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 +400 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_18_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.gscales +3 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.planes +3 -0
.gitattributes
CHANGED
|
@@ -797,3 +797,403 @@ deepseek-r1-1.5b-unary4/model_layers_4_self_attn_k_proj_weight.planes filter=lfs
|
|
| 797 |
deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 798 |
deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 799 |
deepseek-r1-1.5b-unary4/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 797 |
deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 798 |
deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 799 |
deepseek-r1-1.5b-unary4/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 800 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 801 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 802 |
+
qwen3-4b-log5-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 803 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 804 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 805 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 806 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 807 |
+
qwen3-4b-log5-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 808 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 809 |
+
qwen3-4b-log5-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 810 |
+
qwen3-4b-log5-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 811 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 812 |
+
qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 813 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 814 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 815 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 816 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 817 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 818 |
+
qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 819 |
+
qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 820 |
+
qwen3-4b-log5-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 821 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 822 |
+
qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 823 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 824 |
+
qwen3-4b-log5-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 825 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 826 |
+
qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 827 |
+
qwen3-4b-log5-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 828 |
+
qwen3-4b-log5-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 829 |
+
qwen3-4b-log5-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 830 |
+
qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 831 |
+
deepseek-r1-1.5b-unary4/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
|
| 832 |
+
qwen3-4b-log5-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 833 |
+
qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 834 |
+
qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 835 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 836 |
+
qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 837 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 838 |
+
qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 839 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 840 |
+
qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 841 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 842 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 843 |
+
qwen3-4b-log5-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 844 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 845 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 846 |
+
qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 847 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 848 |
+
qwen3-4b-log5-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 849 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 850 |
+
qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 851 |
+
qwen3-4b-log5-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 852 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 853 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 854 |
+
qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 855 |
+
qwen3-4b-log5-unary/model_layers_31_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 856 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 857 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 858 |
+
qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 859 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 860 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 861 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 862 |
+
qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 863 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 864 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 865 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 866 |
+
qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 867 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 868 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 869 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 870 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 871 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 872 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 873 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 874 |
+
qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 875 |
+
qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 876 |
+
qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 877 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 878 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 879 |
+
qwen3-4b-log5-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 880 |
+
qwen3-4b-log5-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 881 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 882 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 883 |
+
qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 884 |
+
qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 885 |
+
qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 886 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 887 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 888 |
+
qwen3-4b-log5-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 889 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 890 |
+
qwen3-4b-log5-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 891 |
+
qwen3-4b-log5-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 892 |
+
qwen3-4b-log5-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 893 |
+
qwen3-4b-log5-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 894 |
+
qwen3-4b-log5-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 895 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 896 |
+
qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 897 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 898 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 899 |
+
qwen3-4b-log5-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 900 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 901 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 902 |
+
qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 903 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 904 |
+
qwen3-4b-log5-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 905 |
+
qwen3-4b-log5-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 906 |
+
qwen3-4b-log5-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 907 |
+
qwen3-4b-log5-unary/model_layers_25_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 908 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 909 |
+
qwen3-4b-log5-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 910 |
+
qwen3-4b-log5-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 911 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 912 |
+
qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 913 |
+
qwen3-4b-log5-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 914 |
+
qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 915 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 916 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 917 |
+
qwen3-4b-log5-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 918 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 919 |
+
qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 920 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 921 |
+
qwen3-4b-log5-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 922 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 923 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 924 |
+
qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 925 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 926 |
+
qwen3-4b-log5-unary/model_layers_29_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 927 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 928 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 929 |
+
qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 930 |
+
qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 931 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 932 |
+
qwen3-4b-log5-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 933 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 934 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 935 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 936 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 937 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 938 |
+
qwen3-4b-log5-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 939 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 940 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 941 |
+
qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 942 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 943 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 944 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 945 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 946 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 947 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 948 |
+
qwen3-4b-log5-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 949 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 950 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 951 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 952 |
+
qwen3-4b-log5-unary/model_layers_35_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 953 |
+
qwen3-4b-log5-unary/model_layers_31_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 954 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 955 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 956 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 957 |
+
qwen3-4b-log5-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 958 |
+
qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 959 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 960 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 961 |
+
qwen3-4b-log5-unary/model_layers_30_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 962 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 963 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 964 |
+
qwen3-4b-log5-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 965 |
+
qwen3-4b-log5-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 966 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 967 |
+
qwen3-4b-log5-unary/model_layers_32_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 968 |
+
qwen3-4b-log5-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 969 |
+
qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 970 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 971 |
+
qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 972 |
+
qwen3-4b-log5-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 973 |
+
qwen3-4b-log5-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 974 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 975 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 976 |
+
qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 977 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 978 |
+
qwen3-4b-log5-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 979 |
+
qwen3-4b-log5-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 980 |
+
qwen3-4b-log5-unary/model_layers_33_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 981 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 982 |
+
qwen3-4b-log5-unary/model_layers_33_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 983 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 984 |
+
qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 985 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 986 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 987 |
+
qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 988 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 989 |
+
qwen3-4b-log5-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 990 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 991 |
+
qwen3-4b-log5-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 992 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 993 |
+
qwen3-4b-log5-unary/model_layers_33_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 994 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 995 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 996 |
+
qwen3-4b-log5-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 997 |
+
qwen3-4b-log5-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 998 |
+
qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 999 |
+
qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1000 |
+
qwen3-4b-log5-unary/model_layers_29_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1001 |
+
qwen3-4b-log5-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1002 |
+
qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1003 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1004 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1005 |
+
qwen3-4b-log5-unary/model_layers_14_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1006 |
+
qwen3-4b-log5-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1007 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1008 |
+
qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1009 |
+
qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1010 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1011 |
+
qwen3-4b-log5-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1012 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1013 |
+
qwen3-4b-log5-unary/model_layers_35_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1014 |
+
qwen3-4b-log5-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1015 |
+
qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1016 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1017 |
+
qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1018 |
+
qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1019 |
+
qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1020 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1021 |
+
qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1022 |
+
qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1023 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1024 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1025 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1026 |
+
qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1027 |
+
qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1028 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1029 |
+
qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1030 |
+
qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1031 |
+
qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1032 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1033 |
+
qwen3-4b-log5-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1034 |
+
qwen3-4b-log5-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1035 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1036 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1037 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1038 |
+
