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 +160 -0
- deepseek-r1-1.5b-unary4/model_layers_0_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_0_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_0_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_0_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_10_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_10_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_10_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_10_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_11_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_12_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_13_self_attn_v_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_14_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_14_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_self_attn_k_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.planes +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.sign +3 -0
- deepseek-r1-1.5b-unary4/model_layers_15_self_attn_v_proj_weight.planes +3 -0
.gitattributes
CHANGED
|
@@ -637,3 +637,163 @@ deepseek-r1-1.5b-unary4/model_layers_22_self_attn_v_proj_weight.planes filter=lf
|
|
| 637 |
deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 638 |
deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 639 |
deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 637 |
deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 638 |
deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 639 |
deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 640 |
+
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 641 |
+
deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 642 |
+
deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 643 |
+
deepseek-r1-1.5b-unary4/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 644 |
+
deepseek-r1-1.5b-unary4/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 645 |
+
deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 646 |
+
deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 647 |
+
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 648 |
+
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 649 |
+
deepseek-r1-1.5b-unary4/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 650 |
+
deepseek-r1-1.5b-unary4/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 651 |
+
deepseek-r1-1.5b-unary4/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 652 |
+
deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 653 |
+
deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 654 |
+
deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 655 |
+
deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 656 |
+
deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 657 |
+
deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 658 |
+
deepseek-r1-1.5b-unary4/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 659 |
+
deepseek-r1-1.5b-unary4/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 660 |
+
deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 661 |
+
deepseek-r1-1.5b-unary4/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 662 |
+
deepseek-r1-1.5b-unary4/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 663 |
+
deepseek-r1-1.5b-unary4/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 664 |
+
deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 665 |
+
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 666 |
+
deepseek-r1-1.5b-unary4/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 667 |
+
deepseek-r1-1.5b-unary4/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 668 |
+
deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 669 |
+
deepseek-r1-1.5b-unary4/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 670 |
+
deepseek-r1-1.5b-unary4/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 671 |
+
deepseek-r1-1.5b-unary4/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 672 |
+
deepseek-r1-1.5b-unary4/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 673 |
+
deepseek-r1-1.5b-unary4/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 674 |
+
deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 675 |
+
deepseek-r1-1.5b-unary4/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 676 |
+
deepseek-r1-1.5b-unary4/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 677 |
+
deepseek-r1-1.5b-unary4/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 678 |
+
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 679 |
+
deepseek-r1-1.5b-unary4/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 680 |
+
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 681 |
+
deepseek-r1-1.5b-unary4/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 682 |
+
deepseek-r1-1.5b-unary4/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 683 |
+
deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 684 |
+
deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 685 |
+
deepseek-r1-1.5b-unary4/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 686 |
+
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 687 |
+
deepseek-r1-1.5b-unary4/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 688 |
+
deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 689 |
+
deepseek-r1-1.5b-unary4/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 690 |
+
deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 691 |
+
deepseek-r1-1.5b-unary4/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 692 |
+
deepseek-r1-1.5b-unary4/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 693 |
+
deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 694 |
+
deepseek-r1-1.5b-unary4/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 695 |
+
deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 696 |
+
deepseek-r1-1.5b-unary4/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 697 |
+
deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 698 |
+
deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 699 |
+
deepseek-r1-1.5b-unary4/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 700 |
+
deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 701 |
+
deepseek-r1-1.5b-unary4/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 702 |
+
deepseek-r1-1.5b-unary4/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 703 |
+
deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 704 |
+
deepseek-r1-1.5b-unary4/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 705 |
+
deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 706 |
+
deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 707 |
+
deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 708 |
+
