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 +801 -0
- model/model/language_model/embed_tokens/embedding/0.0 +3 -0
- model/model/language_model/layers/33/mlp/down_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/33/mlp/down_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/33/mlp/down_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/33/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/33/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/33/mlp/up_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/34/mlp/down_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/34/mlp/down_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/34/mlp/down_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/34/mlp/down_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/34/mlp/gate_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/34/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/34/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/34/mlp/gate_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/34/mlp/up_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/34/mlp/up_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/34/mlp/up_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/34/mlp/up_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/35/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/35/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/35/mlp/up_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/35/self_attn/k_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/35/self_attn/k_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/35/self_attn/k_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/35/self_attn/k_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/35/self_attn/o_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/35/self_attn/o_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/35/self_attn/o_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/35/self_attn/o_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/35/self_attn/q_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/35/self_attn/q_proj/kernel/3.0 +3 -0
- model/model/language_model/layers/35/self_attn/v_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/2.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/0.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/1.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/2.0 +3 -0
- model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/3.0 +3 -0
- model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.0 +3 -0
- model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.1 +3 -0
- model/model/language_model/layers/36/mlp/gate_proj/kernel/1.0 +3 -0
- model/model/language_model/layers/36/mlp/gate_proj/kernel/2.0 +3 -0
- model/model/language_model/layers/37/linear_attn/in_proj_z/kernel/0.0 +3 -0
- model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.2 +3 -0
- model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.3 +3 -0
- model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
- model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
.gitattributes
CHANGED
|
@@ -1285,3 +1285,804 @@ model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.3 filter=lfs
|
|
| 1285 |
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1286 |
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1287 |
model/model/language_model/layers/47/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1285 |
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1286 |
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1287 |
model/model/language_model/layers/47/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1288 |
+
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1289 |
+
model/model/language_model/layers/47/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1290 |
+
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1291 |
+
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1292 |
+
model/model/language_model/layers/47/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1293 |
+
model/model/language_model/layers/47/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1294 |
+
model/model/language_model/layers/50/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1295 |
+
model/model/language_model/layers/47/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1296 |
+
model/model/language_model/layers/47/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1297 |
+
model/model/language_model/layers/47/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1298 |
+
model/model/language_model/layers/47/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1299 |
+
model/model/language_model/layers/48/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1300 |
+
model/model/language_model/layers/48/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1301 |
+
model/model/language_model/layers/47/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1302 |
+
model/model/language_model/layers/47/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1303 |
+
model/model/language_model/layers/48/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1304 |
+
model/model/language_model/layers/50/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1305 |
+
model/model/language_model/layers/47/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1306 |
+
model/model/language_model/layers/48/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1307 |
+
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1308 |
+
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1309 |
+
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1310 |
+
model/model/language_model/layers/48/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1311 |
+
model/model/language_model/layers/48/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1312 |
+
model/model/language_model/layers/48/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1313 |
+
model/model/language_model/layers/50/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1314 |
+
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1315 |
+
model/model/language_model/layers/48/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1316 |
+
model/model/language_model/layers/48/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1317 |
+
model/model/language_model/layers/47/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1318 |
+
model/model/language_model/layers/48/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1319 |
+
model/model/language_model/layers/50/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1320 |
+
model/model/language_model/layers/50/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1321 |
+
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1322 |
+
model/model/language_model/layers/50/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1323 |
+
model/model/language_model/layers/50/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1324 |
+
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1325 |
+
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1326 |
+
model/model/language_model/layers/50/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1327 |
+
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1328 |
+
model/model/language_model/layers/50/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1329 |
+
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1330 |
+
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1331 |
+
model/model/language_model/layers/48/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1332 |
+
model/model/language_model/layers/50/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1333 |
+
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1334 |
+
model/model/language_model/layers/50/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1335 |
+
model/model/language_model/layers/50/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1336 |
+
model/model/language_model/layers/49/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1337 |
+
model/model/language_model/layers/48/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1338 |
+
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1339 |
+
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1340 |
+
model/model/language_model/layers/49/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1341 |
+
model/model/language_model/layers/49/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1342 |
+
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1343 |
+
model/model/language_model/layers/50/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1344 |
+
model/model/language_model/layers/50/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1345 |
+
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1346 |
+
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1347 |
+
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1348 |
+
model/model/language_model/layers/46/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1349 |
+
model/model/language_model/layers/50/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1350 |
+
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1351 |
+
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1352 |
+
model/model/language_model/layers/46/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1353 |
+
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1354 |
+
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1355 |
+
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1356 |
+
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1357 |
+
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1358 |
+
model/model/language_model/layers/49/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1359 |
+
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1360 |
+
model/model/language_model/layers/49/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1361 |
+
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1362 |
+
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1363 |
+
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1364 |
+
