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 +252 -0
- deepseek-r1-1.5b-gunary/model_layers_0_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_0_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_12_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_15_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_18_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_18_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_bias.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.gscales +0 -0
- deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.sign +0 -0
- deepseek-r1-1.5b-gunary/model_layers_1_input_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_1_post_attention_layernorm_weight.fp16 +0 -0
- deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_bias.fp16 +0 -0
.gitattributes
CHANGED
|
@@ -33,3 +33,255 @@ saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 33 |
*.zip filter=lfs diff=lfs merge=lfs -text
|
| 34 |
*.zst filter=lfs diff=lfs merge=lfs -text
|
| 35 |
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
| 36 |
+
deepseek-r1-1.5b-ternary/model_layers_9_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 37 |
+
deepseek-r1-1.5b-ternary/model_layers_22_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 38 |
+
deepseek-r1-1.5b-ternary/model_layers_0_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 39 |
+
deepseek-r1-1.5b-ternary/model_layers_4_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 40 |
+
deepseek-r1-1.5b-ternary/model_layers_12_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 41 |
+
deepseek-r1-1.5b-ternary/model_layers_20_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 42 |
+
deepseek-r1-1.5b-ternary/model_layers_15_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 43 |
+
deepseek-r1-1.5b-ternary/model_layers_1_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 44 |
+
deepseek-r1-1.5b-ternary/model_layers_9_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 45 |
+
deepseek-r1-1.5b-ternary/model_layers_6_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 46 |
+
deepseek-r1-1.5b-ternary/model_layers_4_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 47 |
+
deepseek-r1-1.5b-ternary/model_layers_22_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 48 |
+
deepseek-r1-1.5b-ternary/model_layers_6_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 49 |
+
deepseek-r1-1.5b-ternary/model_layers_6_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 50 |
+
deepseek-r1-1.5b-ternary/model_layers_3_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 51 |
+
deepseek-r1-1.5b-ternary/model_layers_9_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 52 |
+
deepseek-r1-1.5b-ternary/model_layers_16_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text
|
| 53 |
+
deepseek-r1-1.5b-ternary/model_layers_15_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 54 |
+
deepseek-r1-1.5b-ternary/model_layers_23_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 55 |
+
deepseek-r1-1.5b-ternary/model_layers_1_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text
|
| 56 |
+
deepseek-r1-1.5b-packed/model_layers_20_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 57 |
+
deepseek-r1-1.5b-packed/model_layers_15_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 58 |
+
deepseek-r1-1.5b-packed/model_layers_24_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 59 |
+
deepseek-r1-1.5b-packed/model_layers_2_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 60 |
+
deepseek-r1-1.5b-packed/model_layers_22_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 61 |
+
deepseek-r1-1.5b-packed/model_layers_12_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 62 |
+
deepseek-r1-1.5b-packed/model_layers_12_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 63 |
+
deepseek-r1-1.5b-packed/model_layers_21_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 64 |
+
deepseek-r1-1.5b-packed/model_layers_18_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 65 |
+
deepseek-r1-1.5b-packed/model_layers_10_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 66 |
+
deepseek-r1-1.5b-packed/model_layers_16_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 67 |
+
deepseek-r1-1.5b-packed/model_layers_12_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 68 |
+
deepseek-r1-1.5b-packed/model_layers_1_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 69 |
+
deepseek-r1-1.5b-packed/model_layers_16_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 70 |
+
deepseek-r1-1.5b-packed/model_layers_18_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 71 |
+
deepseek-r1-1.5b-packed/model_layers_20_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 72 |
+
deepseek-r1-1.5b-packed/model_layers_12_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 73 |
+
deepseek-r1-1.5b-packed/model_layers_7_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 74 |
+
deepseek-r1-1.5b-packed/model_layers_11_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 75 |
+
deepseek-r1-1.5b-packed/model_layers_12_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 76 |
+
deepseek-r1-1.5b-packed/model_layers_8_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 77 |
+
deepseek-r1-1.5b-packed/model_layers_19_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 78 |
+
deepseek-r1-1.5b-packed/model_layers_23_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 79 |
+
deepseek-r1-1.5b-packed/model_layers_2_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 80 |
