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 +600 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 +3 -0
- model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 +3 -0
- model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/1/mlp/down_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/1/mlp/up_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
.gitattributes
CHANGED
|
@@ -136,3 +136,603 @@ model/model/visual/blocks/23/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge
|
|
| 136 |
model/model/visual/blocks/3/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 137 |
model/model/visual/blocks/23/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 138 |
model/model/visual/blocks/23/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 136 |
model/model/visual/blocks/3/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 137 |
model/model/visual/blocks/23/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 138 |
model/model/visual/blocks/23/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
model/model/visual/blocks/3/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
model/model/visual/blocks/3/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
model/model/visual/blocks/23/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
model/model/visual/blocks/3/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
model/model/visual/blocks/4/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
model/model/visual/blocks/3/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
model/model/visual/blocks/4/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 164 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 165 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 166 |
+
model/model/visual/blocks/4/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 167 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 168 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 169 |
+
model/model/visual/blocks/4/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 170 |
+
model/model/visual/blocks/5/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 171 |
+
model/model/language_model/layers/17/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 172 |
+
model/model/language_model/layers/17/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 173 |
+
model/model/language_model/layers/16/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 174 |
+
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 175 |
+
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 176 |
+
model/model/language_model/layers/17/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 177 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 178 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 179 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 180 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 181 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 182 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 183 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 184 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 185 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 186 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 187 |
+
model/model/language_model/layers/17/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 188 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 189 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 190 |
+
model/model/language_model/layers/18/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 191 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 192 |
+
model/model/language_model/layers/17/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 193 |
+
model/model/language_model/layers/17/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 194 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 195 |
+
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 196 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 197 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 198 |
+
model/model/language_model/layers/18/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 199 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 200 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 201 |
+
model/model/language_model/layers/19/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 202 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 203 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 204 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 205 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 206 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 207 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 208 |
+
model/model/language_model/layers/18/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 209 |
+
model/model/language_model/layers/19/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 210 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 211 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 212 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 213 |
+
model/model/language_model/layers/19/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 214 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 215 |
+
model/model/language_model/layers/17/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 216 |
+
model/model/language_model/layers/19/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 217 |
+
model/model/language_model/layers/19/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 218 |
+
model/model/language_model/layers/18/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 219 |
+
model/model/language_model/layers/19/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 220 |
+
model/model/language_model/layers/19/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 221 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 222 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 223 |
+
model/model/language_model/layers/19/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 224 |
+
model/model/language_model/layers/2/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 225 |
+
model/model/language_model/layers/18/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 226 |
+
model/model/language_model/layers/19/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 227 |
+
model/model/language_model/layers/18/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 228 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 229 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 230 |
+
model/model/visual/blocks/6/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 231 |
+
model/model/visual/blocks/5/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 232 |
+
model/model/visual/blocks/6/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 233 |
+
model/model/visual/blocks/6/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 234 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 235 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 236 |
+
model/model/visual/blocks/5/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 237 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 238 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 239 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 240 |
+
model/model/visual/blocks/6/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 241 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 242 |
+
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 243 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 244 |
+
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 245 |
+
model/model/visual/blocks/5/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 246 |
+
model/model/visual/blocks/6/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 247 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 248 |
+
model/model/visual/blocks/6/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 249 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 250 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 251 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 252 |
+
model/model/visual/blocks/6/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 253 |
+
model/model/visual/blocks/6/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 254 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 255 |
+
model/model/visual/blocks/7/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 256 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 257 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 258 |
