Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +200 -0
- model/params/lm_head/kernel/0.0 +3 -0
- model/params/model/layers/0/mlp/experts/down_proj/bias/0.0 +3 -0
- model/params/model/layers/0/mlp/experts/down_proj/kernel/2.0.0 +3 -0
- model/params/model/layers/0/mlp/experts/up_proj/kernel/1.0.0 +3 -0
- model/params/model/layers/0/mlp/router/kernel/0.0 +3 -0
- model/params/model/layers/1/mlp/experts/gate_proj/bias/0.0 +3 -0
- model/params/model/layers/1/mlp/experts/gate_proj/bias/1.0 +3 -0
- model/params/model/layers/1/mlp/experts/gate_proj/bias/2.0 +3 -0
- model/params/model/layers/1/mlp/experts/gate_proj/kernel/1.0.0 +3 -0
- model/params/model/layers/1/mlp/experts/up_proj/bias/0.0 +3 -0
- model/params/model/layers/1/mlp/experts/up_proj/bias/1.0 +3 -0
- model/params/model/layers/1/mlp/experts/up_proj/bias/2.0 +3 -0
- model/params/model/layers/1/mlp/experts/up_proj/bias/3.0 +3 -0
- model/params/model/layers/1/mlp/router/kernel/0.0 +3 -0
- model/params/model/layers/1/self_attn/k_proj/kernel/0.0 +3 -0
- model/params/model/layers/1/self_attn/k_proj/kernel/1.0 +3 -0
- model/params/model/layers/1/self_attn/k_proj/kernel/2.0 +3 -0
- model/params/model/layers/1/self_attn/k_proj/kernel/3.0 +3 -0
- model/params/model/layers/1/self_attn/o_proj/kernel/0.0 +3 -0
- model/params/model/layers/1/self_attn/o_proj/kernel/0.1 +3 -0
- model/params/model/layers/1/self_attn/o_proj/kernel/0.2 +3 -0
- model/params/model/layers/1/self_attn/o_proj/kernel/0.3 +3 -0
- model/params/model/layers/1/self_attn/q_proj/kernel/0.0 +3 -0
- model/params/model/layers/1/self_attn/q_proj/kernel/1.0 +3 -0
- model/params/model/layers/1/self_attn/q_proj/kernel/2.0 +3 -0
- model/params/model/layers/1/self_attn/q_proj/kernel/3.0 +3 -0
- model/params/model/layers/1/self_attn/v_proj/kernel/0.0 +3 -0
- model/params/model/layers/1/self_attn/v_proj/kernel/1.0 +3 -0
- model/params/model/layers/1/self_attn/v_proj/kernel/2.0 +3 -0
- model/params/model/layers/1/self_attn/v_proj/kernel/3.0 +3 -0
- model/params/model/layers/10/mlp/experts/down_proj/bias/0.0 +3 -0
- model/params/model/layers/10/mlp/experts/down_proj/bias/2.0 +3 -0
- model/params/model/layers/10/mlp/experts/down_proj/bias/3.0 +3 -0
- model/params/model/layers/10/mlp/experts/down_proj/kernel/0.0.0 +3 -0
- model/params/model/layers/10/mlp/experts/gate_proj/bias/2.0 +3 -0
- model/params/model/layers/10/mlp/experts/gate_proj/bias/3.0 +3 -0
- model/params/model/layers/10/mlp/experts/gate_proj/kernel/1.0.0 +3 -0
- model/params/model/layers/11/mlp/experts/gate_proj/kernel/3.0.0 +3 -0
- model/params/model/layers/11/mlp/experts/up_proj/kernel/3.0.0 +3 -0
- model/params/model/layers/12/mlp/experts/down_proj/kernel/2.0.0 +3 -0
- model/params/model/layers/12/mlp/experts/gate_proj/kernel/1.0.0 +3 -0
- model/params/model/layers/13/mlp/experts/up_proj/kernel/0.0.0 +3 -0
- model/params/model/layers/13/mlp/experts/up_proj/kernel/3.0.0 +3 -0
- model/params/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0 +3 -0
- model/params/model/layers/15/mlp/experts/up_proj/kernel/1.0.0 +3 -0
- model/params/model/layers/16/mlp/experts/down_proj/bias/1.0 +3 -0
- model/params/model/layers/16/mlp/experts/down_proj/bias/2.0 +3 -0
- model/params/model/layers/16/mlp/experts/down_proj/bias/3.0 +3 -0
- model/params/model/layers/16/mlp/experts/gate_proj/bias/0.0 +3 -0
.gitattributes
CHANGED
|
@@ -995,3 +995,203 @@ model/params/model/layers/32/mlp/experts/down_proj/bias/1.0 filter=lfs diff=lfs
|
|
| 995 |
model/params/model/layers/32/mlp/experts/gate_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 996 |
model/params/model/layers/32/mlp/experts/down_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 997 |
model/params/model/layers/32/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 995 |
model/params/model/layers/32/mlp/experts/gate_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 996 |
model/params/model/layers/32/mlp/experts/down_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 997 |
model/params/model/layers/32/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 998 |
+
model/params/model/layers/31/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 999 |
+
model/params/model/layers/31/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1000 |
+
model/params/model/layers/31/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1001 |
+
model/params/model/layers/31/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1002 |
+
model/params/model/layers/31/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1003 |
+
model/params/model/layers/31/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1004 |
+
model/params/model/layers/31/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1005 |
+
