Add files using upload-large-folder tool
Browse filesThis view is limited to 50 files because it contains too many changes.
See raw diff
- .gitattributes +600 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales +3 -0
.gitattributes
CHANGED
|
@@ -1197,3 +1197,603 @@ deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.planes filter=lf
|
|
| 1197 |
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1198 |
deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1199 |
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1197 |
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1198 |
deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1199 |
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1200 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1201 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1202 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1203 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1204 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1205 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1206 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1207 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1208 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1209 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1210 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1211 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1212 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1213 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1214 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1215 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1216 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1217 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1218 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1219 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1220 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1221 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1222 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1223 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1224 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1225 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1226 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1227 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1228 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1229 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1230 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1231 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1232 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1233 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1234 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1235 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1236 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1237 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1238 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1239 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1240 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1241 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1242 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1243 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1244 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1245 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1246 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1247 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1248 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1249 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1250 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1251 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1252 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1253 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1254 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1255 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1256 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1257 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1258 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1259 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1260 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1261 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1262 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1263 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1264 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1265 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1266 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1267 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1268 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1269 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1270 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1271 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1272 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1273 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1274 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1275 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1276 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1277 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1278 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1279 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1280 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1281 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1282 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1283 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1284 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1285 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1286 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1287 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1288 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1289 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1290 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1291 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1292 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1293 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1294 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1295 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1296 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1297 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1298 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1299 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1300 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1301 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1302 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1303 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1304 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1305 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1306 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1307 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1308 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1309 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1310 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1311 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1312 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1313 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1314 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1315 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1316 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1317 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1318 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1319 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1320 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1321 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1322 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1323 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1324 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1325 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1326 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1327 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1328 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1329 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1330 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1331 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1332 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1333 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1334 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1335 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1336 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1337 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1338 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1339 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1340 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1341 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1342 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1343 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1344 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1345 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1346 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1347 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1348 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1349 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1350 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1351 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1352 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1353 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1354 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1355 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1356 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1357 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1358 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1359 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1360 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1361 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1362 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1363 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1364 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1365 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1366 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1367 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1368 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1369 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1370 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1371 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1372 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1373 