+
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 259 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 260 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 261 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 262 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 263 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 264 |
+
model/model/visual/blocks/6/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 265 |
+
model/model/visual/blocks/6/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 266 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 267 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 268 |
+
model/model/visual/blocks/6/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 269 |
+
model/model/visual/blocks/7/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 270 |
+
model/model/visual/blocks/8/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 271 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 272 |
+
model/model/visual/blocks/8/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 273 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 274 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 275 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 276 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 277 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 278 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 279 |
+
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 280 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 281 |
+
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 282 |
+
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 283 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 284 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 285 |
+
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 286 |
+
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 287 |
+
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 288 |
+
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 289 |
+
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 290 |
+
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 291 |
+
model/model/language_model/layers/4/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 292 |
+
model/model/language_model/layers/4/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 293 |
+
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 294 |
+
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 295 |
+
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 296 |
+
model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 297 |
+
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 298 |
+
model/model/language_model/layers/5/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 299 |
+
model/model/language_model/layers/4/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 300 |
+
model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 301 |
+
model/model/language_model/layers/4/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 302 |
+
model/model/language_model/layers/4/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 303 |
+
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 304 |
+
model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 305 |
+
model/model/language_model/layers/4/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 306 |
+
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 307 |
+
model/model/language_model/layers/4/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 308 |
+
model/model/language_model/layers/4/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 309 |
+
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 310 |
+
model/model/language_model/layers/5/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 311 |
+
model/model/language_model/layers/4/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 312 |
+
model/model/language_model/layers/4/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 313 |
+
model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 314 |
+
model/model/language_model/layers/5/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 315 |
+
model/model/language_model/layers/12/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 316 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 317 |
+
model/model/language_model/layers/13/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 318 |
+
model/model/language_model/layers/13/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 319 |
+
model/model/language_model/layers/13/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 320 |
+
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 321 |
+
model/model/language_model/layers/13/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 322 |
+
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 323 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 324 |
+
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 325 |
+
model/model/language_model/layers/13/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 326 |
+
model/model/language_model/layers/13/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 327 |
+
model/model/language_model/layers/13/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 328 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 329 |
+
model/model/language_model/layers/13/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 330 |
+
model/model/language_model/layers/13/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 331 |
+
model/model/language_model/layers/13/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 332 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 333 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 334 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 335 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 336 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 337 |
+
model/model/language_model/layers/14/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 338 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 339 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 340 |
+
model/model/language_model/layers/14/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 341 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 342 |
+
model/model/language_model/layers/14/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 343 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 344 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 345 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 346 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 347 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 348 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 349 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 350 |
+
model/model/language_model/layers/14/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 351 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 352 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 353 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 354 |
+
model/model/language_model/layers/15/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 355 |
+
model/model/language_model/layers/15/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 356 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 357 |
+
model/model/language_model/layers/15/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 358 |
+
model/model/language_model/layers/15/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 359 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 360 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 361 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 362 |
+
model/model/language_model/layers/15/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 363 |
+
model/model/language_model/layers/15/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 364 |
+
model/model/language_model/layers/13/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 365 |
+
model/model/language_model/layers/15/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 366 |
+
model/model/language_model/layers/14/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 367 |
+
model/model/language_model/layers/15/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 368 |
+
model/model/language_model/layers/15/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 369 |
+