qwen3-4b-log5-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1039 |
+
qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1040 |
+
qwen3-4b-log5-unary/model_layers_21_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1041 |
+
qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1042 |
+
qwen3-4b-log5-unary/model_layers_32_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1043 |
+
qwen3-4b-log5-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1044 |
+
qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1045 |
+
qwen3-4b-log5-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1046 |
+
qwen3-4b-log5-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1047 |
+
qwen3-4b-log5-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1048 |
+
qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1049 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1050 |
+
qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1051 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1052 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1053 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1054 |
+
qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1055 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1056 |
+
qwen3-4b-log5-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1057 |
+
qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1058 |
+
qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1059 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1060 |
+
qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1061 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1062 |
+
qwen3-4b-log5-unary/model_layers_31_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1063 |
+
qwen3-4b-log5-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1064 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1065 |
+
qwen3-4b-log5-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1066 |
+
qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1067 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1068 |
+
qwen3-4b-log5-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1069 |
+
qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1070 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1071 |
+
qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1072 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1073 |
+
qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1074 |
+
qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1075 |
+
qwen3-4b-log5-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1076 |
+
qwen3-4b-log5-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1077 |
+
qwen3-4b-log5-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1078 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1079 |
+
qwen3-4b-log5-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1080 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1081 |
+
qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1082 |
+
qwen3-4b-log5-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1083 |
+
qwen3-4b-log5-unary/model_layers_29_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1084 |
+
qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1085 |
+
qwen3-4b-log5-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1086 |
+
qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1087 |
+
qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1088 |
+
qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1089 |
+
qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1090 |
+
qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1091 |
+
qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1092 |
+
qwen3-4b-log5-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1093 |
+
qwen3-4b-log5-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1094 |
+
qwen3-4b-log5-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1095 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1096 |
+
qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1097 |
+
qwen3-4b-log5-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1098 |
+
qwen3-4b-log5-unary/model_layers_34_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1099 |
+
qwen3-4b-log5-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1100 |
+
qwen3-4b-log5-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1101 |
+
qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1102 |
+
qwen3-4b-log5-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1103 |
+
qwen3-4b-log5-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1104 |
+
qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1105 |
+
qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1106 |
+
qwen3-4b-log5-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1107 |
+
qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1108 |
+
qwen3-4b-log5-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1109 |
+
qwen3-4b-log5-unary/model_layers_7_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1110 |
+
qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1111 |
+
qwen3-4b-log5-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1112 |
+
qwen3-4b-log5-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1113 |
+
qwen3-4b-log5-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1114 |
+
qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1115 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1116 |
+
qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1117 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1118 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1119 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1120 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1121 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1122 |
+
deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1123 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1124 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1125 |
+
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1126 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1127 |
+
deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1128 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1129 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1130 |
+
deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1131 |
+
deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1132 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1133 |
+
deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1134 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1135 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1136 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1137 |
+
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1138 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1139 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1140 |
+
deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1141 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1142 |
+
deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1143 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1144 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1145 |
+
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1146 |
+
deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1147 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1148 |
+
deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1149 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1150 |
+
deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1151 |
+
deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1152 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1153 |
+
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1154 |
+
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1155 |
+
deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1156 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1157 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1158 |
+
deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1159 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1160 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1161 |
+
deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1162 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1163 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1164 |