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1374 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1375 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1376 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1377 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1378 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1379 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1380 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1381 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1382 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1383 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1384 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1385 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1386 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1387 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1388 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1389 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1390 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1391 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1392 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1393 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1394 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1395 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1396 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1397 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1398 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1399 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1400 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1401 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1402 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1403 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1404 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1405 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1406 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1407 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1408 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1409 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1410 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1411 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1412 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1413 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1414 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1415 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1416 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1417 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1418 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1419 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1420 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1421 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1422 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1423 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1424 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1425 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1426 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1427 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1428 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1429 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1430 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1431 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1432 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1433 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1434 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1435 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1436 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1437 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1438 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1439 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1440 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1441 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1442 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1443 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1444 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1445 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1446 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1447 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1448 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1449 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1450 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1451 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1452 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1453 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1454 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1455 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1456 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1457 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1458 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1459 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1460 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1461 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1462 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1463 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1464 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1465 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1466 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1467 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1468 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1469 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1470 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1471 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1472 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1473 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1474 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1475 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1476 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1477 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1478 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1479 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1480 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1481 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1482 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1483 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1484 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1485 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1486 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1487 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1488 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1489 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1490 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1491 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1492 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1493 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1494 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1495 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1496 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1497 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1498 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1499 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1500 |
+
qwen3-4b-log5-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 1501 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1502 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1503 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1504 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1505 |
+
deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1506 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1507 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1508 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1509 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1510 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1511 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1512 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1513 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1514 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1515 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1516 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1517 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1518 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1519 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1520 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1521 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1522 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1523 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1524 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1525 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1526 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1527 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1528 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1529 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1530 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1531 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1532 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1533 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1534 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1535 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1536 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1537 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1538 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1539 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1540 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1541 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1542 |
+
deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1543 |
+
deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1544 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1545 |
+
deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1546 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1547 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1548 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1549 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1550 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1551 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1552 |
+
deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1553 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1554 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1555 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1556 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1557 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1558 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1559 |