model/model/language_model/layers/14/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 370 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 371 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 372 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 373 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 374 |
+
tokenizer.json filter=lfs diff=lfs merge=lfs -text
|
| 375 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 376 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 377 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 378 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 379 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 380 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 381 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 382 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 383 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 384 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 385 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 386 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 387 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 388 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 389 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 390 |
+
model/model/language_model/layers/1/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 391 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 392 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 393 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 394 |
+
model/model/language_model/layers/10/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 395 |
+
model/model/language_model/layers/10/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 396 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 397 |
+
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 398 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 399 |
+
model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 400 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 401 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 402 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 403 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 404 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 405 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 406 |
+
model/model/language_model/layers/10/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 407 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 408 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 409 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 410 |
+
model/model/language_model/layers/10/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 411 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 412 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 413 |
+
model/model/language_model/layers/11/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 414 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 415 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 416 |
+
model/model/language_model/layers/10/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 417 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 418 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 419 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 420 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 421 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 422 |
+
model/model/language_model/layers/20/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 423 |
+
model/model/language_model/layers/2/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 424 |
+
model/model/language_model/layers/2/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 425 |
+
model/model/language_model/layers/20/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 426 |
+
model/model/language_model/layers/20/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 427 |
+
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 428 |
+
model/model/language_model/layers/2/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 429 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 430 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 431 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 432 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 433 |
+
model/model/language_model/layers/20/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 434 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 435 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 436 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 437 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 438 |
+
model/model/language_model/layers/21/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 439 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 440 |
+
model/model/language_model/layers/21/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 441 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 442 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 443 |
+
model/model/language_model/layers/20/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 444 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 445 |
+
model/model/language_model/layers/20/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 446 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 447 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 448 |
+
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 449 |
+
model/model/language_model/layers/20/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 450 |
+
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 451 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 452 |
+
model/model/language_model/layers/22/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 453 |
+
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 454 |
+
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 455 |
+
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 456 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 457 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 458 |
+
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 459 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 460 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 461 |
+
model/model/language_model/layers/21/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 462 |
+
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 463 |
+
model/model/language_model/layers/22/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 464 |
+
model/model/language_model/layers/21/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 465 |
+
model/model/language_model/layers/22/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 466 |
+
model/model/language_model/layers/22/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 467 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 468 |
+
model/model/visual/blocks/10/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 469 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 470 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 471 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 472 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 473 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 474 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 475 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 476 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 477 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 478 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 479 |
+
model/model/visual/blocks/11/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 480 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 481 |
+
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 482 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 483 |
+
model/model/visual/blocks/11/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 484 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 485 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 486 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 487 |
+
model/model/visual/blocks/11/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 488 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 489 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 490 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 491 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 492 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 493 |
+
model/model/visual/blocks/12/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 494 |
+
model/model/visual/blocks/11/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 495 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 496 |
+