model/model/language_model/layers/56/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1365 |
+
model/model/language_model/layers/59/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1366 |
+
model/model/language_model/layers/54/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1367 |
+
model/model/language_model/layers/56/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1368 |
+
model/model/language_model/layers/56/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1369 |
+
model/model/language_model/layers/59/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1370 |
+
model/model/language_model/layers/51/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1371 |
+
model/model/language_model/layers/51/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1372 |
+
model/model/language_model/layers/59/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1373 |
+
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1374 |
+
model/model/language_model/layers/56/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1375 |
+
model/model/language_model/layers/59/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1376 |
+
model/model/language_model/layers/56/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1377 |
+
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1378 |
+
model/model/language_model/layers/56/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1379 |
+
model/model/language_model/layers/59/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1380 |
+
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1381 |
+
model/model/language_model/layers/59/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1382 |
+
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1383 |
+
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1384 |
+
model/model/language_model/layers/51/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1385 |
+
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1386 |
+
model/model/language_model/layers/59/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1387 |
+
model/model/language_model/layers/51/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1388 |
+
model/model/language_model/layers/51/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1389 |
+
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1390 |
+
model/model/language_model/layers/51/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1391 |
+
model/model/language_model/layers/59/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1392 |
+
model/model/language_model/layers/51/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1393 |
+
model/model/language_model/layers/51/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1394 |
+
model/model/language_model/layers/51/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1395 |
+
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1396 |
+
model/model/language_model/layers/61/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1397 |
+
model/model/language_model/layers/51/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1398 |
+
model/model/language_model/layers/51/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1399 |
+
model/model/language_model/layers/59/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1400 |
+
model/model/language_model/layers/53/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1401 |
+
model/model/language_model/layers/59/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1402 |
+
model/model/language_model/layers/59/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1403 |
+
model/model/language_model/layers/61/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1404 |
+
model/model/language_model/layers/53/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1405 |
+
model/model/language_model/layers/53/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1406 |
+
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1407 |
+
model/model/language_model/layers/53/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1408 |
+
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1409 |
+
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1410 |
+
model/model/language_model/layers/53/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1411 |
+
model/model/language_model/layers/61/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1412 |
+
model/model/language_model/layers/59/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1413 |
+
model/model/language_model/layers/51/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1414 |
+
model/model/language_model/layers/33/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1415 |
+
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1416 |
+
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1417 |
+
model/model/language_model/layers/33/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1418 |
+
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1419 |
+
model/model/language_model/layers/33/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1420 |
+
model/model/language_model/layers/33/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1421 |
+
model/model/language_model/layers/35/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1422 |
+
model/model/language_model/layers/33/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1423 |
+
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1424 |
+
model/model/language_model/layers/33/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1425 |
+
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1426 |
+
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1427 |
+
model/model/language_model/layers/35/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1428 |
+
model/model/language_model/layers/34/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1429 |
+
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1430 |
+
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1431 |
+
model/model/language_model/layers/34/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1432 |
+
model/model/language_model/layers/35/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1433 |
+
model/model/language_model/layers/34/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1434 |
+
model/model/language_model/layers/34/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1435 |
+
model/model/language_model/layers/35/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1436 |
+
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1437 |
+
model/model/language_model/layers/35/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1438 |
+
model/model/language_model/layers/34/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1439 |
+
model/model/language_model/layers/34/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1440 |
+
model/model/language_model/layers/34/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1441 |
+
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1442 |
+
model/model/language_model/layers/34/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1443 |
+
model/model/language_model/layers/34/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1444 |
+
model/model/language_model/layers/34/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1445 |
+
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1446 |
+
model/model/language_model/layers/34/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1447 |
+
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1448 |
+
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1449 |
+
model/model/language_model/layers/34/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1450 |
+
model/model/language_model/layers/36/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1451 |
+
model/model/language_model/layers/35/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1452 |
+
model/model/language_model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1453 |
+
model/model/language_model/layers/35/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1454 |
+
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1455 |
+
model/model/language_model/layers/35/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1456 |
+
model/model/language_model/layers/35/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1457 |
+
model/model/language_model/layers/36/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1458 |
+
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1459 |
+
model/model/language_model/layers/37/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1460 |
+
model/model/language_model/layers/35/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1461 |
+
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1462 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1463 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1464 |
+
model/model/visual/blocks/8/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1465 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1466 |
+
model/model/visual/blocks/9/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1467 |
+
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1468 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1469 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1470 |
+
model/model/visual/blocks/9/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1471 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1472 |
+
model/model/visual/blocks/9/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1473 |
+
model/model/visual/blocks/9/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1474 |
+
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1475 |
+
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1476 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1477 |
+
model/model/visual/blocks/10/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1478 |
+
model/model/visual/blocks/10/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1479 |
+
model/model/visual/blocks/10/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1480 |
+
model/model/visual/blocks/10/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1481 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1482 |