+
deepseek-r1-1.5b-packed/model_layers_7_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 81 |
+
deepseek-r1-1.5b-packed/model_layers_0_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 82 |
+
deepseek-r1-1.5b-packed/model_layers_11_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 83 |
+
deepseek-r1-1.5b-packed/model_layers_6_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 84 |
+
deepseek-r1-1.5b-packed/model_layers_10_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 85 |
+
deepseek-r1-1.5b-packed/model_layers_0_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 86 |
+
deepseek-r1-1.5b-packed/model_layers_16_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 87 |
+
deepseek-r1-1.5b-packed/model_layers_23_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 88 |
+
deepseek-r1-1.5b-packed/model_layers_20_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 89 |
+
deepseek-r1-1.5b-packed/model_layers_14_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 90 |
+
deepseek-r1-1.5b-packed/model_layers_14_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 91 |
+
deepseek-r1-1.5b-packed/model_layers_12_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 92 |
+
deepseek-r1-1.5b-packed/model_layers_25_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 93 |
+
deepseek-r1-1.5b-packed/model_layers_9_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 94 |
+
deepseek-r1-1.5b-packed/model_layers_20_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 95 |
+
deepseek-r1-1.5b-packed/model_layers_26_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 96 |
+
deepseek-r1-1.5b-packed/model_layers_5_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 97 |
+
deepseek-r1-1.5b-packed/model_layers_3_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 98 |
+
deepseek-r1-1.5b-packed/model_layers_4_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 99 |
+
deepseek-r1-1.5b-packed/model_layers_26_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 100 |
+
deepseek-r1-1.5b-packed/model_layers_16_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 101 |
+
deepseek-r1-1.5b-packed/model_layers_9_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 102 |
+
deepseek-r1-1.5b-packed/model_layers_25_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 103 |
+
deepseek-r1-1.5b-packed/model_layers_10_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 104 |
+
deepseek-r1-1.5b-packed/model_layers_24_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 105 |
+
deepseek-r1-1.5b-packed/model_layers_19_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 106 |
+
deepseek-r1-1.5b-packed/model_layers_18_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 107 |
+
deepseek-r1-1.5b-packed/model_layers_21_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 108 |
+
deepseek-r1-1.5b-packed/model_layers_15_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 109 |
+
deepseek-r1-1.5b-packed/model_layers_0_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 110 |
+
deepseek-r1-1.5b-packed/model_layers_21_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 111 |
+
deepseek-r1-1.5b-packed/model_layers_24_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 112 |
+
deepseek-r1-1.5b-packed/model_layers_1_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 113 |
+
deepseek-r1-1.5b-packed/model_layers_6_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 114 |
+
deepseek-r1-1.5b-packed/model_layers_17_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 115 |
+
deepseek-r1-1.5b-packed/model_layers_23_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 116 |
+
deepseek-r1-1.5b-packed/model_layers_3_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 117 |
+
deepseek-r1-1.5b-packed/model_layers_22_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 118 |
+
deepseek-r1-1.5b-packed/model_layers_22_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 119 |
+
deepseek-r1-1.5b-packed/model_layers_3_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 120 |
+
deepseek-r1-1.5b-packed/model_layers_24_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 121 |
+
deepseek-r1-1.5b-packed/model_layers_3_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 122 |
+
deepseek-r1-1.5b-packed/model_layers_14_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 123 |
+
deepseek-r1-1.5b-packed/model_layers_23_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 124 |
+
deepseek-r1-1.5b-packed/model_layers_26_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 125 |
+
deepseek-r1-1.5b-packed/model_layers_2_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 126 |
+
deepseek-r1-1.5b-packed/model_layers_26_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 127 |
+
deepseek-r1-1.5b-packed/model_layers_12_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 128 |
+
deepseek-r1-1.5b-packed/model_layers_10_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 129 |
+
deepseek-r1-1.5b-packed/model_layers_16_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 130 |
+
deepseek-r1-1.5b-packed/model_layers_11_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 131 |
+
deepseek-r1-1.5b-packed/model_layers_5_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 132 |
+
deepseek-r1-1.5b-packed/model_layers_21_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 133 |
+
deepseek-r1-1.5b-packed/model_layers_19_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 134 |