model/model/visual/blocks/12/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 497 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 498 |
+
model/model/visual/blocks/12/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 499 |
+
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 500 |
+
model/model/visual/blocks/13/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 501 |
+
model/model/visual/blocks/13/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 502 |
+
model/model/visual/blocks/13/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 503 |
+
model/model/visual/blocks/13/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 504 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 505 |
+
model/model/visual/blocks/12/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 506 |
+
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 507 |
+
model/model/visual/blocks/14/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 508 |
+
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 509 |
+
model/model/visual/blocks/13/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 510 |
+
model/model/visual/blocks/13/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 511 |
+
model/model/visual/blocks/14/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 512 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 513 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 514 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 515 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 516 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 517 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 518 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 519 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 520 |
+
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 521 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 522 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 523 |
+
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 524 |
+
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 525 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 526 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 527 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 528 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 529 |
+
model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 530 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 531 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 532 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 533 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 534 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 535 |
+
model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 536 |
+
model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 537 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 538 |
+
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 539 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 540 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 541 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 542 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 543 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 544 |
+
model/model/language_model/layers/1/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 545 |
+
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 546 |
+
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 547 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 548 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 549 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 550 |
+
model/model/language_model/layers/11/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 551 |
+
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 552 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 553 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 554 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 555 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 556 |
+
model/model/language_model/layers/11/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 557 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 558 |
+
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 559 |
+
model/model/language_model/layers/11/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 560 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 561 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 562 |
+
model/model/language_model/layers/11/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 563 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 564 |
+
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 565 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 566 |
+
model/model/language_model/layers/11/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 567 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 568 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 569 |
+
model/model/language_model/layers/12/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 570 |
+
model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 571 |
+
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 572 |
+
model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 573 |
+
model/model/language_model/layers/12/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 574 |
+
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 575 |
+
model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 576 |
+
model/model/language_model/layers/12/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 577 |
+
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 578 |
+
model/model/language_model/layers/12/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 579 |
+
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 580 |
+
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 581 |
+
model/model/language_model/layers/12/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 582 |
+
model/model/language_model/layers/12/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 583 |
+
model/model/language_model/layers/12/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 584 |
+
model/model/language_model/layers/12/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 585 |
+
model/model/language_model/layers/13/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 586 |
+
model/model/language_model/layers/12/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 587 |
+
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 588 |
+
model/model/language_model/layers/12/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 589 |
+
model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 590 |
+
model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 591 |
+
model/model/language_model/layers/12/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 592 |
+
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 593 |
+
model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 594 |
+
model/model/language_model/layers/7/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 595 |
+
model/model/language_model/layers/6/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 596 |
+
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 597 |
+
model/model/language_model/layers/7/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 598 |
+
model/model/language_model/layers/7/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 599 |
+
model/model/language_model/layers/7/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 600 |
+
model/model/language_model/layers/8/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 601 |
+
model/model/language_model/layers/6/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 602 |
+
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 603 |
+
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 604 |
+
model/model/language_model/layers/7/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 605 |
+
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 606 |
+
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 607 |
+
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 608 |
+
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 609 |
+
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 610 |
+
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 611 |
+
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 612 |
+
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 613 |
+
model/model/language_model/layers/7/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 614 |
+
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 615 |