+
deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1560 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1561 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1562 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1563 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1564 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1565 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1566 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1567 |
+
deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1568 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1569 |
+
deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1570 |
+
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1571 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1572 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1573 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1574 |
+
deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1575 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1576 |
+
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1577 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1578 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1579 |
+
deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1580 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1581 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1582 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1583 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1584 |
+
deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1585 |
+
deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1586 |
+
deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1587 |
+
deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1588 |
+
deepseek-r1-1.5b-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1589 |
+
deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1590 |
+
deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1591 |
+
deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1592 |
+
deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1593 |
+
deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1594 |
+
deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1595 |
+
deepseek-r1-1.5b-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1596 |
+
deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1597 |
+
deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1598 |
+
deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1599 |
+
deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1600 |
+
deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1601 |
+
deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1602 |
+
deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1603 |
+
deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1604 |
+
deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1605 |
+
deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1606 |
+
deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1607 |
+
deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1608 |
+
deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1609 |
+
deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1610 |
+
deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1611 |
+
deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1612 |
+
deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1613 |
+
deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1614 |
+
deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1615 |
+
deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1616 |
+
deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1617 |
+
deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1618 |
+
deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1619 |
+
deepseek-r1-1.5b-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1620 |
+
deepseek-r1-1.5b-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1621 |
+
deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1622 |
+
deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1623 |
+
deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1624 |
+
deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1625 |
+
deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1626 |
+
deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1627 |
+
deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1628 |
+
deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1629 |
+
deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1630 |
+
deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1631 |
+
deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1632 |
+
deepseek-r1-1.5b-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1633 |
+
deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1634 |
+
deepseek-r1-1.5b-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1635 |
+
deepseek-r1-1.5b-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1636 |
+
deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1637 |
+
deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1638 |
+
deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1639 |
+
deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1640 |
+
deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1641 |
+
deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1642 |
+
deepseek-r1-1.5b-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1643 |
+
deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1644 |
+
deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1645 |
+
deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1646 |
+
deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1647 |
+
deepseek-r1-1.5b-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1648 |
+
deepseek-r1-1.5b-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1649 |
+
deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1650 |
+
deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1651 |
+
deepseek-r1-1.5b-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1652 |
+
deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1653 |
+
deepseek-r1-1.5b-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1654 |
+
deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1655 |
+
deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1656 |
+
deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1657 |
+
deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1658 |
+
deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1659 |
+
deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1660 |
+
deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1661 |
+
deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1662 |
+
deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1663 |
+
deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1664 |
+
deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1665 |
+
deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1666 |
+
deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1667 |
+
deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1668 |
+
deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1669 |
+
deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1670 |
+
deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1671 |
+
deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1672 |
+
deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1673 |
+
deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1674 |
+
deepseek-r1-1.5b-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1675 |
+
deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1676 |
+
deepseek-r1-1.5b-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1677 |
+
deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1678 |
+
deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1679 |
+
deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1680 |
+
deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1681 |
+
deepseek-r1-1.5b-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1682 |
+
deepseek-r1-1.5b-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1683 |
+
deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1684 |
+
deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1685 |
+
deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1686 |
+
deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1687 |
+
deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1688 |
+
deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1689 |
+
deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1690 |
+
deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1691 |
+
deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1692 |
+
deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1693 |
+
deepseek-r1-1.5b-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1694 |
+
deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1695 |
+
deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1696 |
+
deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1697 |
+
deepseek-r1-1.5b-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1698 |
+
deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1699 |
+
deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1700 |
+
deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1701 |
+
deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1702 |
+
deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1703 |
+
deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1704 |
+
deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1705 |
+
deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1706 |
+
deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1707 |
+
deepseek-r1-1.5b-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1708 |
+
deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1709 |
+
deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1710 |
+
deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1711 |
+
deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1712 |
+
deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1713 |
+
deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1714 |
+
deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1715 |
+
deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1716 |
+
deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1717 |
+
deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1718 |
+
deepseek-r1-1.5b-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1719 |
+
deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1720 |
+
deepseek-r1-1.5b-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1721 |
+
deepseek-r1-1.5b-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1722 |
+
deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1723 |
+
deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1724 |
+
deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1725 |
+
deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1726 |
+
deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1727 |
+
deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1728 |
+
deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1729 |
+
deepseek-r1-1.5b-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1730 |
+
deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1731 |
+
deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1732 |
+
deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1733 |
+
deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1734 |
+
deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1735 |
+
deepseek-r1-1.5b-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1736 |
+
deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1737 |
+
deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1738 |
+
deepseek-r1-1.5b-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1739 |
+
deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1740 |
+
deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1741 |
+
deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1742 |
+
deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1743 |
+
deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1744 |
+
deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1745 |
+
deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1746 |
+
deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1747 |
+
deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1748 |
+
deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1749 |
+
deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1750 |
+
deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1751 |
+
deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1752 |
+
deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1753 |
+
deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1754 |
+
deepseek-r1-1.5b-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1755 |
+
deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1756 |
+
deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1757 |
+
qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1758 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1759 |
+
qwen3-4b-proper-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 1760 |
+
qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1761 |
+
qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1762 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1763 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1764 |
+
qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1765 |
+
qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1766 |
+
qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1767 |
+
qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1768 |
+
qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1769 |
+
qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1770 |
+
qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1771 |
+
qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1772 |
+
qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1773 |
+
qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1774 |
+
qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1775 |
+
qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1776 |
+
qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1777 |
+
qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1778 |
+
qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1779 |
+
qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1780 |
+
qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1781 |
+
qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1782 |
+
qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1783 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1784 |
+
qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1785 |
+
qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1786 |
+
deepseek-r1-1.5b-unary/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 1787 |
+
qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1788 |
+
qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1789 |
+
qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1790 |
+
qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1791 |
+
qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1792 |
+
qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1793 |
+
qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1794 |
+
qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1795 |
+
qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1796 |
+
qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1797 |
+
qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1798 |
+
qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1799 |
+
qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:41a565cf4ad6caad5784cc2b245cf3ebe43e6833846a33aa8a408234f9fa9250
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aebf634fa7fd1d7a743ad203c482187cbff012f446f1a91c118c54c133c4db30
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2cf601ab6062858b266017e3ccc33f77bb1a6560510ddb28d0bddd9822adbd0b
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:148eb6d49ddd155343e2e5921194591d3ef9637e510057975f706834b7f40290
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43b1f543227944a1af2750e991457b30cb7188988bc96d74d0a5dd89facf6877
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:594cd7fc161e3d0d781837d5f1f775a4adbd2aba450101511495d7d359b0bc69
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:befb3203ab2e2fb0d225ef5ee3023d6140ca7efe07460d726eb6d01753099e38
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:afa7c60db5e54d8009750dd241125670907a01f6b0741fecf14e3983914efbbe
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:309d57ade0f91f24b5103d9ecbd792df958ee7c78a00cce46a026eb9ee5eeb44
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a26bc402bc8fd77dfc2e51d325de3fd516759548c5fbfa38094e48dd6c3b408d
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ff9e0f47cfa701c1f6755e706e0cb7cb569e45ad33d2f980eba76fa1bded9145
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfaf77c3d0ebd2633fe22d13760b0e93d8bf50d828291d46946a010a38c467fe
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15e36fc84052edd625ec45b7aaad2357970df7203632ee44d485b763234589ff
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2c5430535790e7ee20be30386c6fa4478877dc3885dae5ad930fb9c09a1eeedf
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bfd9fb905b7a7aa7317c2d7222028f73ae408c01f6be0bbafae64b2aad6debc8
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4f08039962b28fb5a0bcbe724e0936cfb36f9ef610f9317498148829ca519bed
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6141cb87f1e38f8cf5d667a05694a76b7c109a2d453cac853664ebeac587545
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:137cc07609c4da4aacd304b4fbb93a179102e1f1a78384d3e4f87c40eabb4810
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a15ab382ddd34d8b47eaee74a02ce12aff375399b7c23b8b595179a76b48a717
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c8d38e33a29916b3a384d78f3154474f9b47aa396ce1f0b4ab1c44518164ce8
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8b67625dec70cfd7aeb284a41a98bb2f8cd198209a63a8ee73be4d7af2f223de
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fe42ad280bffdb73f427b1fcb4601b4c336923d9c34223edcbd271ce82dd90b
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d01eace59e54e0e59dbd31c6ec530e16b5f16cd5a291bce1d09a572851fec1de
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:818ace90bc281478fab736c6f8ad713bde8edc876c40441e8e87786526e99d75
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b07cb8f37f8c3fb5f800b008ee48cc27f089db360aa642d7498bc09b8314e21c
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2422715d9cb42eaefaff21120cfde70189525f51f0f51971cc5e950f1bdc48b2
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2ed8d2ccba78d3a4c3c05e6c3ace1bd5eda7f340ed9a83b911002892e2c722eb
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:45d86aaad8d2251a7d22ceaed7ceaf3fdd11acbad65f89fec69e73ba2cf2de05
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b7a5f3a1c4f5b00d240b49aefc7889546755e6776dec3abec018307942480c7
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6fd172fab1208267ae2028ee008aaa7a330a6f9d89c86a67cbe6ec83e2addd4
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7896dbc98b38bceecad1a8224f2e390f82f69aa6e91ac2547581ca0a0cd18e52
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1d611b70c73fe8e6eba72a5ba82b60fd569b34ceb4e7293ddc306bcbd89e6b31
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:26ebaf3de7a21e5d9522bda710cce50c67f6dd55bf67a743dee91c8b5ae8701e
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:60aa5f439af1750b697977171496e97a96c845dd439232a9a82e60e6ddb6d45c
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cec6fcfdda1dfa8d756124998f159ccb939ae0620c1f7e26b08d6157146dc65c
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f33b24f2a78abbf21cbfbf2bc2d42a38cf7c581a3ebeb6a55839010b666c4e54
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dce4c7e52b4e6c2a2018b23aafe37204e13dae6f9f1294aa3ef82ada72b30479
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:529f227fe6dcc789d5e630591de08f934b14595c485810502b41fac46cfe5f9e
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c14b6d3acea03c311f93e75fefb892326fc1dbe8504efa50e0ab1d522dd862e9
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:24e315087197a243bb73095a1798240e0207e21b333afae58414f0854ca6bb86
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7c836480f99d47c2adf0b21e043d62a6155dee5954123aa932b8476ff5cea8e
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e37e732f01681926e9d322ca01b9ad55f72e1c0f4f2e9f448ad6e6780d306a63
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c9b44cebdb1661b1457a9cf2bca5e630520bbdfc9b7176ce7704b726b2524981
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1457d0402e211b3ace67d73e6557b16c2bb570384bcf80a736957f6602646e90
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:be7dbfba76b7cfcb74c3a97c77fecb97f430ba4a3d2b75990e8ba1acdfb00878
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:254cc5a48dfce816b905ccdbbe19316fa485986612269f5de5167ea1547d6b9a
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5bc2c1c7c10e5c3ad3ba154e41f9165188f1e00e96a529deee71f4b231548698
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b99c13197a9fd4d1233f95ba7aeaff88e06a93d91c95bb771fda4f56567a3cf2
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5667d001614e6a4be5333becf2ddb67a2622837264daa78b232e442005310145
|
| 3 |
+
size 294912
|