+
model/model/visual/blocks/10/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1483 |
+
model/model/visual/blocks/9/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1484 |
+
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1485 |
+
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1486 |
+
model/model/visual/blocks/16/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1487 |
+
model/model/visual/blocks/16/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1488 |
+
model/model/visual/blocks/16/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1489 |
+
model/model/visual/blocks/16/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1490 |
+
model/model/visual/blocks/10/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1491 |
+
model/model/visual/blocks/9/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1492 |
+
model/model/visual/blocks/16/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1493 |
+
model/model/visual/blocks/16/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1494 |
+
model/model/visual/blocks/16/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1495 |
+
model/model/visual/blocks/16/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1496 |
+
model/model/visual/blocks/16/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1497 |
+
model/model/visual/blocks/10/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1498 |
+
model/model/visual/blocks/10/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1499 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1500 |
+
model/model/visual/blocks/16/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1501 |
+
model/model/visual/blocks/16/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1502 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1503 |
+
model/model/visual/blocks/16/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1504 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1505 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1506 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1507 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1508 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1509 |
+
model/model/language_model/layers/49/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1510 |
+
model/model/language_model/layers/49/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1511 |
+
model/model/language_model/layers/49/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1512 |
+
model/model/language_model/layers/49/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1513 |
+
model/model/language_model/layers/52/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1514 |
+
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1515 |
+
model/model/language_model/layers/52/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1516 |
+
model/model/language_model/layers/49/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1517 |
+
model/model/language_model/layers/49/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1518 |
+
model/model/language_model/layers/46/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1519 |
+
model/model/language_model/layers/46/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1520 |
+
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1521 |
+
model/model/language_model/layers/46/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1522 |
+
model/model/language_model/layers/49/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1523 |
+
model/model/language_model/layers/46/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1524 |
+
model/model/language_model/layers/46/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1525 |
+
model/model/language_model/layers/49/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1526 |
+
model/model/language_model/layers/46/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1527 |
+
model/model/language_model/layers/49/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1528 |
+
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1529 |
+
model/model/language_model/layers/46/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1530 |
+
model/model/language_model/layers/46/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1531 |
+
model/model/language_model/layers/46/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1532 |
+
model/model/language_model/layers/46/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1533 |
+
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1534 |
+
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1535 |
+
model/model/language_model/layers/52/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1536 |
+
model/model/language_model/layers/46/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1537 |
+
model/model/language_model/layers/49/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1538 |
+
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1539 |
+
model/model/language_model/layers/46/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1540 |
+
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1541 |
+
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1542 |
+
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1543 |
+
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1544 |
+
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1545 |
+
model/model/language_model/layers/54/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1546 |
+
model/model/language_model/layers/54/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1547 |
+
model/model/language_model/layers/52/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1548 |
+
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1549 |
+
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1550 |
+
model/model/language_model/layers/54/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1551 |
+
model/model/language_model/layers/52/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1552 |
+
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1553 |
+
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1554 |
+
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1555 |
+
model/model/language_model/layers/51/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1556 |
+
model/model/visual/blocks/18/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1557 |
+
model/model/visual/blocks/10/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1558 |
+
model/model/visual/blocks/18/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1559 |
+
model/model/visual/blocks/16/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1560 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1561 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1562 |
+
model/model/visual/blocks/3/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1563 |
+
model/model/visual/blocks/3/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1564 |
+
model/model/visual/blocks/3/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1565 |
+
model/model/visual/blocks/3/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1566 |
+
model/model/visual/blocks/18/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1567 |
+
model/model/visual/blocks/3/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1568 |
+
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1569 |
+
model/model/visual/blocks/18/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1570 |
+
model/model/visual/blocks/18/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1571 |
+
model/model/visual/blocks/18/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1572 |
+
model/model/visual/blocks/18/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1573 |
+
model/model/visual/blocks/18/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1574 |
+
model/model/visual/blocks/18/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1575 |
+
model/model/visual/blocks/3/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1576 |
+
model/model/visual/blocks/18/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1577 |
+
model/model/visual/blocks/3/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1578 |
+
model/model/visual/blocks/18/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1579 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1580 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1581 |
+
model/model/visual/blocks/17/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1582 |
+
model/model/visual/blocks/17/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1583 |
+
model/model/visual/blocks/17/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1584 |
+
model/model/visual/blocks/17/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1585 |
+
model/model/visual/blocks/17/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1586 |
+
model/model/visual/blocks/17/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1587 |
+
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1588 |
+
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1589 |
+
model/model/visual/blocks/17/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1590 |
+
model/model/visual/blocks/18/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1591 |
+
model/model/visual/blocks/17/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1592 |
+
model/model/visual/blocks/17/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1593 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1594 |
+
model/model/visual/blocks/11/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1595 |
+
model/model/visual/blocks/18/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1596 |
+
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1597 |
+
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1598 |
+
model/model/visual/blocks/22/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1599 |
+
model/model/visual/blocks/13/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1600 |
+
model/model/visual/blocks/22/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1601 |
