512x640864affine6995496471265684
2344model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.down_proj.biasesBF162560x10464affine332422148332473348
2345model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.down_proj.scalesBF162560x10464affine35747434043574794604
2346model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.down_proj.weightU322560x80464affine6909480469914004
2347model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.gate_proj.biasesBF16640x40464affine6904360469094804
2348model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.gate_proj.scalesBF16640x40464affine930406436930457636
2349model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.gate_proj.weightU32640x320464affine23376343802338453580
2350model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.up_proj.biasesBF16640x40464affine6899240469043604
2351model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.up_proj.scalesBF16640x40464affine37356956923735746892
2352model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert.up_proj.weightU32640x320464affine536371476537190676
2353model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert_gate.biasesBF161x40464affine26026969082602696988
2354model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert_gate.scalesBF161x40464affine10618586921061858772
2355model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp.shared_expert_gate.weightU321x320464affine6899112468992404
2356model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp_hyper_connection.block_inject_weight.weightBF164x1024015810852761581167196
2357model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp_hyper_connection.hc_norm.weightBF16102406897064468991124
2358model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp_hyper_connection.input_mix_weight_down.weightBF16320x102406241704468970644
2359model-00016-of-00017.safetensorslanguage_model.model.layers.7.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320296179812302733412
2360model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.indexer.index_qk_proj.biasesBF16640x40864affine824054404824105604
2361model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.indexer.index_qk_proj.scalesBF16640x40864affine6072744460778644
2362model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.indexer.index_qk_proj.weightU32640x640864affine6077864462417044
2363model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.indexer.k_layernorm.weightBF16128408605876408606132
2364model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.indexer.q_layernorm.weightBF161286072718860727444
2365model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.k_norm.weightBF162566072667660727188
2366model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.k_proj.biasesBF16512x40464affine5998939660030356
2367model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.k_proj.scalesBF16512x40464affine6003035660071316
2368model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.k_proj.weightU32512x320464affine6007131660726676
2369model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.o_proj.biasesBF162560x96464affine26043778042604869324
2370model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.o_proj.scalesBF162560x96464affine5949787659989396
2371model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.o_proj.weightU322560x768464affine537880852545745172
2372model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.q_norm.weightBF162565949736459497876
2373model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.q_proj.biasesBF1612288x40464affine710708180711691220
2374model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.q_proj.scalesBF1612288x40464affine4278568443768724
2375model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.q_proj.weightU3212288x320464affine4376872459497364
2376model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.v_proj.biasesBF16512x40464affine4270376442744724
2377model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.v_proj.scalesBF16512x40464affine4274472442785684
2378model-00016-of-00017.safetensorslanguage_model.model.layers.7.self_attn.v_proj.weightU32512x320464affine364932100365587460
2379model-00016-of-00017.safetensorslanguage_model.model.layers.8.attn_hyper_connection.block_inject_weight.weightBF164x102404262184442703764
2380model-00016-of-00017.safetensorslanguage_model.model.layers.8.attn_hyper_connection.hc_norm.weightBF161024012718783801271898860
2381model-00016-of-00017.safetensorslanguage_model.model.layers.8.attn_hyper_connection.input_mix_weight_down.weightBF16320x102403606824442621844
2382model-00016-of-00017.safetensorslanguage_model.model.layers.8.attn_hyper_connection.input_mix_weight_up.weightBF1610240x3202951464436068244
2383model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.A_logBF164814867571001486757196
2384model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.conv1d.weightBF1610240x4x117060905241706172444
2385model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.dt_biasBF164820754829402075483036
2386model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_a.biasesBF1648x40464affine2951080429514644
2387model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_a.scalesBF1648x40464affine15510782361551082076
2388model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_a.weightU3248x320464affine26036903482603751788
2389model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_b.biasesBF1648x40464affine17325028921732506732
2390model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_b.scalesBF1648x40464affine2944552429449364
2391model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_b.weightU3248x320464affine2944936429510804
2392model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_qkv.biasesBF1610240x40464affine22802304122281049612
2393model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_qkv.scalesBF1610240x40464affine2862632429445524