+
deepseek-r1-1.5b-packed/model_layers_8_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 135 |
+
deepseek-r1-1.5b-packed/model_layers_16_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 136 |
+
deepseek-r1-1.5b-packed/model_layers_17_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 137 |
+
deepseek-r1-1.5b-packed/model_layers_9_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 138 |
+
deepseek-r1-1.5b-packed/model_layers_11_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 139 |
+
deepseek-r1-1.5b-packed/model_layers_18_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 140 |
+
deepseek-r1-1.5b-packed/model_layers_11_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 141 |
+
deepseek-r1-1.5b-packed/model_layers_1_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 142 |
+
deepseek-r1-1.5b-packed/model_layers_24_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 143 |
+
deepseek-r1-1.5b-packed/model_layers_20_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 144 |
+
deepseek-r1-1.5b-packed/model_layers_4_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 145 |
+
deepseek-r1-1.5b-packed/model_layers_20_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 146 |
+
deepseek-r1-1.5b-packed/model_layers_16_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 147 |
+
deepseek-r1-1.5b-packed/model_layers_5_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 148 |
+
deepseek-r1-1.5b-packed/model_layers_7_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 149 |
+
deepseek-r1-1.5b-packed/model_layers_1_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 150 |
+
deepseek-r1-1.5b-packed/model_layers_3_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 151 |
+
deepseek-r1-1.5b-packed/model_layers_24_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 152 |
+
deepseek-r1-1.5b-packed/model_layers_14_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 153 |
+
deepseek-r1-1.5b-packed/model_layers_26_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 154 |
+
deepseek-r1-1.5b-packed/model_layers_13_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 155 |
+
deepseek-r1-1.5b-packed/model_layers_6_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 156 |
+
deepseek-r1-1.5b-packed/model_layers_13_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 157 |
+
deepseek-r1-1.5b-packed/model_layers_26_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 158 |
+
deepseek-r1-1.5b-packed/model_layers_3_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 159 |
+
deepseek-r1-1.5b-packed/model_layers_18_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 160 |
+
deepseek-r1-1.5b-packed/model_layers_13_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 161 |
+
deepseek-r1-1.5b-packed/model_layers_6_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 162 |
+
deepseek-r1-1.5b-packed/model_layers_10_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 163 |
+
deepseek-r1-1.5b-packed/model_layers_2_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 164 |
+
deepseek-r1-1.5b-packed/model_layers_14_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 165 |
+
deepseek-r1-1.5b-packed/model_layers_19_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 166 |
+
deepseek-r1-1.5b-packed/model_layers_19_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 167 |
+
deepseek-r1-1.5b-packed/model_layers_17_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 168 |
+
deepseek-r1-1.5b-packed/model_layers_11_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 169 |
+
deepseek-r1-1.5b-packed/model_layers_23_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 170 |
+
deepseek-r1-1.5b-packed/model_layers_19_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 171 |
+
deepseek-r1-1.5b-packed/model_layers_0_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 172 |
+
deepseek-r1-1.5b-packed/model_layers_5_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 173 |
+
deepseek-r1-1.5b-packed/model_layers_8_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 174 |
+
deepseek-r1-1.5b-packed/model_layers_9_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 175 |
+
deepseek-r1-1.5b-packed/model_layers_16_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 176 |
+
deepseek-r1-1.5b-packed/model_layers_10_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 177 |
+
deepseek-r1-1.5b-packed/model_layers_16_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 178 |
+
deepseek-r1-1.5b-packed/model_layers_25_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 179 |
+
deepseek-r1-1.5b-packed/model_layers_24_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 180 |
+
deepseek-r1-1.5b-packed/model_layers_20_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 181 |
+
deepseek-r1-1.5b-packed/model_layers_9_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 182 |
+
deepseek-r1-1.5b-packed/model_layers_5_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 183 |
+
deepseek-r1-1.5b-packed/model_layers_10_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 184 |
+
deepseek-r1-1.5b-packed/model_layers_17_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 185 |
+
deepseek-r1-1.5b-packed/model_layers_15_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 186 |
+
deepseek-r1-1.5b-packed/model_layers_1_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 187 |
+
deepseek-r1-1.5b-packed/model_layers_9_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 188 |
+