+
model/model/visual/blocks/22/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1602 |
+
model/model/visual/blocks/12/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1603 |
+
model/model/visual/blocks/22/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1604 |
+
model/model/visual/blocks/22/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1605 |
+
model/model/visual/blocks/13/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1606 |
+
model/model/visual/blocks/22/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1607 |
+
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1608 |
+
model/model/visual/blocks/13/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1609 |
+
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1610 |
+
model/model/visual/blocks/22/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1611 |
+
model/model/visual/blocks/22/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1612 |
+
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1613 |
+
model/model/visual/blocks/13/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1614 |
+
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1615 |
+
model/model/visual/blocks/22/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1616 |
+
model/model/visual/blocks/20/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1617 |
+
model/model/visual/blocks/20/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1618 |
+
model/model/visual/blocks/20/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1619 |
+
model/model/visual/blocks/22/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1620 |
+
model/model/visual/blocks/20/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1621 |
+
model/model/visual/blocks/20/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1622 |
+
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1623 |
+
model/model/visual/blocks/20/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1624 |
+
model/model/visual/blocks/20/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1625 |
+
model/model/visual/blocks/20/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1626 |
+
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1627 |
+
model/model/visual/blocks/22/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1628 |
+
model/model/visual/blocks/22/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1629 |
+
model/model/visual/blocks/20/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1630 |
+
model/model/visual/blocks/15/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1631 |
+
model/model/visual/blocks/20/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1632 |
+
model/model/visual/blocks/22/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1633 |
+
model/model/visual/blocks/20/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1634 |
+
model/model/visual/blocks/20/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1635 |
+
model/model/visual/blocks/15/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1636 |
+
model/model/visual/blocks/15/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1637 |
+
model/model/visual/blocks/20/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1638 |
+
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1639 |
+
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1640 |
+
model/model/visual/blocks/15/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1641 |
+
model/model/visual/blocks/15/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1642 |
+
model/model/visual/blocks/15/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1643 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1644 |
+
model/model/visual/blocks/5/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1645 |
+
model/model/visual/blocks/5/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1646 |
+
model/model/visual/blocks/7/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1647 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1648 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1649 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1650 |
+
model/model/visual/blocks/7/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1651 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1652 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1653 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1654 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1655 |
+
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1656 |
+
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1657 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1658 |
+
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1659 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1660 |
+
model/model/visual/blocks/5/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1661 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1662 |
+
model/model/visual/blocks/8/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1663 |
+
model/model/visual/blocks/7/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1664 |
+
model/model/visual/blocks/8/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1665 |
+
model/model/visual/blocks/7/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1666 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1667 |
+
model/model/visual/blocks/9/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1668 |
+
model/model/visual/blocks/9/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1669 |
+
model/model/visual/blocks/7/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1670 |
+
model/model/visual/blocks/8/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1671 |
+
model/model/visual/blocks/8/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1672 |
+
model/model/visual/blocks/9/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1673 |
+
model/model/visual/blocks/9/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1674 |
+
model/model/visual/blocks/9/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1675 |
+
model/model/visual/blocks/8/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1676 |
+
model/model/visual/blocks/8/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1677 |
+
model/model/visual/blocks/9/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1678 |
+
model/model/visual/blocks/9/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1679 |
+
model/model/visual/blocks/8/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1680 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1681 |
+
model/model/visual/blocks/8/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1682 |
+
model/model/visual/blocks/10/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1683 |
+
model/model/visual/blocks/8/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1684 |
+
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1685 |
+
model/model/visual/blocks/17/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1686 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1687 |
+
model/model/visual/blocks/11/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1688 |
+
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1689 |
+
model/model/visual/blocks/17/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1690 |
+
model/model/visual/blocks/17/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1691 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1692 |
+
model/model/visual/blocks/11/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1693 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1694 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1695 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1696 |
+
model/model/visual/blocks/11/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1697 |
+
model/model/visual/blocks/11/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1698 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1699 |
+
model/model/visual/blocks/12/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1700 |
+
model/model/visual/blocks/17/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1701 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1702 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1703 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1704 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1705 |
+
model/model/visual/blocks/11/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1706 |
+
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1707 |
+
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1708 |
+
model/model/visual/blocks/11/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1709 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1710 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1711 |
+
model/model/visual/blocks/12/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1712 |
+
model/model/visual/blocks/12/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1713 |
+
model/model/visual/blocks/12/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1714 |
+
model/model/visual/blocks/12/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1715 |
+
model/model/visual/blocks/13/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1716 |
+
model/model/visual/blocks/12/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1717 |
+
model/model/visual/blocks/13/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1718 |
+
model/model/visual/blocks/13/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1719 |
+
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1720 |
+
model/model/visual/blocks/13/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1721 |
+
model/model/visual/blocks/13/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1722 |
+
model/model/visual/blocks/13/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1723 |
+
model/model/visual/blocks/13/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1724 |
+
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1725 |
+
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1726 |
+
model/model/visual/blocks/13/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1727 |