model/params/model/layers/31/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1006 |
+
model/params/model/layers/31/mlp/experts/up_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1007 |
+
model/params/model/layers/31/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1008 |
+
model/params/model/layers/31/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1009 |
+
model/params/model/layers/0/mlp/experts/down_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1010 |
+
model/params/model/layers/15/mlp/experts/up_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1011 |
+
model/params/model/layers/11/mlp/experts/gate_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1012 |
+
model/params/model/layers/0/mlp/experts/up_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1013 |
+
model/params/model/layers/17/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1014 |
+
model/params/model/layers/17/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1015 |
+
model/params/model/layers/26/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1016 |
+
model/params/model/layers/17/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1017 |
+
model/params/model/layers/26/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1018 |
+
model/params/model/layers/17/mlp/experts/gate_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1019 |
+
model/params/model/layers/17/mlp/experts/up_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1020 |
+
model/params/model/layers/17/mlp/experts/gate_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1021 |
+
model/params/model/layers/17/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1022 |
+
model/params/model/layers/26/mlp/experts/down_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1023 |
+
model/params/model/layers/26/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1024 |
+
model/params/model/layers/17/mlp/experts/down_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1025 |
+
model/params/model/layers/17/mlp/experts/gate_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1026 |
+
model/params/model/layers/17/mlp/experts/down_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1027 |
+
model/params/model/layers/17/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1028 |
+
model/params/model/layers/25/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1029 |
+
model/params/model/layers/17/mlp/experts/down_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1030 |
+
model/params/model/layers/16/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1031 |
+
model/params/model/layers/17/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1032 |
+
model/params/model/layers/25/mlp/experts/up_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1033 |
+
model/params/model/layers/25/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1034 |
+
model/params/model/layers/17/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1035 |
+
model/params/model/layers/16/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1036 |
+
model/params/model/layers/25/mlp/experts/up_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1037 |
+
model/params/model/layers/25/mlp/experts/gate_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1038 |
+
model/params/model/layers/17/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1039 |
+
model/params/model/layers/16/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1040 |
+
model/params/model/layers/17/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1041 |
+
model/params/model/layers/25/mlp/experts/down_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1042 |
+
model/params/model/layers/25/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1043 |
+
model/params/model/layers/16/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1044 |
+
model/params/model/layers/25/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1045 |
+
model/params/model/layers/25/mlp/experts/down_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1046 |
+
model/params/model/layers/16/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1047 |
+
model/params/model/layers/16/mlp/experts/up_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1048 |
+
model/params/model/layers/16/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1049 |
+
model/params/model/layers/16/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1050 |
+
model/params/model/layers/25/mlp/experts/gate_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1051 |
+
model/params/model/layers/16/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1052 |
+
model/params/model/layers/25/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1053 |
+
model/params/model/layers/25/mlp/experts/down_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1054 |