deepseek-r1-1.5b-packed/model_layers_25_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 189 |
+
deepseek-r1-1.5b-packed/model_layers_9_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 190 |
+
deepseek-r1-1.5b-packed/model_layers_17_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 191 |
+
deepseek-r1-1.5b-packed/model_layers_27_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 192 |
+
deepseek-r1-1.5b-packed/model_layers_3_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 193 |
+
deepseek-r1-1.5b-packed/model_layers_0_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 194 |
+
deepseek-r1-1.5b-packed/model_layers_6_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 195 |
+
deepseek-r1-1.5b-packed/model_layers_0_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 196 |
+
deepseek-r1-1.5b-packed/model_layers_2_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 197 |
+
deepseek-r1-1.5b-packed/model_layers_8_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 198 |
+
deepseek-r1-1.5b-packed/model_layers_0_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 199 |
+
deepseek-r1-1.5b-packed/model_layers_9_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 200 |
+
deepseek-r1-1.5b-packed/model_layers_20_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 201 |
+
deepseek-r1-1.5b-packed/model_layers_4_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 202 |
+
deepseek-r1-1.5b-packed/model_layers_13_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 203 |
+
deepseek-r1-1.5b-packed/model_layers_17_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 204 |
+
deepseek-r1-1.5b-packed/model_layers_21_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 205 |
+
deepseek-r1-1.5b-packed/model_layers_13_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 206 |
+
deepseek-r1-1.5b-packed/model_layers_27_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 207 |
+
deepseek-r1-1.5b-packed/model_layers_23_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 208 |
+
deepseek-r1-1.5b-packed/model_layers_18_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 209 |
+
deepseek-r1-1.5b-packed/model_layers_7_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 210 |
+
deepseek-r1-1.5b-packed/model_layers_11_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 211 |
+
deepseek-r1-1.5b-packed/model_layers_10_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 212 |
+
deepseek-r1-1.5b-packed/model_layers_7_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 213 |
+
deepseek-r1-1.5b-packed/model_layers_23_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 214 |
+
deepseek-r1-1.5b-packed/model_layers_15_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 215 |
+
deepseek-r1-1.5b-packed/model_layers_9_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 216 |
+
deepseek-r1-1.5b-packed/model_layers_22_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 217 |
+
deepseek-r1-1.5b-packed/model_layers_8_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 218 |
+
deepseek-r1-1.5b-packed/model_layers_16_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 219 |
+
deepseek-r1-1.5b-packed/model_layers_21_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 220 |
+
deepseek-r1-1.5b-packed/model_layers_4_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 221 |
+
deepseek-r1-1.5b-packed/model_layers_22_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 222 |
+
deepseek-r1-1.5b-packed/model_layers_14_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 223 |
+
deepseek-r1-1.5b-packed/model_layers_26_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 224 |
+
deepseek-r1-1.5b-packed/model_layers_23_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 225 |
+
deepseek-r1-1.5b-packed/model_layers_25_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 226 |
+
deepseek-r1-1.5b-packed/model_layers_20_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 227 |
+
deepseek-r1-1.5b-packed/model_layers_18_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 228 |
+
deepseek-r1-1.5b-packed/model_layers_20_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 229 |
+
deepseek-r1-1.5b-packed/model_layers_19_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 230 |
+
deepseek-r1-1.5b-packed/model_layers_18_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 231 |
+
deepseek-r1-1.5b-packed/model_layers_18_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 232 |
+
deepseek-r1-1.5b-packed/model_layers_8_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 233 |
+
deepseek-r1-1.5b-packed/model_layers_19_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 234 |
+
deepseek-r1-1.5b-packed/model_layers_13_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 235 |
+
deepseek-r1-1.5b-packed/model_layers_5_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 236 |
+
deepseek-r1-1.5b-packed/model_layers_12_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 237 |
+
deepseek-r1-1.5b-packed/model_layers_12_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 238 |
+
deepseek-r1-1.5b-packed/model_layers_25_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 239 |
+
deepseek-r1-1.5b-packed/model_layers_11_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 240 |
+
deepseek-r1-1.5b-packed/model_layers_15_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 241 |
+
deepseek-r1-1.5b-packed/model_layers_17_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 242 |
+