deepseek-r1-1.5b-unary4/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 709 |
+
deepseek-r1-1.5b-unary4/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 710 |
+
deepseek-r1-1.5b-unary4/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 711 |
+
deepseek-r1-1.5b-unary4/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 712 |
+
deepseek-r1-1.5b-unary4/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 713 |
+
deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 714 |
+
deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 715 |
+
deepseek-r1-1.5b-unary4/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 716 |
+
deepseek-r1-1.5b-unary4/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 717 |
+
deepseek-r1-1.5b-unary4/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 718 |
+
deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 719 |
+
deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 720 |
+
deepseek-r1-1.5b-unary4/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 721 |
+
deepseek-r1-1.5b-unary4/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 722 |
+
deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 723 |
+
deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 724 |
+
deepseek-r1-1.5b-unary4/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 725 |
+
deepseek-r1-1.5b-unary4/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 726 |
+
deepseek-r1-1.5b-unary4/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 727 |
+
deepseek-r1-1.5b-unary4/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 728 |
+
deepseek-r1-1.5b-unary4/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 729 |
+
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 730 |
+
deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 731 |
+
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 732 |
+
deepseek-r1-1.5b-unary4/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 733 |
+
deepseek-r1-1.5b-unary4/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 734 |
+
deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 735 |
+
deepseek-r1-1.5b-unary4/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 736 |
+
deepseek-r1-1.5b-unary4/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 737 |
+
deepseek-r1-1.5b-unary4/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 738 |
+
deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 739 |
+
deepseek-r1-1.5b-unary4/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 740 |
+
deepseek-r1-1.5b-unary4/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 741 |
+
deepseek-r1-1.5b-unary4/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 742 |
+
deepseek-r1-1.5b-unary4/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 743 |
+
deepseek-r1-1.5b-unary4/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 744 |
+
deepseek-r1-1.5b-unary4/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 745 |
+
deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 746 |
+
deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 747 |
+
deepseek-r1-1.5b-unary4/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 748 |
+
deepseek-r1-1.5b-unary4/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 749 |
+
deepseek-r1-1.5b-unary4/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 750 |
+
deepseek-r1-1.5b-unary4/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 751 |
+
deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 752 |
+
deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 753 |
+
deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 754 |
+
deepseek-r1-1.5b-unary4/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 755 |
+
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 756 |
+
deepseek-r1-1.5b-unary4/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 757 |
+
deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 758 |
+
deepseek-r1-1.5b-unary4/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 759 |
+
deepseek-r1-1.5b-unary4/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 760 |
+
deepseek-r1-1.5b-unary4/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 761 |
+
deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 762 |
+
deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 763 |
+
deepseek-r1-1.5b-unary4/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 764 |
+
deepseek-r1-1.5b-unary4/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 765 |
+
deepseek-r1-1.5b-unary4/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 766 |
+
deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 767 |
+
deepseek-r1-1.5b-unary4/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 768 |
+
deepseek-r1-1.5b-unary4/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 769 |
+
deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 770 |
+
deepseek-r1-1.5b-unary4/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 771 |
+
deepseek-r1-1.5b-unary4/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 772 |
+
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 773 |
+
deepseek-r1-1.5b-unary4/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 774 |
+
deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 775 |
+
deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 776 |
+
deepseek-r1-1.5b-unary4/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 777 |
+
deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 778 |
+
deepseek-r1-1.5b-unary4/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 779 |
+
deepseek-r1-1.5b-unary4/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 780 |
+
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 781 |
+
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 782 |
+
deepseek-r1-1.5b-unary4/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 783 |
+
deepseek-r1-1.5b-unary4/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 784 |
+
deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 785 |
+
deepseek-r1-1.5b-unary4/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 786 |
+
deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 787 |
+
deepseek-r1-1.5b-unary4/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 788 |
+
deepseek-r1-1.5b-unary4/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 789 |
+
deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 790 |
+
deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 791 |
+
deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 792 |
+
deepseek-r1-1.5b-unary4/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 793 |
+
deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 794 |
+
deepseek-r1-1.5b-unary4/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
|
| 795 |
+