+
model/params/model/layers/16/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1055 |
+
model/params/model/layers/16/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1056 |
+
model/params/model/layers/16/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1057 |
+
model/params/model/layers/16/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1058 |
+
model/params/model/layers/16/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1059 |
+
model/params/model/layers/16/mlp/experts/gate_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1060 |
+
model/params/model/layers/16/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1061 |
+
model/params/model/layers/16/mlp/experts/up_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1062 |
+
model/params/model/layers/16/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1063 |
+
model/params/model/layers/16/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1064 |
+
model/params/model/layers/16/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1065 |
+
model/params/model/layers/16/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1066 |
+
model/params/model/layers/16/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1067 |
+
model/params/model/layers/16/mlp/experts/up_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1068 |
+
model/params/model/layers/16/mlp/experts/down_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1069 |
+
model/params/model/layers/16/mlp/experts/gate_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1070 |
+
model/params/model/layers/16/mlp/experts/gate_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1071 |
+
model/params/model/layers/24/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1072 |
+
model/params/model/layers/16/mlp/experts/down_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1073 |
+
model/params/model/layers/16/mlp/experts/down_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1074 |
+
model/params/model/layers/24/mlp/experts/up_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1075 |
+
model/params/model/layers/24/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1076 |
+
model/params/model/layers/11/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1077 |
+
model/params/model/layers/0/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1078 |
+
model/params/lm_head/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1079 |
+
model/params/model/layers/12/mlp/experts/down_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1080 |
+
model/params/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1081 |
+
model/params/model/layers/13/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1082 |
+
model/params/model/layers/10/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1083 |
+
model/params/model/layers/13/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1084 |
+
model/params/model/layers/1/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1085 |
+
model/params/model/layers/0/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1086 |
+
model/params/model/layers/10/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1087 |
+
model/params/model/layers/12/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1088 |
+
model/params/model/layers/35/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1089 |
+
model/params/model/layers/26/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1090 |
+
model/params/model/layers/26/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1091 |
+
model/params/model/layers/26/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1092 |
+
model/params/model/layers/26/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1093 |
+
model/params/model/layers/35/mlp/experts/gate_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1094 |
+
model/params/model/layers/34/mlp/experts/down_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1095 |
+
model/params/model/layers/26/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1096 |
+
model/params/model/layers/26/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1097 |
+
model/params/model/layers/34/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1098 |
+
model/params/model/layers/34/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1099 |
+
model/params/model/layers/26/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1100 |
+
model/params/model/layers/26/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1101 |
+
model/params/model/layers/34/mlp/experts/up_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1102 |
+
model/params/model/layers/26/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1103 |
+