deepseek-r1-1.5b-packed/model_layers_25_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 243 |
+
deepseek-r1-1.5b-packed/model_layers_22_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 244 |
+
deepseek-r1-1.5b-packed/model_layers_15_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 245 |
+
deepseek-r1-1.5b-packed/model_layers_23_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 246 |
+
deepseek-r1-1.5b-packed/model_layers_22_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 247 |
+
deepseek-r1-1.5b-packed/model_layers_13_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 248 |
+
deepseek-r1-1.5b-packed/model_layers_2_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 249 |
+
deepseek-r1-1.5b-packed/model_layers_20_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 250 |
+
deepseek-r1-1.5b-packed/model_layers_1_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 251 |
+
deepseek-r1-1.5b-packed/model_layers_12_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 252 |
+
deepseek-r1-1.5b-packed/model_layers_17_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 253 |
+
deepseek-r1-1.5b-packed/model_layers_13_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 254 |
+
deepseek-r1-1.5b-packed/model_layers_25_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 255 |
+
deepseek-r1-1.5b-packed/model_layers_7_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 256 |
+
deepseek-r1-1.5b-packed/model_layers_23_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 257 |
+
deepseek-r1-1.5b-packed/model_layers_5_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 258 |
+
deepseek-r1-1.5b-packed/model_layers_7_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 259 |
+
deepseek-r1-1.5b-packed/model_layers_27_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 260 |
+
deepseek-r1-1.5b-packed/model_layers_14_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 261 |
+
deepseek-r1-1.5b-packed/model_layers_6_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 262 |
+
deepseek-r1-1.5b-packed/model_layers_15_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 263 |
+
deepseek-r1-1.5b-packed/model_layers_7_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 264 |
+
deepseek-r1-1.5b-packed/model_layers_1_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 265 |
+
deepseek-r1-1.5b-packed/model_layers_24_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 266 |
+
deepseek-r1-1.5b-packed/model_layers_13_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 267 |
+
deepseek-r1-1.5b-packed/model_layers_10_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 268 |
+
deepseek-r1-1.5b-packed/model_layers_6_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 269 |
+
deepseek-r1-1.5b-packed/model_layers_15_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 270 |
+
deepseek-r1-1.5b-packed/model_layers_4_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 271 |
+
deepseek-r1-1.5b-packed/model_layers_6_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 272 |
+
deepseek-r1-1.5b-packed/model_layers_25_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 273 |
+
deepseek-r1-1.5b-packed/model_layers_22_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 274 |
+
deepseek-r1-1.5b-packed/model_layers_24_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 275 |
+
deepseek-r1-1.5b-packed/model_layers_17_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 276 |
+
deepseek-r1-1.5b-packed/model_layers_26_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 277 |
+
deepseek-r1-1.5b-packed/model_layers_4_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 278 |
+
deepseek-r1-1.5b-packed/model_layers_6_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 279 |
+
deepseek-r1-1.5b-packed/model_layers_6_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 280 |
+
deepseek-r1-1.5b-packed/model_layers_17_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 281 |
+
deepseek-r1-1.5b-packed/model_layers_1_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 282 |
+
deepseek-r1-1.5b-packed/model_layers_11_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 283 |
+
deepseek-r1-1.5b-packed/model_layers_21_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 284 |
+
deepseek-r1-1.5b-packed/model_layers_21_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 285 |
+
deepseek-r1-1.5b-packed/model_layers_6_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
| 286 |
+
deepseek-r1-1.5b-packed/model_layers_1_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text
|
| 287 |
+
deepseek-r1-1.5b-packed/model_layers_14_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text
|
deepseek-r1-1.5b-gunary/model_layers_0_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_0_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_12_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_15_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_18_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_18_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_bias.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.gscales
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.sign
ADDED
|
Binary file (49.2 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_1_input_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_1_post_attention_layernorm_weight.fp16
ADDED
|
Binary file (3.07 kB). View file
|
|
|
deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_bias.fp16
ADDED
|
Binary file (512 Bytes). View file
|
|
|