+
model/model/visual/blocks/13/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1728 |
+
model/model/language_model/layers/52/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1729 |
+
model/model/language_model/layers/52/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1730 |
+
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1731 |
+
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1732 |
+
model/model/language_model/layers/52/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1733 |
+
model/model/language_model/layers/51/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1734 |
+
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1735 |
+
model/model/language_model/layers/56/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1736 |
+
model/model/language_model/layers/52/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1737 |
+
model/model/language_model/layers/51/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1738 |
+
model/model/language_model/layers/52/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1739 |
+
model/model/language_model/layers/51/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1740 |
+
model/model/language_model/layers/51/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1741 |
+
model/model/language_model/layers/52/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1742 |
+
model/model/language_model/layers/51/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1743 |
+
model/model/language_model/layers/51/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1744 |
+
model/model/language_model/layers/52/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1745 |
+
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1746 |
+
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1747 |
+
model/model/language_model/layers/52/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1748 |
+
model/model/language_model/layers/52/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1749 |
+
model/model/language_model/layers/56/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1750 |
+
model/model/language_model/layers/52/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1751 |
+
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1752 |
+
model/model/language_model/layers/51/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1753 |
+
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1754 |
+
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1755 |
+
model/model/language_model/layers/54/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1756 |
+
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1757 |
+
model/model/language_model/layers/54/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1758 |
+
model/model/language_model/layers/56/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1759 |
+
model/model/language_model/layers/54/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1760 |
+
model/model/language_model/layers/51/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1761 |
+
model/model/language_model/layers/54/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1762 |
+
model/model/language_model/layers/54/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1763 |
+
model/model/language_model/layers/51/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1764 |
+
model/model/language_model/layers/54/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1765 |
+
model/model/language_model/layers/51/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1766 |
+
model/model/language_model/layers/54/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1767 |
+
model/model/language_model/layers/54/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1768 |
+
model/model/language_model/layers/54/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1769 |
+
model/model/language_model/layers/54/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1770 |
+
model/model/language_model/layers/51/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1771 |
+
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1772 |
+
model/model/language_model/layers/51/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1773 |
+
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1774 |
+
model/model/language_model/layers/54/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1775 |
+
model/model/language_model/layers/59/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1776 |
+
model/model/language_model/layers/53/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1777 |
+
model/model/language_model/layers/56/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1778 |
+
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1779 |
+
model/model/language_model/layers/53/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1780 |
+
model/model/language_model/layers/56/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1781 |
+
model/model/language_model/layers/56/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1782 |
+
model/model/language_model/layers/56/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1783 |
+
model/model/language_model/layers/56/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1784 |
+
model/model/language_model/layers/56/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1785 |
+
model/model/language_model/layers/55/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1786 |
+
model/model/language_model/layers/61/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1787 |
+
model/model/language_model/layers/61/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1788 |
+
model/model/language_model/layers/55/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1789 |
+
model/model/language_model/layers/61/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1790 |
+
model/model/language_model/layers/61/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1791 |
+
model/model/language_model/layers/61/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1792 |
+
model/model/language_model/layers/61/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1793 |
+
model/model/language_model/layers/55/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1794 |
+
model/model/language_model/layers/57/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1795 |
+
model/model/language_model/layers/55/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1796 |
+
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1797 |
+
model/model/language_model/layers/57/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1798 |
+
model/model/language_model/layers/63/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1799 |
+
model/model/language_model/layers/63/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1800 |
+
model/model/language_model/layers/55/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1801 |
+
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1802 |
+
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1803 |
+
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1804 |
+
model/model/language_model/layers/63/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1805 |
+
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1806 |
+
model/model/language_model/layers/63/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1807 |
+
model/model/language_model/layers/57/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1808 |
+
model/model/language_model/layers/63/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1809 |
+
model/model/language_model/layers/62/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1810 |
+
model/model/language_model/layers/57/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1811 |
+
model/model/language_model/layers/57/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1812 |
+
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1813 |
+
model/model/language_model/layers/57/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1814 |
+
model/model/language_model/layers/62/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1815 |
+
model/model/language_model/layers/57/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1816 |
+
model/model/language_model/layers/57/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1817 |
+
model/model/language_model/layers/57/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1818 |
+
model/model/language_model/layers/57/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1819 |
+
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1820 |
+
model/model/language_model/layers/55/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1821 |
+
model/model/language_model/layers/63/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1822 |
+
model/model/language_model/layers/63/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1823 |
+
model/model/language_model/layers/63/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1824 |
+
model/model/language_model/layers/57/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1825 |
+
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1826 |
+
model/model/language_model/layers/57/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1827 |
+
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1828 |
+
model/model/language_model/layers/55/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1829 |
+
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1830 |
+
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1831 |
+
model/model/language_model/layers/55/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1832 |
+
model/model/language_model/layers/55/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1833 |
+
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1834 |
+
model/model/language_model/layers/62/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1835 |
+
model/model/language_model/layers/55/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1836 |
+
model/model/language_model/layers/55/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1837 |
+
model/model/language_model/layers/55/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1838 |