model/params/model/layers/26/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1104 |
+
model/params/model/layers/34/mlp/experts/up_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1105 |
+
model/params/model/layers/26/mlp/experts/gate_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1106 |
+
model/params/model/layers/26/mlp/experts/up_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1107 |
+
model/params/model/layers/26/mlp/experts/gate_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1108 |
+
model/params/model/layers/26/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1109 |
+
model/params/model/layers/35/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1110 |
+
model/params/model/layers/26/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1111 |
+
model/params/model/layers/26/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1112 |
+
model/params/model/layers/26/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1113 |
+
model/params/model/layers/34/mlp/experts/down_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1114 |
+
model/params/model/layers/34/mlp/experts/gate_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1115 |
+
model/params/model/layers/34/mlp/experts/down_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1116 |
+
model/params/model/layers/26/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1117 |
+
model/params/model/layers/26/mlp/experts/up_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1118 |
+
model/params/model/layers/35/mlp/experts/gate_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1119 |
+
model/params/model/layers/26/mlp/experts/up_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1120 |
+
model/params/model/layers/26/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1121 |
+
model/params/model/layers/26/mlp/experts/gate_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1122 |
+
model/params/model/layers/26/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1123 |
+
model/params/model/layers/34/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1124 |
+
model/params/model/layers/26/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1125 |
+
model/params/model/layers/34/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1126 |
+
model/params/model/layers/26/mlp/experts/down_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1127 |
+
model/params/model/layers/34/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1128 |
+
model/params/model/layers/33/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1129 |
+
model/params/model/layers/26/mlp/experts/down_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1130 |
+
model/params/model/layers/25/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1131 |
+
model/params/model/layers/34/mlp/experts/gate_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1132 |
+
model/params/model/layers/33/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1133 |
+
model/params/model/layers/26/mlp/experts/down_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1134 |
+
model/params/model/layers/25/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1135 |
+
model/params/model/layers/33/mlp/experts/down_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1136 |
+
model/params/model/layers/25/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1137 |
+
model/params/model/layers/25/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1138 |
+
model/params/model/layers/25/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1139 |
+
model/params/model/layers/25/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1140 |
+
model/params/model/layers/33/mlp/experts/up_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1141 |
+
model/params/model/layers/25/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1142 |
+
model/params/model/layers/25/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1143 |
+
model/params/model/layers/25/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1144 |
+
model/params/model/layers/33/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1145 |
+
model/params/model/layers/25/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1146 |
+
model/params/model/layers/33/mlp/experts/up_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1147 |
+
model/params/model/layers/33/mlp/experts/down_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1148 |
+
model/params/model/layers/33/mlp/experts/down_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1149 |
+
model/params/model/layers/25/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1150 |
+
model/params/model/layers/25/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1151 |
+
model/params/model/layers/25/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1152 |