2394model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_qkv.weightU3210240x320464affine11875467961200653996
2395model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_z.biasesBF166144x40464affine1977896420270484
2396model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_z.scalesBF166144x40464affine2027048420762004
2397model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.in_proj_z.weightU326144x320464affine2076200428626324
2398model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.norm.weightBF16128126526788126527044
2399model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.out_proj.biasesBF162560x96464affine30521010523052592572
2400model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.out_proj.scalesBF162560x96464affine1928744419778964
2401model-00016-of-00017.safetensorslanguage_model.model.layers.8.linear_attn.out_proj.weightU322560x768464affine21242272442132091564
2402model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.gate.biasesBF16512x40864affine17080950041708135964
2403model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.gate.scalesBF16512x40864affine130095012130135972
2404model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.gate.weightU32512x640864affine1797672419287444
2405model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.down_proj.biasesBF162560x10464affine1787432417925524
2406model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.down_proj.scalesBF162560x10464affine1792552417976724
2407model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.down_proj.weightU322560x80464affine37282715963729090796
2408model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.gate_proj.biasesBF16640x40464affine20438703642043921564
2409model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.gate_proj.scalesBF16640x40464affine1700392417055124
2410model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.gate_proj.weightU32640x320464affine1705512417874324
2411model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.up_proj.biasesBF16640x40464affine1690152416952724
2412model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.up_proj.scalesBF16640x40464affine1695272417003924
2413model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert.up_proj.weightU32640x320464affine20347350042035554204
2414model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert_gate.biasesBF161x40464affine1690136416901444
2415model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert_gate.scalesBF161x40464affine1690144416901524
2416model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp.shared_expert_gate.weightU321x320464affine11801035001180104780
2417model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp_hyper_connection.block_inject_weight.weightBF164x102401681944416901364
2418model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp_hyper_connection.hc_norm.weightBF161024023007995802300820060
2419model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240849690916856244516
2420model-00016-of-00017.safetensorslanguage_model.model.layers.8.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x320206499988213053588
2421model-00016-of-00017.safetensorslanguage_model.model.layers.9.attn_hyper_connection.block_inject_weight.weightBF164x102401673752416819444
2422model-00016-of-00017.safetensorslanguage_model.model.layers.9.attn_hyper_connection.hc_norm.weightBF16102401671704416737524
2423model-00016-of-00017.safetensorslanguage_model.model.layers.9.attn_hyper_connection.input_mix_weight_down.weightBF16320x1024021329619642139515564
2424model-00016-of-00017.safetensorslanguage_model.model.layers.9.attn_hyper_connection.input_mix_weight_up.weightBF1610240x3201016344416717044
2425model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.A_logBF164825381638202538163916
2426model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.conv1d.weightBF1610240x4x11008152410163444
2427model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.dt_biasBF164813360756761336075772
2428model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_a.biasesBF1648x40464affine1001240410016244
2429model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_a.scalesBF1648x40464affine1001624410020084
2430model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_a.weightU3248x320464affine1002008410081524
2431model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_b.biasesBF1648x40464affine99432849947124
2432model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_b.scalesBF1648x40464affine99471249950964
2433model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_b.weightU3248x320464affine995096410012404
2434model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_qkv.biasesBF1610240x40464affine91240849943284
2435model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_qkv.scalesBF1610240x40464affine11164646121117283812
2436model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_qkv.weightU3210240x320464affine30033647963016471996
2437model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_z.biasesBF166144x40464affine81410448632564
2438model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_z.scalesBF166144x40464affine86325649124084
2439model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.in_proj_z.weightU326144x320464affine16020842681609948588
2440model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.norm.weightBF1612836106641403610664396
2441model-00016-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.out_proj.weightU322560x768464affine2767248141044
2442model-00016-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.gate_proj.biasesBF16512x640x40464affine509993236536207636
2443model-00016-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.gate_proj.scalesBF16512x640x40464affine879622436905836836
2444model-00016-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.up_proj.biasesBF16512x640x40464affine23679591162394173516