+
model/model/visual/blocks/2/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1839 |
+
model/model/language_model/layers/63/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1840 |
+
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1841 |
+
model/model/visual/blocks/2/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1842 |
+
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1843 |
+
model/model/visual/blocks/2/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1844 |
+
model/model/language_model/layers/63/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1845 |
+
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1846 |
+
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1847 |
+
model/model/visual/blocks/2/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1848 |
+
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1849 |
+
model/model/visual/blocks/2/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1850 |
+
model/model/visual/blocks/2/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1851 |
+
model/model/visual/blocks/2/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1852 |
+
model/model/language_model/layers/58/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1853 |
+
model/model/visual/blocks/2/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1854 |
+
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1855 |
+
model/model/visual/blocks/2/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1856 |
+
model/model/visual/blocks/2/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1857 |
+
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1858 |
+
model/model/language_model/layers/58/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1859 |
+
model/model/visual/blocks/2/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1860 |
+
model/model/visual/blocks/0/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1861 |
+
model/model/language_model/layers/58/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1862 |
+
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1863 |
+
model/model/visual/blocks/0/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1864 |
+
model/model/language_model/layers/63/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1865 |
+
model/model/language_model/layers/60/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1866 |
+
model/model/language_model/layers/60/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1867 |
+
model/model/language_model/layers/60/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1868 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1869 |
+
model/model/language_model/layers/58/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1870 |
+
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1871 |
+
model/model/language_model/layers/58/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1872 |
+
model/model/visual/blocks/0/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1873 |
+
model/model/language_model/layers/60/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1874 |
+
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1875 |
+
model/model/visual/blocks/0/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1876 |
+
model/model/language_model/layers/58/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1877 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1878 |
+
model/model/visual/blocks/0/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1879 |
+
model/model/language_model/layers/60/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1880 |
+
model/model/language_model/layers/58/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1881 |
+
model/model/language_model/layers/60/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1882 |
+
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1883 |
+
model/model/language_model/layers/60/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1884 |
+
model/model/language_model/layers/58/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1885 |
+
model/model/visual/blocks/4/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1886 |
+
model/model/language_model/layers/58/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1887 |
+
model/model/visual/blocks/4/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1888 |
+
model/model/language_model/layers/58/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1889 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1890 |
+
model/model/visual/blocks/0/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1891 |
+
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1892 |
+
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1893 |
+
model/model/language_model/layers/58/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1894 |
+
model/model/language_model/layers/60/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1895 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1896 |
+
model/model/language_model/layers/60/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1897 |
+
model/model/visual/blocks/4/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1898 |
+
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1899 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1900 |
+
model/model/visual/blocks/19/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1901 |
+
model/model/visual/blocks/14/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1902 |
+
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1903 |
+
model/model/visual/blocks/19/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1904 |
+
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1905 |
+
model/model/visual/blocks/19/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1906 |
+
model/model/visual/blocks/19/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1907 |
+
model/model/visual/blocks/19/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1908 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1909 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1910 |
+
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1911 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1912 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1913 |
+
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1914 |
+
model/model/visual/blocks/19/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1915 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1916 |
+
model/model/visual/blocks/25/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1917 |
+
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1918 |
+
model/model/visual/blocks/25/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1919 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1920 |
+
model/model/visual/blocks/25/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1921 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1922 |
+
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1923 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1924 |
+
model/model/visual/blocks/23/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1925 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1926 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1927 |
+
model/model/visual/blocks/25/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1928 |
+
model/model/visual/blocks/25/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1929 |
+
model/model/visual/blocks/25/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1930 |
+
model/model/visual/blocks/23/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1931 |
+
model/model/visual/blocks/23/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1932 |
+
model/model/visual/blocks/23/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1933 |
+
model/model/visual/blocks/23/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1934 |
+
model/model/visual/blocks/26/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1935 |
+
model/model/visual/blocks/23/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1936 |
+
model/model/visual/blocks/26/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1937 |
+
model/model/visual/blocks/26/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1938 |
+
model/model/visual/blocks/23/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1939 |
+
model/model/visual/blocks/26/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1940 |
+
model/model/visual/blocks/23/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1941 |
+
model/model/visual/blocks/26/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1942 |
+
model/model/visual/blocks/23/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1943 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1944 |
+
model/model/visual/blocks/23/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1945 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1946 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1947 |
+
model/model/language_model/layers/60/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1948 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1949 |
+
model/model/visual/blocks/0/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1950 |
+
model/model/visual/blocks/4/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1951 |
+
model/model/visual/blocks/4/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1952 |
+
model/model/visual/blocks/0/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1953 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1954 |
+
model/model/language_model/layers/58/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1955 |
+
model/model/visual/blocks/1/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1956 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1957 |
+
model/model/language_model/layers/60/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1958 |
+
model/model/visual/blocks/0/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1959 |
+
model/model/visual/blocks/0/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1960 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1961 |