+
model/params/model/layers/25/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1153 |
+
model/params/model/layers/25/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1154 |
+
model/params/model/layers/25/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1155 |
+
model/params/model/layers/33/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1156 |
+
model/params/model/layers/10/mlp/experts/gate_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1157 |
+
model/params/model/layers/10/mlp/experts/down_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1158 |
+
model/params/model/layers/19/mlp/experts/gate_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1159 |
+
model/params/model/layers/19/mlp/experts/gate_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1160 |
+
model/params/model/layers/1/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1161 |
+
model/params/model/layers/10/mlp/experts/down_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1162 |
+
model/params/model/layers/19/mlp/experts/down_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1163 |
+
model/params/model/layers/10/mlp/experts/down_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1164 |
+
model/params/model/layers/1/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1165 |
+
model/params/model/layers/10/mlp/experts/gate_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1166 |
+
model/params/model/layers/1/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1167 |
+
model/params/model/layers/19/mlp/experts/down_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1168 |
+
model/params/model/layers/1/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1169 |
+
model/params/model/layers/19/mlp/experts/down_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1170 |
+
model/params/model/layers/19/mlp/experts/down_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1171 |
+
model/params/model/layers/19/mlp/experts/gate_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1172 |
+
model/params/model/layers/1/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1173 |
+
model/params/model/layers/1/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1174 |
+
model/params/model/layers/19/mlp/experts/gate_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1175 |
+
model/params/model/layers/1/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1176 |
+
model/params/model/layers/1/mlp/router/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1177 |
+
model/params/model/layers/1/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1178 |
+
model/params/model/layers/1/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1179 |
+
model/params/model/layers/18/mlp/experts/up_proj/kernel/2.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1180 |
+
model/params/model/layers/1/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1181 |
+
model/params/model/layers/1/mlp/experts/up_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1182 |
+
model/params/model/layers/1/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1183 |
+
model/params/model/layers/1/mlp/experts/gate_proj/bias/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1184 |
+
model/params/model/layers/18/mlp/experts/up_proj/kernel/1.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1185 |
+
model/params/model/layers/1/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1186 |
+
model/params/model/layers/1/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1187 |
+
model/params/model/layers/1/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1188 |
+
model/params/model/layers/1/mlp/experts/gate_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1189 |
+
model/params/model/layers/1/mlp/experts/up_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1190 |
+
model/params/model/layers/1/mlp/experts/up_proj/bias/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1191 |
+
model/params/model/layers/18/mlp/experts/up_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1192 |
+
model/params/model/layers/1/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1193 |
+
model/params/model/layers/18/mlp/experts/gate_proj/kernel/3.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1194 |
+
model/params/model/layers/1/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1195 |
+
model/params/model/layers/18/mlp/experts/up_proj/kernel/0.0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1196 |
+
model/params/model/layers/1/mlp/experts/up_proj/bias/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1197 |
+
model/params/model/layers/1/mlp/experts/gate_proj/bias/2.0 filter=lfs diff=lfs merge=lfs -text
|