+
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 616 |
+
model/model/language_model/layers/8/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 617 |
+
model/model/language_model/layers/8/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 618 |
+
model/model/language_model/layers/8/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 619 |
+
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 620 |
+
model/model/language_model/layers/8/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 621 |
+
model/model/language_model/layers/8/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 622 |
+
model/model/language_model/layers/8/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 623 |
+
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 624 |
+
model/model/language_model/layers/8/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 625 |
+
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 626 |
+
model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 627 |
+
model/model/language_model/layers/8/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 628 |
+
model/model/visual/blocks/0/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 629 |
+
model/model/language_model/layers/8/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 630 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 631 |
+
model/model/visual/blocks/0/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 632 |
+
model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 633 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 634 |
+
model/model/language_model/layers/8/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 635 |
+
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 636 |
+
model/model/language_model/layers/9/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 637 |
+
model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 638 |
+
model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 639 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 640 |
+
model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 641 |
+
model/model/visual/blocks/0/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 642 |
+
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 643 |
+
model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 644 |
+
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 645 |
+
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 646 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 647 |
+
model/model/language_model/layers/22/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 648 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 649 |
+
model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 650 |
+
model/model/language_model/layers/21/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 651 |
+
model/model/language_model/layers/22/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 652 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 653 |
+
model/model/language_model/layers/22/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 654 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 655 |
+
model/model/language_model/layers/21/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 656 |
+
model/model/language_model/layers/22/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 657 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 658 |
+
model/model/language_model/layers/22/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 659 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 660 |
+
model/model/language_model/layers/22/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 661 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 662 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 663 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 664 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 665 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 666 |
+
model/model/language_model/layers/23/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 667 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 668 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 669 |
+
model/model/language_model/layers/22/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 670 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 671 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 672 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 673 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 674 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 675 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 676 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 677 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 678 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 679 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 680 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 681 |
+
model/model/language_model/layers/23/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 682 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 683 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 684 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 685 |
+
model/model/language_model/layers/22/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 686 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 687 |
+
model/model/language_model/layers/23/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 688 |
+
model/model/language_model/layers/23/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 689 |
+
model/model/language_model/layers/23/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 690 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 691 |
+
model/model/language_model/layers/22/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 692 |
+
model/model/language_model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 693 |
+
model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 694 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 695 |
+
model/model/language_model/layers/23/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 696 |
+
model/model/language_model/layers/3/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 697 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 698 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 699 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 700 |
+
model/model/language_model/layers/23/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 701 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 702 |
+
model/model/language_model/layers/3/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 703 |
+
model/model/language_model/layers/3/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 704 |
+
model/model/language_model/layers/3/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 705 |
+
model/model/language_model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 706 |
+
model/model/language_model/layers/3/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 707 |
+
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 708 |
+
model/model/language_model/layers/5/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 709 |
+
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 710 |
+
model/model/language_model/layers/4/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 711 |
+
model/model/language_model/layers/5/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 712 |
+
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 713 |
+
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 714 |
+
model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 715 |
+
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 716 |
+
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 717 |
+
model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 718 |
+
model/model/language_model/layers/5/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 719 |
+
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 720 |
+
model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 721 |
+
model/model/language_model/layers/5/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 722 |
+
model/model/language_model/layers/4/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 723 |
+
model/model/language_model/layers/5/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 724 |
+
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 725 |
+
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 726 |
+
model/model/language_model/layers/5/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 727 |