+
model/model/language_model/layers/60/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1962 |
+
model/model/language_model/layers/60/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1963 |
+
model/model/visual/blocks/1/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1964 |
+
model/model/visual/blocks/1/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1965 |
+
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1966 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1967 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1968 |
+
model/model/visual/blocks/1/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1969 |
+
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1970 |
+
model/model/visual/blocks/1/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1971 |
+
model/model/visual/blocks/1/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1972 |
+
model/model/visual/blocks/1/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1973 |
+
model/model/visual/blocks/1/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1974 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1975 |
+
model/model/visual/blocks/1/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1976 |
+
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1977 |
+
model/model/visual/blocks/1/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1978 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1979 |
+
model/model/visual/blocks/4/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1980 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 1981 |
+
model/model/visual/blocks/1/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1982 |
+
model/model/visual/blocks/1/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1983 |
+
model/model/visual/blocks/1/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1984 |
+
model/model/visual/blocks/5/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1985 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1986 |
+
model/model/visual/blocks/4/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1987 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1988 |
+
model/model/visual/blocks/5/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 1989 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1990 |
+
model/model/visual/blocks/5/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1991 |
+
model/model/visual/blocks/7/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1992 |
+
model/model/visual/blocks/7/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 1993 |
+
model/model/visual/blocks/5/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1994 |
+
model/model/language_model/layers/55/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 1995 |
+
model/model/language_model/layers/63/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 1996 |
+
model/model/language_model/layers/55/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1997 |
+
model/model/language_model/layers/55/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 1998 |
+
model/model/language_model/layers/55/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 1999 |
+
model/model/language_model/layers/55/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2000 |
+
model/model/language_model/layers/63/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2001 |
+
model/model/language_model/layers/55/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2002 |
+
model/model/language_model/layers/62/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2003 |
+
model/model/language_model/layers/63/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2004 |
+
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2005 |
+
model/model/language_model/layers/62/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2006 |
+
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2007 |
+
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2008 |
+
model/model/language_model/layers/62/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2009 |
+
model/model/language_model/layers/63/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2010 |
+
model/model/language_model/layers/62/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2011 |
+
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2012 |
+
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2013 |
+
model/model/language_model/layers/62/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2014 |
+
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2015 |
+
model/model/language_model/layers/63/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2016 |
+
model/model/language_model/layers/62/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2017 |
+
model/model/language_model/layers/62/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2018 |
+
model/model/language_model/layers/58/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2019 |
+
model/model/language_model/layers/62/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2020 |
+
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2021 |
+
model/model/language_model/layers/58/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2022 |
+
model/model/language_model/layers/62/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2023 |
+
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2024 |
+
model/model/language_model/layers/62/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2025 |
+
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2026 |
+
model/model/language_model/layers/63/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2027 |
+
model/model/language_model/layers/62/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2028 |
+
model/model/language_model/layers/63/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2029 |
+
model/model/language_model/layers/63/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2030 |
+
model/model/language_model/layers/63/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2031 |
+
model/model/language_model/layers/58/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2032 |
+
model/model/language_model/layers/63/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2033 |
+
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2034 |
+
model/model/language_model/layers/63/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2035 |
+
model/model/language_model/layers/62/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2036 |
+
model/model/language_model/layers/63/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2037 |
+
model/model/language_model/layers/60/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2038 |
+
model/model/language_model/layers/60/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2039 |
+
model/model/visual/blocks/2/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2040 |
+
model/model/language_model/layers/63/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2041 |
+
model/model/language_model/layers/63/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2042 |
+
model/model/visual/blocks/2/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2043 |
+
model/model/visual/blocks/15/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2044 |
+
model/model/visual/blocks/14/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2045 |
+
model/model/visual/blocks/15/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2046 |
+
model/model/visual/blocks/15/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2047 |
+
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2048 |
+
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2049 |
+
model/model/visual/blocks/15/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2050 |
+
model/model/visual/blocks/15/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2051 |
+
model/model/visual/blocks/15/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2052 |
+
model/model/visual/blocks/15/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2053 |
+
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2054 |
+
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2055 |
+
model/model/visual/blocks/14/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2056 |
+
model/model/visual/blocks/14/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2057 |
+
model/model/visual/blocks/14/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2058 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2059 |
+
model/model/visual/blocks/14/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2060 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2061 |
+
model/model/visual/blocks/24/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2062 |
+
model/model/visual/blocks/14/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2063 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2064 |
+
model/model/visual/blocks/14/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2065 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2066 |
+
model/model/visual/blocks/24/attn/qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2067 |
+
model/model/visual/blocks/14/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2068 |
+
model/model/visual/blocks/14/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2069 |
+
model/model/visual/blocks/14/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2070 |
+
model/model/visual/blocks/14/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2071 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
|
| 2072 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2073 |
+
model/model/visual/blocks/14/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2074 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2075 |
+
model/model/visual/blocks/24/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2076 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2077 |
+
model/model/visual/blocks/24/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2078 |
+
model/model/visual/blocks/19/attn/qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2079 |