model/params/lm_head/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87b30c7ae21f6bdcbac761cfed35128c394de8dc8e009143a37f800364430801
|
| 3 |
+
size 226982539
|
model/params/model/layers/0/mlp/experts/down_proj/bias/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10930d7001e6d9c9d3c27ef08cb81c72d9b575801bf3456d62f02926580d790f
|
| 3 |
+
size 146058
|
model/params/model/layers/0/mlp/experts/down_proj/kernel/2.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6209a14340cc031d900abfbd1517b71d9d9898a665c5e2ad6a1b0ccf7d1c84f3
|
| 3 |
+
size 196646312
|
model/params/model/layers/0/mlp/experts/up_proj/kernel/1.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6dd21b2ad262adc6bc784c613a062f8c048cb8e3dc6f9400da7402b12e4c4457
|
| 3 |
+
size 173159184
|
model/params/model/layers/0/mlp/router/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dda651545553bbb9a37d7da0501370c6b6a4936685cac778952e83e1db62afdb
|
| 3 |
+
size 586702
|
model/params/model/layers/1/mlp/experts/gate_proj/bias/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ae3c0c0056d3ac099e2a8562173b8d2c61d6e37b9082497ab2944159202ba44a
|
| 3 |
+
size 128478
|
model/params/model/layers/1/mlp/experts/gate_proj/bias/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:72a406eee2c123aa1d6da159e595c22b9e282873b4eb7e415c79e241df1fa69a
|
| 3 |
+
size 128898
|
model/params/model/layers/1/mlp/experts/gate_proj/bias/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:451cb6381ba06c88b4f8b5c00dc41fa18b57ebf2a73fb5e1db0644edc3a038ff
|
| 3 |
+
size 129490
|
model/params/model/layers/1/mlp/experts/gate_proj/kernel/1.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e654a8910e31acec6941302d3cd7bf86f0c48509f0d702b5ab4ccb5828b25d1d
|
| 3 |
+
size 179358292
|
model/params/model/layers/1/mlp/experts/up_proj/bias/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3ee287895518c5d0b7a1704a3f5c34ddb64068f5c5f9df27c00a229390d3ba74
|
| 3 |
+
size 117259
|
model/params/model/layers/1/mlp/experts/up_proj/bias/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a56f94e33b605bfcf2a98d2301403783e70a3ed43ab1024142a95348a6c6c207
|
| 3 |
+
size 119436
|
model/params/model/layers/1/mlp/experts/up_proj/bias/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a8354119e3867ca524a33e287a209769e55f21c63e00c592992d66d00e5942eb
|
| 3 |
+
size 118992
|
model/params/model/layers/1/mlp/experts/up_proj/bias/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:820a4c772e2255b224e6c4c19c5a62213ad667f7ac61a440aa43aeeb4737655f
|
| 3 |
+
size 119570
|
model/params/model/layers/1/mlp/router/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74f73537daed1e7062d4414acf3d9ec0371211d9985c1b541c5f5bf9855bfd9e
|
| 3 |
+
size 584058
|
model/params/model/layers/1/self_attn/k_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be43130c4d3a22dc91b97d7f9e176c08dc9f52fd090862846b5b0f37f27eba63
|
| 3 |
+
size 585973
|
model/params/model/layers/1/self_attn/k_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:545957adaced422de0c0e3ab7db8f6f27d2521a710be5db95fabf0a432a1dfc9
|
| 3 |
+
size 585991
|
model/params/model/layers/1/self_attn/k_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5f39da8d3b70ea76a496d17e0812c97b4409a88a81b729456b9dacf7d1c9a739
|
| 3 |
+
size 585929
|
model/params/model/layers/1/self_attn/k_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f4e266803d297922faa0619f79af42d9a9626bedd5bbea587a6d18ebeea762b3
|
| 3 |
+
size 585496
|
model/params/model/layers/1/self_attn/o_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:36a7a2cbfed328c98e913ef47379b733a88e1245ce249a0618f1d1d800e5df14
|
| 3 |
+
size 4661655
|
model/params/model/layers/1/self_attn/o_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:286ab24c570b418b1c6e2ffdabd361de24719888f02b070e2fedde94ecbe09ca
|
| 3 |
+
size 4662898
|
model/params/model/layers/1/self_attn/o_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:17a76eb7c1a78e571326109db8e1aec7068be3ec13b3d1d9b127fde40e36e90d
|
| 3 |
+
size 4649133
|
model/params/model/layers/1/self_attn/o_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:224824624d95c030e9a789cbc124e16dc88f3bd833ca5d5011dcb2a7754d6d74
|
| 3 |
+
size 4660878
|
model/params/model/layers/1/self_attn/q_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ccb7f3ddd1d846b1889e2d495644507b389d14c74b8ce38d7972237944ff589
|
| 3 |
+
size 4697111
|
model/params/model/layers/1/self_attn/q_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2773d9e75d6f5a060b91ec243cc770707175c6c68b1680f15a31e1fe21292e9f
|
| 3 |
+
size 4698427
|
model/params/model/layers/1/self_attn/q_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a393482267e3e450a8fdc0936761d76c98a90e2a28c1366d35c68985053979e
|
| 3 |
+
size 4695166
|