+
deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1165 |
+
deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1166 |
+
deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1167 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1168 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1169 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1170 |
+
deepseek-r1-1.5b-gunary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1171 |
+
deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1172 |
+
deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1173 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1174 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1175 |
+
deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1176 |
+
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1177 |
+
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1178 |
+
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1179 |
+
deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1180 |
+
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1181 |
+
deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1182 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1183 |
+
deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1184 |
+
deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1185 |
+
deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1186 |
+
deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1187 |
+
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1188 |
+
deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1189 |
+
deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1190 |
+
deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1191 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1192 |
+
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 1193 |
+
deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1194 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 1195 |
+
deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text
|
| 1196 |
+
deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.planes 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
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:54f62786480e272b2ed469c552ac304aabbb598108c825d9c9665c7e86777a47
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b49338069c9db0f188c0b6e9b2a9bbb1c3ee94d02d186706f7d297872e2711a7
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a83d28ebe8f492a9158ad1a8a133f5d0e1017c690263f563f08bde04eee9c5db
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:43d9bdf4d1234bacc928a5c169b655f1e1164b25526040091ab94f650804ea66
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:556096531abd03fc5e5f04c6d35b923f99fa220b279f136aea4b8d2af372d579
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e19a35ef06acc8f5d6566c9af77f3dc578890077dd464f46252b7e812f3217c
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:16a44f8cc78acaecf3ce04f9c82ae74c8b981ec9c16ab2fc83b53d970cd02d12
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:dd02eeb3ca3e5e87712fc9a0ab22f0776fc4725b77740493499225d54b5cfb20
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:10efc6f355c61758546a025d5224854654a26a7dc025d2b3223619b5fd6d9437
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9c07a7242f454596ef980d3a493b09e0256f3be1b1eeac073ab967d339067ff0
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a4847d5317087ec5fb48fcbdeed53f33406317164757b57579921c853d4952e9
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:89dcf3fc7b962c525fae4ef008d366bc49a3e047009ba22d3dc43c9a6b84d2fb
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4e806a7cf129ba583e070b3b130586dc8817867227eddc8244a38a4c322dea96
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c5fa0b967ed7ef8ab6e68611ceff0a2509fb8bf9844ea315d628572265e3ba4c
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:74b78534d997cae0ee012f47a780c4ec9731aa9e9967f59d53292b783ece5fa8
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0e9369d1267c574eb177b974c5234e1036cb2cf6a6192440c5c9e91da45d08a4
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9183bd87e537d7e24397454092cb24f0ca9f0380d67a80781b46e8fe64b8bf6e
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f77567267cb678b75a75436084cd6345d32a1fefcadc4ae5a11f4b7908598bec
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cbb5c8ca87dbd7b70c965623a171e81db5514b89442c6ae3028faf3677ce51ce
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea2f382a9a3eb87a5a14022d6247e27552a29c02f980844bad68847a20347ad6
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3636d54b40e62d0ae2d034aa949568ce9b86c7ad14daa17a771f65bf37d76093
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:70f24fab77596535c98d31e186283ab317b45b4f01121b254bea3ce96c420cf9
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0b1d71717a33bae43b6cc287107fa866ebf2d3a053742a709381035b2c234a66
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c3d299280e2d994f2ccbc488be50f2c21ce6eb92acec7dcc45fcb9bf1d3614a2
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:664e41309d4c02a6256a3195cee51f805bbd8e0cd402a128a56f1f4e889d1ed8
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bd675b7630cc6905107d8978b6875c50f17c3adaa2d32eaa0df8506d25d1a297
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e91a1d6f385ad3d88d5e5c53ecf35b89889bf5c3ec372d052f9c744ff2df5150
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:65b662b9a71e1c30f54e9781190dc2c4847527cdecdb022b85b3909d2b4c11cb
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6c60b2568946e4917be427453919b81ab9eb10d065e3c629a2fe71512fedaf0c
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a7057ab1398767efb88fd1695756e64064a78d4fb909c74dde10113e98ea3961
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8da4270e466c8d0be4527cc144f503fb296a5a5707d1049a1f5ebba2fa5cdb10
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:34f6e603eba0d028243475143858f84f483936b40edb059f7591965180d43bf1
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:043ea7daa9281049fa820608b120e4c985a3577629f4e72f6054edc745347496
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:734ce6777ce6133dcba5fbf6b3ac05bf3ff10d3a7c8abc153de7e1a0584c82e8
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8f655d7cdcf1060a1d2ae7f4ea253af59d082f45041a2bbd8071c384bbd18aec
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1571370b85679b6c52d3d6f2ef1b76f2dd7f801b28d65dc1e85b755243c36e6d
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5dc18786161e2b0c95165c34e2acbf2f29eba79e8e9168bcf6e9ce7b89113763
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1067f067d104241cc94d0b8e7bceb2cbdffb74c4d41fe6eb40a9bfb6f5267df5
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d4ff9bd22f2dd85190a685a281007fd84a676f2110e201f70c117f6c2a9fb750
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:12da43a0806d2e61f9672bcad20a1646733789929ee8c1f5cec83f638dd6cd36
|
| 3 |
+
size 12042240
|
deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a6a141b1fe1ce3804b212901c841b08c3ee808dd961b68ae62d0f76a20445476
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:995ee1315098be36de0cc245f5085ecab79c813b8966d152955b480c288f4d1d
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f6b42ce46e2be8289a439a9d67d24600d151efcc389e85a9a5c17f822130b4b8
|
| 3 |
+
size 2064384
|
deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:14201e8f76cba5255cd5b956e5eb8747f1ac83c323bdc1b4f0322ac3fae9e585
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4116492b8ccbf686d2709b6685c8317b39beb150ce05af974a1e8fea983a739f
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a9ea82664a312ba18c7166b1ade4bb403ffc8b252f524cd4094c95a2185f5c68
|
| 3 |
+
size 344064
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.gscales
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e5fc7eda51e80d3d3939b986ade5fb1f06929284b02f2f92604c9669e5e63c3f
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:2de5f2a6748bfae662d5f29cc9974111ade6445151f4ccf652d60c179f5d44f7
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9406e8c7ecd1697faf5397d877ecf33709c03ccdace67ec727695b389eff1534
|
| 3 |
+
size 344064
|