+
model/model/visual/blocks/19/attn/proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
|
| 2080 |
+
model/model/visual/blocks/19/attn/qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2081 |
+
model/model/visual/blocks/24/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2082 |
+
model/model/visual/blocks/19/attn/proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2083 |
+
model/model/visual/blocks/19/mlp/linear_fc1/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
|
| 2084 |
+
model/model/visual/blocks/24/attn/qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
|
| 2085 |
+
model/model/visual/blocks/24/mlp/linear_fc2/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
| 2086 |
+
model/model/visual/blocks/25/mlp/linear_fc1/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
|
| 2087 |
+
model/model/visual/blocks/19/mlp/linear_fc2/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
|
| 2088 |
+
model/model/visual/blocks/19/mlp/linear_fc1/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
|
model/model/language_model/embed_tokens/embedding/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:af82da78d1151067f2d00fbac699c3fb0ab5e31db6b9180fb70cf5f5552edba4
|
| 3 |
+
size 494023164
|
model/model/language_model/layers/33/mlp/down_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8402322c86f9990bb99c24084c9971a47cabdb4b41263c3b175ea41b28b2db18
|
| 3 |
+
size 34739431
|
model/model/language_model/layers/33/mlp/down_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c0e1e9c354aadd2422c62ee42a79c7ca6835c8a95bea2db48329fe8445a39cc3
|
| 3 |
+
size 34773007
|
model/model/language_model/layers/33/mlp/down_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:68ab64fbe00cdf51fe9becae09ec28613fac6a2db829b04f6f59fbb99bc9df00
|
| 3 |
+
size 34780186
|
model/model/language_model/layers/33/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3168d83a8c6ab38bdc644adcfaec2df710dedf5e2dca73028293fbe5507dc9d
|
| 3 |
+
size 34754507
|
model/model/language_model/layers/33/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80648b38a8dd1a134404437a14112ecaaa20ecc85778d96ce180e0ba6f27ab65
|
| 3 |
+
size 34759183
|
model/model/language_model/layers/33/mlp/up_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cb98d48488ed306451cbe55797d56a675c27ec620a7875b3a660031f353b1600
|
| 3 |
+
size 34708740
|
model/model/language_model/layers/34/mlp/down_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9093f0ee77a8857759efc88b6028a70e755fa665677dc1f2732f8dae03f1e50e
|
| 3 |
+
size 34743143
|
model/model/language_model/layers/34/mlp/down_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d73a241cb15a8488e012c26e73b67de69b4bc110741d7ecf0fad460b548a674c
|
| 3 |
+
size 34772683
|
model/model/language_model/layers/34/mlp/down_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5b7a00a735af43d862fd98c5c1f65c0366822e0966cf2e75494c1527d11487f
|
| 3 |
+
size 34779894
|
model/model/language_model/layers/34/mlp/down_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf1d0c601d350990f48b906b0279f612c897f627bbeda8243974a762684f7f29
|
| 3 |
+
size 34743023
|
model/model/language_model/layers/34/mlp/gate_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5584fbe3dd770d29ec51b0c6c301c8256f56ddae0cca308b9582e02502c70f3e
|
| 3 |
+
size 34774854
|
model/model/language_model/layers/34/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:432552be0ed575022bc149773a23963507dc00c3eab4991a4f498290d9f3e713
|
| 3 |
+
size 34784113
|
model/model/language_model/layers/34/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a25c0f1bc92f6e614855ff04da3c5072e31efc06d514cc6440d1f45fb6e64839
|
| 3 |
+
size 34790120
|
model/model/language_model/layers/34/mlp/gate_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14d505917c86c2be22914cdbe676cc68542ab70b586fa704ee823252670acfd8
|
| 3 |
+
size 34771118
|
model/model/language_model/layers/34/mlp/up_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:09943b7dd399bc3d087c01e14fdd8774e6d6824adea1fc8bddce0aec3f3774ea
|
| 3 |
+
size 34721407
|
model/model/language_model/layers/34/mlp/up_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4a06d4dbfdbb2af41cf76b74486aac4b465d6ada58c62581ea638f6aa49cd07b
|
| 3 |
+
size 34733741
|
model/model/language_model/layers/34/mlp/up_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:754da28c70e6945602dd33c8c7fb93a962735bdd16c8621dbeb770c3e1666fc3
|
| 3 |
+
size 34740185
|
model/model/language_model/layers/34/mlp/up_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:33861c6c7a1ea2f50ce503043d1bf55962112ef3220d7f9d0f8ced3ebaab111a
|
| 3 |
+
size 34720524
|
model/model/language_model/layers/35/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b87274d5816d4ecfeef83b03fa6d561c46127bc1f9139e6335ef5e09f1eb1cbb
|
| 3 |
+
size 34740880
|
model/model/language_model/layers/35/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5bd7f4ec452b2ee80a62bc61c37bbc2957bfc29d73c0985b230d1967ec3afab
|
| 3 |
+
size 34744346
|
model/model/language_model/layers/35/mlp/up_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6684033a50991637aae65805e2dbe592a04f38ac4f45aa07afa7bf94cb863dba
|
| 3 |
+
size 34710442
|
model/model/language_model/layers/35/self_attn/k_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d95c3c1c8e17f3c57fb62cdae18510532420736553b307c3c60552a2fa53b7a3
|
| 3 |
+
size 2042760
|
model/model/language_model/layers/35/self_attn/k_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f78f1a72b91b6952f88d05f47bf62823396398d5374831aa16425b462d5c3d60
|
| 3 |
+
size 2044286
|
model/model/language_model/layers/35/self_attn/k_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8e32d3208d456e40c04e38ed0e3f7ebe028aebbe68de3140557ea8a7f6284ffc
|
| 3 |
+
size 2044604
|
model/model/language_model/layers/35/self_attn/k_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ddc25d2e71e39bd5dd594d7dc1c21d0ce6bd80701da34b6980737b68cbed9726
|
| 3 |
+
size 2042324
|
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0d450f6a45af1e135d06121d105f5cd3845d714ff353a682a9074773ff764c88
|
| 3 |
+
size 12256456
|
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3a05bb1d81dfa7154f9c61e59d7eb057e51409fd0814d5ddfa0fe1e08ffda2a0
|
| 3 |
+
size 12275797
|
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:66b984ca0ca1e25eb2a07a26d785dfd66c5d9611d00ef6bc01e077445ab0cd72
|
| 3 |
+
size 12277249
|
model/model/language_model/layers/35/self_attn/o_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b9ca6a23c97bc802c09bd13d0df5224c30fed9e2809c2287e005d101f13cdbf
|
| 3 |
+
size 12255955
|
model/model/language_model/layers/35/self_attn/q_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0ed9b7168a413f3769e9b8e4dba202d236e097c1dffb4dc23d03c7a0477190c3
|
| 3 |
+
size 24509881
|
model/model/language_model/layers/35/self_attn/q_proj/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a01e900b55fe7a5248bd0abfdf067c692c80ed3d6402a375f4d97b77c316c39
|
| 3 |
+
size 24489552
|
model/model/language_model/layers/35/self_attn/v_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a06213552aded920ae054527cedaca9f2c2c5abac88c8dabf6f1def6bff10993
|
| 3 |
+
size 2048918
|
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d7c1f9e3c3b02a6aae411aaa89dfca15658870c665204383f0afb57635288cd
|
| 3 |
+
size 20414081
|
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3c026665a77a879701fa9e88f95c4e8424fa101dc22e27b9bd095a0b464cfd61
|
| 3 |
+
size 20418779
|
model/model/language_model/layers/36/linear_attn/in_proj_qkv/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:47994dd26e1a81b2456d6159dca95500f7cc36b0458ed705281acccbfb3dff0b
|
| 3 |
+
size 20405541
|
model/model/language_model/layers/36/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:ab79d698f32d7d4defdec9742c4ae28141a23995252cc860c00b399aef0b6a17
|
| 3 |
+
size 12234106
|
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:91ffa30e7fb53d263903a19929e3f690c3591c371e317cfdfa283a07ffee98f3
|
| 3 |
+
size 12235996
|
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12c66a42dd13daa3012788cb1d2bb8308ba22e611aba088a4967e8c5d2f37c7a
|
| 3 |
+
size 12237051
|
model/model/language_model/layers/36/linear_attn/in_proj_z/kernel/3.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:50a687c7ae2bac500adda097641aeae3a17f7062cbe21d4d755b33f9c6232c2c
|
| 3 |
+
size 12232109
|
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d8c6ecb3cfcb227bf20fcd6306155d09e79378995f95f6d24959a811aeea3f28
|
| 3 |
+
size 12241165
|
model/model/language_model/layers/36/linear_attn/out_proj/kernel/0.1
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f496a41d25e02a670aa6a644ad56151d58baf67909a61566018b1b8fde32dcc7
|
| 3 |
+
size 12250853
|
model/model/language_model/layers/36/mlp/gate_proj/kernel/1.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:eab3b4459f3348fc79fbf8929ab2c43ac599ffc92b867faec49a41a8c50a8ee4
|
| 3 |
+
size 34707096
|
model/model/language_model/layers/36/mlp/gate_proj/kernel/2.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d3882873a16296f9881e6f5992e85e238862cecd42f72cb1f280ceb6d2005f4a
|
| 3 |
+
size 34710061
|
model/model/language_model/layers/37/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:d2f38489d936f54da76959bdd91e63cd3cb9ae36c75041f09066642385e2b870
|
| 3 |
+
size 12242330
|
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.2
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7a68a477e0d85bc381f0d0df4b3508f074712fa746321962f449b6689b155f7
|
| 3 |
+
size 12256510
|
model/model/language_model/layers/37/linear_attn/out_proj/kernel/0.3
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:99d41048fb54aaa1afc3d25e492d580c92721cf79e661c54f0d0312db32f8ebf
|
| 3 |
+
size 12249221
|
model/model/language_model/layers/46/linear_attn/in_proj_qkv/kernel/0.0
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6849b0753bced75251b9fd75a8958bba95a94a583f4af6ae53fc9d1a86e248a3
|
| 3 |
+
size 20408255
|
model/model/language_model/layers/46/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:b29c29e4f116c360948f68fa58674d30522bcd2f9f12165b8a18eed85c00a41b
|
| 3 |
+
size 20420447
|