2445model-00016-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.up_proj.scalesBF16512x640x40464affine36983154203724529820
2446model-00016-of-00017.safetensorslanguage_model.model.layers.9.mlp.switch_mlp.up_proj.weightU32512x640x320464affine38368658844256296284
2447model-00017-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.out_proj.biasesBF162560x96464affine1655204217043562
2448model-00017-of-00017.safetensorslanguage_model.model.layers.9.linear_attn.out_proj.scalesBF162560x96464affine1786276218354282
2449model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.gate.biasesBF16512x40864affine77046827745642
2450model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.gate.scalesBF16512x40864affine85648428605802
2451model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.gate.weightU32512x640864affine86058029916522
2452model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.down_proj.biasesBF162560x10464affine209002260202
2453model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.down_proj.scalesBF162560x10464affine260202311402
2454model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.down_proj.weightU322560x80464affine3114021130602
2455model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.gate_proj.biasesBF16640x40464affine106602157802
2456model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.gate_proj.scalesBF16640x40464affine157802209002
2457model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.gate_proj.weightU32640x320464affine1704356217862762
2458model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.up_proj.biasesBF16640x40464affine420255402
2459model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.up_proj.scalesBF16640x40464affine55402106602
2460model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert.up_proj.weightU32640x320464affine77456428564842
2461model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert_gate.biasesBF161x40464affine28422922
2462model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert_gate.scalesBF161x40464affine27622842
2463model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp.shared_expert_gate.weightU321x320464affine29224202
2464model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp_hyper_connection.block_inject_weight.weightBF164x102401647012216552042
2465model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp_hyper_connection.hc_norm.weightBF161024076842027704682
2466model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp_hyper_connection.input_mix_weight_down.weightBF16320x10240991652216470122
2467model-00017-of-00017.safetensorslanguage_model.model.layers.9.mlp_hyper_connection.input_mix_weight_up.weightBF1610240x32011306027684202
2468ngram-table.safetensorsngram.biasesBF16320001536x5432affine2880013864832000154008
2469ngram-table.safetensorsngram.scalesBF16320001536x5432affine2560012328828800138648
2470ngram-table.safetensorsngram.weightU32320001536x20432affine40825600123288
2471mtp.safetensorsmtp.fc_embedding.weightBF162560x2560620917036634024236
2472mtp.safetensorsmtp.fc_hidden.weightBF162560x256011797448121192852012
2473mtp.safetensorsmtp.hyper_connection_mixer.hc_norm.weightBF1610240640577836640598316
2474mtp.safetensorsmtp.hyper_connection_mixer.input_mix_weight_down.weightBF16320x10240746326572752880172
2475mtp.safetensorsmtp.hyper_connection_mixer.input_mix_weight_up.weightBF1610240x320614310956620864556
2476mtp.safetensorsmtp.layers.0.attn_hyper_connection.block_inject_weight.weightBF164x102408098062081062540
2477mtp.safetensorsmtp.layers.0.attn_hyper_connection.hc_norm.weightBF1610240614290476614310956
2478mtp.safetensorsmtp.layers.0.attn_hyper_connection.input_mix_weight_down.weightBF16320x10240753760812760314412
2479mtp.safetensorsmtp.layers.0.attn_hyper_connection.input_mix_weight_up.weightBF1610240x320634024236640577836
2480mtp.safetensorsmtp.layers.0.mlp.gate.biasesBF16512x40864affine194706476194747436
2481mtp.safetensorsmtp.layers.0.mlp.gate.scalesBF16512x40864affine194747436194788396
2482mtp.safetensorsmtp.layers.0.mlp.gate.weightU32512x640864affine193395756194706476
2483mtp.safetensorsmtp.layers.0.mlp.shared_expert.down_proj.biasesBF162560x10464affine140915756140966956
2484mtp.safetensorsmtp.layers.0.mlp.shared_expert.down_proj.scalesBF162560x10464affine614239276614290476
2485mtp.safetensorsmtp.layers.0.mlp.shared_expert.down_proj.weightU322560x80464affine640649516641468716
2486mtp.safetensorsmtp.layers.0.mlp.shared_expert.gate_proj.biasesBF16640x40464affine640598316640649516
2487mtp.safetensorsmtp.layers.0.mlp.shared_expert.gate_proj.scalesBF16640x40464affine1914126019192460
2488mtp.safetensorsmtp.layers.0.mlp.shared_expert.gate_proj.weightU32640x320464affine752941612753760812
2489mtp.safetensorsmtp.layers.0.mlp.shared_expert.up_proj.biasesBF16640x40464affine140045356140096556
2490mtp.safetensorsmtp.layers.0.mlp.shared_expert.up_proj.scalesBF16640x40464affine620864556620915756
2491mtp.safetensorsmtp.layers.0.mlp.shared_expert.up_proj.weightU32640x320464affine140096556140915756
2492mtp.safetensorsmtp.layers.0.mlp.shared_expert_gate.biasesBF161x40464affine140045196140045276
2493mtp.safetensorsmtp.layers.0.mlp.shared_expert_gate.scalesBF161x40464affine140045276140045356
2494mtp.safetensorsmtp.layers.0.mlp.shared_expert_gate.weightU321x320464affine620915756620917036
2495mtp.safetensorsmtp.layers.0.mlp.switch_mlp.down_proj.biasesBF16512x2560x20264affine140966956193395756
2496mtp.safetensorsmtp.layers.0.mlp.switch_mlp.down_proj.scalesBF16512x2560x20264affine641468716693897516
2497mtp.safetensorsmtp.layers.0.mlp.switch_mlp.down_proj.weightU32512x2560x80264affine12531451321672575532
2498mtp.safetensorsmtp.layers.0.mlp.switch_mlp.gate_proj.biasesBF16512x640x80264affine693897772746326572
2499mtp.safetensorsmtp.layers.0.mlp.switch_mlp.gate_proj.scalesBF16512x640x80264affine2027790072706700
2500mtp.safetensorsmtp.layers.0.mlp.switch_mlp.gate_proj.weightU32512x640x320264affine7603144121179744812
The file is too large to be shown. View Raw