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
|
| 796 |
+
deepseek-r1-1.5b-unary4/model_layers_4_self_attn_k_proj_weight.planes 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
|
deepseek-r1-1.5b-unary4/model_layers_0_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa94b58beb0bf8adb0bc8d39f8759491a5a6b3f176c7412970ce55355a0dd1eb
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/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 sha256:857224fb95d2540934f18e7300d711e018b3dcf113591e1321c06f4258cb12f0
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/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-unary4/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:b27e73cf0f5f5912b11c3b8a2373ebef8b8e67a690c34ac5565941d02ac567b0
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/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:f53f83594c6850d67064cfcb38e7ee64ecacd8bb665a32fff41a7c38d6c787e1
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/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-unary4/model_layers_10_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4774a75c6515de3177e286d22d948777c4c78b1cba28c86393a760f3b30d4f8a
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/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 sha256:5303be2ea3d388e414f18e13cde77013753c3899fe6edd697a695a2003b231c2
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/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-unary4/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 sha256:1dc09c6a4f16a82e36b3efcd5c89d9950359c3d6dc7f8620649bb682ff3a483c
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/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 sha256:8abf5343f513d54c98bc5542c8abf0dec557d6f9fdb60a7377bee7af183ed1a9
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/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-unary4/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-unary4/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 sha256:91ca7913f4d4daba5dbe6a2282cd8f8c022c992f381a2e4f587014f350e6be45
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/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-unary4/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-unary4/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-unary4/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:d1a6ff0c0a5ef27a1a4555ec6ad44c4a63c4d03112961ca830f93ae06eecc7f7
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a377c5b8d79227e31d6ed9baf7f97edd69ab8501e07aa7cce5229192c2e41a8
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/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-unary4/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:ac26d0f8d18ed6d0c3fe742dff6f0f6108ff35cab28cd8e090e5cdecfa989388
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3217b5edb53900b88a21b72534fa586628816ac7e456dbdf9cd853bda8336d9f
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fa8874205a1141bacaae9fdcf35ac12c56211a602ebefcde5e571e9429da90d4
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-unary4/model_layers_12_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:59ea0c1e1fff9039f309d8fb6fcb4a0a3e1bf6e0b654aedfd69f9e4779666602
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b19b277401a0cbc2723d6fc65f8c1d4765b0a03aeeb190adb422769425e8f5b3
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ac99282038cf8cd8e834990e63fbecfca747e61ea02130e4b88ba39c57ee625f
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:658a3e7cfbbbc9864d5a25f76433fea533f8675ec8b145d76dd1f0ee770a0947
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:cff4b70c3b221a7d0855b311d1358611893ea1f455ad773798b07e2b5860a1b9
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8c52f49f7109f6b3b8fa48d71e2d0b1c3a6934eff0e61b5b613e10aaa047e706
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:94843ca28be62ce519030003fb00c05f190531028b570d188f0202642bba3060
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f327cc707dc55c907d977eb0e379e910794574fb36268752913fc042a383b8a9
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5e99fcf7ac870047d47d0c8d8e9410e91e7983a800dea53e3d764fa8a52f837c
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/model_layers_13_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a97a54886af2e995d3f93945a65067ae6d6da27fde52d273912743901a03fcaa
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4c83cb5a88b3300dec9bedff5b81c980a47652ae26afc602560199012eb3c77e
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c6a62b3e005442b9ac9a51a505347398cd9a43d80b5bedf204ae184f08a8c715
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_14_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1ad5ac7a001aad2ba4ff8666731b7b197faf8ec964894eac5cf39ea59c9eb07d
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_14_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7dfc0d17810c2240928b2d31fa07d24fc163f72b4557b06851903ca17fa8a1e9
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9ab51db9b7c598f9dbfbf25f941a0115e5bea9799b9cf3db8d837cb60156687c
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95a32faef3e164c23a3222d470186c15bc31aa5a84f2e7b8e9f546cad03aa5f8
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b684bcc0c65183e127d15e995f38140b7c7fa34626ffbdf52377bfd192205a9e
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:37eaf4b08800fc8155b2341202a8d45e8e98a50d65e8a58fe0ce8052d0828f63
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9f94a7a6c53e6df8e0ef8e8bd1211637f8f40f597baa134c82fa904b4c69faf8
|
| 3 |
+
size 6881280
|
deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5206a02260028ee28fbde6edf9df24199656473b0a98f2b038b7fc841608e572
|
| 3 |
+
size 1720320
|
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_k_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ca749add2e918b0fe50d7447cbf4239643d036af4172199c71c24e7acc9f43de
|
| 3 |
+
size 196608
|
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:991adbb977f284d68a1d8677e10e13fcab2295e549095743f5022b426c6b20dd
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a564f99a29539779b4e31ec8e2238c03ccace4c568b8495bd5028f5fc08e9416
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:176f0daff6ca09d4537c37b0e2c3f2bdce26ad312d47035c2eca74c9aa14ccac
|
| 3 |
+
size 1179648
|
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.sign
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:948dd3df371302f40faa36ab26de7f6b12e1bc3acb9bb0e7b6c11be8ffce8b73
|
| 3 |
+
size 294912
|
deepseek-r1-1.5b-unary4/model_layers_15_self_attn_v_proj_weight.planes
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0c72becc9c81e37613cbedddd79303bdf7d08f6e76c96aaa9948b6f21af1effc
|
| 3 |
+
size 196608
|