model/params/model/layers/1/self_attn/q_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:27b0dbe1a703cc5f38441ffe7f3601f170cad105bea2fa2c942ff2794118360e
|
| 3 |
+
size 4695175
|
model/params/model/layers/1/self_attn/v_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2125ebaf81666e39c18072db45f6f251d7b57233f07d35bb15223b861b83a351
|
| 3 |
+
size 580578
|
model/params/model/layers/1/self_attn/v_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a614e55a916623b9b0ac5050f7b74d38e23a58cb00bb4ac921e0d764ecc212e6
|
| 3 |
+
size 580943
|
model/params/model/layers/1/self_attn/v_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e425a2deea5922300474198bc3dd678699124e06d88e52646a65bc629d2ed0ed
|
| 3 |
+
size 580427
|
model/params/model/layers/1/self_attn/v_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2c90bdfb9b3fba7cf82473c1dc3e72808e2e4c32f0433d1b68816f4a92a5b58
|
| 3 |
+
size 580428
|
model/params/model/layers/10/mlp/experts/down_proj/bias/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a042b6d249d97e08f5590c4584a2aad0c667dfb1fb1d73021fa753529850e668
|
| 3 |
+
size 144889
|
model/params/model/layers/10/mlp/experts/down_proj/bias/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2db0c34f5284a23a6ead9984ca70555efda7eac0864c4d0592911714cd9a240e
|
| 3 |
+
size 144922
|
model/params/model/layers/10/mlp/experts/down_proj/bias/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dcf42b4cf5a12f77b4f26ece8fbc8554a4ff6cd4c3a03f22c9b079e5576547a5
|
| 3 |
+
size 144877
|
model/params/model/layers/10/mlp/experts/down_proj/kernel/0.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cf3de9a3297a628c4038dbae6f77f80daef27d09444d0e58dcb03760f81983d4
|
| 3 |
+
size 182671021
|
model/params/model/layers/10/mlp/experts/gate_proj/bias/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:640eebc09888a938397a8f2864dac40ccf72e422be910039785bf4ebc7b60152
|
| 3 |
+
size 138368
|
model/params/model/layers/10/mlp/experts/gate_proj/bias/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f15a94502b3e78fa3083bae802615f068ce145511e9f1cc5450d7e0090c60ef7
|
| 3 |
+
size 140232
|
model/params/model/layers/10/mlp/experts/gate_proj/kernel/1.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:83d554ae69b5a43e164f4f0be788e172b5f0b2844c737452b78c636554292101
|
| 3 |
+
size 186920244
|
model/params/model/layers/11/mlp/experts/gate_proj/kernel/3.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5699631aef43ab0079cfabd181468c0d3158f4ca223354fc0d6319e23b9a0ac5
|
| 3 |
+
size 186630151
|
model/params/model/layers/11/mlp/experts/up_proj/kernel/3.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:009764535179a1df0e4cea28ba781b322634484ae1c556401752fb8890617b83
|
| 3 |
+
size 179128368
|
model/params/model/layers/12/mlp/experts/down_proj/kernel/2.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac7c9e0f70b4238169bfbee61097ea1956f006701fd47d156a5e11c847aa78e7
|
| 3 |
+
size 182267164
|
model/params/model/layers/12/mlp/experts/gate_proj/kernel/1.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f69988b09e07e9182be5bd56ad16d74901e830447be1bbef3d4b7b71dd4ea4ee
|
| 3 |
+
size 186711956
|
model/params/model/layers/13/mlp/experts/up_proj/kernel/0.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d147cbda7d11fe4a491c02fa64606887a3402137569eed58722067c21d1744d6
|
| 3 |
+
size 179781782
|
model/params/model/layers/13/mlp/experts/up_proj/kernel/3.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b49f01a7798ac29a61621aa2556fcc63cb84608dad4e3d72b2e06e9656f0d1e
|
| 3 |
+
size 179849957
|
model/params/model/layers/15/mlp/experts/gate_proj/kernel/0.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:979c273e99ddde41c0d612ca3cb0e6b1e5b6f82273d7d6415874a518327279ec
|
| 3 |
+
size 185492290
|
model/params/model/layers/15/mlp/experts/up_proj/kernel/1.0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f177c3478cbf0eff35567f576ce398e6c647b09bede4b2c41e21b983e7f7697
|
| 3 |
+
size 180489152
|
model/params/model/layers/16/mlp/experts/down_proj/bias/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6988367a74340d2951a004b84e2f4f4d605381b41ddc3ac2eebecfcb83a46ab
|
| 3 |
+
size 144415
|
model/params/model/layers/16/mlp/experts/down_proj/bias/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95d9fc89e068bc129301eddc2f0abbb081abe9cb34af1c51bdc9525568042634
|
| 3 |
+
size 144382
|
model/params/model/layers/16/mlp/experts/down_proj/bias/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:105336f630519b048210df7d554601fdab70dfe95d1e3ab6d85a545aa9da5cb5
|
| 3 |
+
size 144369
|
model/params/model/layers/16/mlp/experts/gate_proj/bias/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ef74a35b07ed3d98c477efa9fb89b657a187366425b65ac7c09de86cc2c75eaa
|
| 3 |
+
size 144181
|