+
model/model/language_model/layers/6/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 728 |
+
model/model/language_model/layers/5/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 729 |
+
model/model/language_model/layers/7/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 730 |
+
model/model/language_model/layers/5/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 731 |
+
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 732 |
+
model/model/language_model/layers/6/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 733 |
+
model/model/language_model/layers/7/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 734 |
+
model/model/language_model/layers/7/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 735 |
+
model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 736 |
+
model/model/language_model/layers/6/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 737 |
+
model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 738 |
+
model/model/language_model/layers/6/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5b5122ddf14755d4653403e71f345eaa7f82dda92ebd6ed2a4a192a3ec1eb58
|
| 3 |
+
size 4911745
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4095e6f026a6af62bb841ed4cb656f87daef8bc4da01331eb5cd2f6101643f8e
|
| 3 |
+
size 4910962
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c6b6d7b9779cfdc5e204eaac2cc50a9359511d62ffacf5449cb2d2c7b6b2950
|
| 3 |
+
size 4910643
|
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4bf5b5b253e1936cfc751be142e1c53829e2df4d78cbfb3d2a6cbca6dee3fe42
|
| 3 |
+
size 4909717
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2d404b4d563061df5e09ef24025eaaed51f6faf1d8b4eaaa4a0594c922f6205f
|
| 3 |
+
size 1634344
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:06237ba0178aef6158bf7826a3fd984b2611acfd63ba7bd2e9c49ae94610c97b
|
| 3 |
+
size 1634214
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af894eeb7c9eb8551e9b36c545abd2848870d65e2353f2b3fcf9581648be32aa
|
| 3 |
+
size 1634290
|
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e377fcb90ef4c40ad2db00f4297832038b52a7d309578988f18adf183ee1d04
|
| 3 |
+
size 1633929
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a76948e81fcb6a90e25fff8cd41aad7d768ec26639cc0440332946aa0d58d8f
|
| 3 |
+
size 1639020
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d7f525558e2f527cc9ed1f1645adbdb53a3480429fb9a1ada86fb417632c148f
|
| 3 |
+
size 1639118
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c407f3b87f8dea6d6b2a74711f8a61b19b3ee4644abe57d976d3496ac56181d
|
| 3 |
+
size 1640780
|
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fd54cfab8b861ebf166565a8264a80f31bbad631841ee0d3510c12ddab42145f
|
| 3 |
+
size 1639357
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4428a81501791820547035dd94f6c9b6f84a2887ad67d54dbd84eaadc309b7ca
|
| 3 |
+
size 4926583
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b173d21dba516d64a5e84cc23c2495d63bb16198c924d6a3cc7d78ea5bb34679
|
| 3 |
+
size 4925485
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6a8e7c754076d8deee73947792c4fa3fb5d4e5818862735387f1905cfca5b5b7
|
| 3 |
+
size 4927465
|
model/model/language_model/layers/0/mlp/down_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9bf47b3660b48e0fdb0cb520430c64a1d2fd757cb0ab2056483d744eca5c515b
|
| 3 |
+
size 4925226
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db17b174045871627339b9fc3f6f3c972b26f90151b3fe4c1950489b5d6aeddb
|
| 3 |
+
size 4907051
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:78836854f228428339549db077c5965c1e3b9eb66168b6b798c8a21d7526b0a1
|
| 3 |
+
size 4905823
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2b69f7770c77934caac85b715847d207a9cf2735fa84f674881288371ee6be8b
|
| 3 |
+
size 4908820
|
model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66f08bf6fa08bb68639b5e0634705f2645b22f466ec4fb3607c802bbb35836f2
|
| 3 |
+
size 4906989
|
model/model/language_model/layers/0/mlp/up_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:143368f921dc79b6e2b22c5a48738251c6d080d3c760fddcce2b30d41ea29ae6
|
| 3 |
+
size 4925836
|
model/model/language_model/layers/0/mlp/up_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:074442597a594936209527cb6a205f0d775957dad6ec4fa625a3b171a1fdde13
|
| 3 |
+
size 4925268
|
model/model/language_model/layers/0/mlp/up_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b99dba2ac7e2d5191ccc09157f10147c0cbfbafb1da2c31978e2558a8acc88ec
|
| 3 |
+
size 4926694
|
model/model/language_model/layers/0/mlp/up_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:73de22434a77e257753f14e3658af78a477235c309c9540408742b70d1c23eb4
|
| 3 |
+
size 4925717
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:42c7c73ee4e3c611ffaa43315e58afcb63cd94a89acb24e9472a4405f3b410ec
|
| 3 |
+
size 4903931
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8cc3841b42448705cdae04e69f34af8498478d4159c685797dee03e3d549b2fc
|
| 3 |
+
size 4903144
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0375f2595359c53202801ab17232f1644c4735367b280fdfc95f6e84571d802
|
| 3 |
+
size 4905395
|
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fb9ae671056db38a390d7e0c7f1cd0d6cc297e5fc56a4158ce51b38b1225ebb
|
| 3 |
+
size 4903463
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3b4da8d14af8d4bb3527885698d21134e2182151f4816f9deb6b1587792665ab
|
| 3 |
+
size 1636467
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:20087e612a59a94097ce410a8d57b4a301455847d833038049911e42a44d29ad
|
| 3 |
+
size 1635983
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fe84463827bd1103d561b0fa95b92ff99c1cdb84e51e171820db5c0e155d9b94
|
| 3 |
+
size 1636495
|
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4173d2863c70593a6e96d8ec20ec3b45ade3d151201ab95d517cbfc7b4ccf2d6
|
| 3 |
+
size 1636564
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:408d26760c325f064b09f7edfcc27fbbc3afe75db0e3013e14d7296a2f8df295
|
| 3 |
+
size 1636518
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:da927262ba2f1e31b788bbbd967a7fae2816926c6c16f63e44bf864fb9ad50ac
|
| 3 |
+
size 1636363
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1d0338801c48f230794d0d4480d71006939cb2cd0898607ab090aa1aa987348
|
| 3 |
+
size 1638129
|
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:547de79877bb507eea0166d40e0c765f47f8feda74074d0013390f935fa77ebf
|
| 3 |
+
size 1636179
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:61df695f03076864daa3f57282182ed94dbedf4f2e17dcac4bedb5781832d0c5
|
| 3 |
+
size 4928722
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4301351ddacdb84d6207fa0929ae6ac9442ac7e154cfe7e3f07d5f29415fa3c6
|
| 3 |
+
size 4927797
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:84e0900e9f56bd063cef43e562bfe53321f041d9da1f0ab2104f59aa3c5fe957
|
| 3 |
+
size 4928920
|
model/model/language_model/layers/1/mlp/down_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:944b165d306b20cbf675bbc696962be1e9d53e66e571ff5e8261edc45c8de369
|
| 3 |
+
size 4928151
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07c247818d8acdf01bd275176df1ae0a816624b12bbd80a8616072e3a76efd23
|
| 3 |
+
size 4904441
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2e01bc02bdc40f632eb79c65fa13392da013bf1744c4c92476309c82628f57b6
|
| 3 |
+
size 4904613
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b37c8f8b3770bde3e6a5cc24fc73d74c229f249d4e9ebb90adc35afb9fe48ab9
|
| 3 |
+
size 4905619
|
model/model/language_model/layers/1/mlp/gate_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d725a43a37e5441d73a60aaf4e22f6c715e8d3bce45c3d0e3d61a71027a7d8ff
|
| 3 |
+
size 4904122
|
model/model/language_model/layers/1/mlp/up_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e8599bc67c40eeb767bede4f83e4c4c9325bea84d2226410bb0344c6413b5e11
|
| 3 |
+
size 4926267
|
model/model/language_model/layers/1/mlp/up_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c79a8b0a84a894fe06bdef87a59647b17a5ac3f6edcdb15612f3c562e168d6c3
|
| 3 |
+
size 4925460
|
model/model/language_model/layers/1/mlp/up_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4226e5d67cf09c86bb681fe5433adfd8223953e81fda944382c5a1ebeb2fb8c7
|
| 3 |
+
size 4926993
|
model/model/language_model/layers/1/mlp/up_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c3b7ab00186b224dad84fda4348fe78d5615b8c58063bf98f600045dae7be13
|
| 3 |
+
size 4926146
|
model/model/language_model/layers/10/linear_attn/in_proj_qkv/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac23aa5882b1cff618fe9ce98229e46486f0eff84dca65545d2bf10b9fd148d9
|
| 3 |
+
size 4921297
|