diff --git a/.gitattributes b/.gitattributes index 5c4afd7258970e0d19244a833a39029e96acc76a..5bde1802e77137a4c0abb7c23494c7594cc8830e 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1197,3 +1197,603 @@ deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.planes filter=lf deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text 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_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +qwen3-4b-log5-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-proper-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..421c0322249af93da74fbc48d3e41a9c7850122c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a565cf4ad6caad5784cc2b245cf3ebe43e6833846a33aa8a408234f9fa9250 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cf34e7cfc6ab98b3387b9bbe32a3adea33b96bf7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aebf634fa7fd1d7a743ad203c482187cbff012f446f1a91c118c54c133c4db30 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..97c721e54a951aa8031e3d0665a92a9b47cba088 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf601ab6062858b266017e3ccc33f77bb1a6560510ddb28d0bddd9822adbd0b +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..cd591fa05bdeb9543e3229b0592cfe5ab88045b3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:148eb6d49ddd155343e2e5921194591d3ef9637e510057975f706834b7f40290 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad057ec33226dd92818e0221690cfab99a2f7ce5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b1f543227944a1af2750e991457b30cb7188988bc96d74d0a5dd89facf6877 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..d335987944a8c64b75537bc94626d3dbcc927eb3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:594cd7fc161e3d0d781837d5f1f775a4adbd2aba450101511495d7d359b0bc69 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..14c40aea0edaa380f0963f120eaf5b425111bbcb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:befb3203ab2e2fb0d225ef5ee3023d6140ca7efe07460d726eb6d01753099e38 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fa5c3f4361129e89d21fe2ecaff339213555bc39 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa7c60db5e54d8009750dd241125670907a01f6b0741fecf14e3983914efbbe +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..168c85367f09431380d0ac5d63d1c9f93e37025a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:309d57ade0f91f24b5103d9ecbd792df958ee7c78a00cce46a026eb9ee5eeb44 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cb9274922df7ec074bdd704034b760180401b639 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a26bc402bc8fd77dfc2e51d325de3fd516759548c5fbfa38094e48dd6c3b408d +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c6b6ba3ac27f10e2ed3eac320a5178677ab6249d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff9e0f47cfa701c1f6755e706e0cb7cb569e45ad33d2f980eba76fa1bded9145 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..d4a35a4c9c148e9ad3261c87cf28abbf69e2a037 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfaf77c3d0ebd2633fe22d13760b0e93d8bf50d828291d46946a010a38c467fe +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d0bd8a9c01c7e8823eabb53adb660b9a14cd554c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e36fc84052edd625ec45b7aaad2357970df7203632ee44d485b763234589ff +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7a09e94f674f967f120dd2f0984281b08932fc84 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5430535790e7ee20be30386c6fa4478877dc3885dae5ad930fb9c09a1eeedf +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..256014f80dc8e7722e599cf794de18f1601875ca --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfd9fb905b7a7aa7317c2d7222028f73ae408c01f6be0bbafae64b2aad6debc8 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..9680b96df8c85255aa74cc1b931c83d03f033000 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f08039962b28fb5a0bcbe724e0936cfb36f9ef610f9317498148829ca519bed +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..067fa990e64247a507cf1acca62bb1e652de4b5d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6141cb87f1e38f8cf5d667a05694a76b7c109a2d453cac853664ebeac587545 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..26f42192e9881c5c406f722bf63a924c45a416ee --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137cc07609c4da4aacd304b4fbb93a179102e1f1a78384d3e4f87c40eabb4810 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e2373e3a046397e085ed893b3dca2986e8d8492e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a15ab382ddd34d8b47eaee74a02ce12aff375399b7c23b8b595179a76b48a717 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1d50e783243a00834ff0fc7e7090d549545a7469 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8d38e33a29916b3a384d78f3154474f9b47aa396ce1f0b4ab1c44518164ce8 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c6017838a6972a4e494aca2f67a27c1ca20c614a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b67625dec70cfd7aeb284a41a98bb2f8cd198209a63a8ee73be4d7af2f223de +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4fdbf2d1500d88e97184bedfa89f8e16ba73441 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe42ad280bffdb73f427b1fcb4601b4c336923d9c34223edcbd271ce82dd90b +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..97ca2b09d8a1a35ec2b5026df875d0358eaf650f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d01eace59e54e0e59dbd31c6ec530e16b5f16cd5a291bce1d09a572851fec1de +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f77ca96306027b8b782856e8977882a6b4ba5f7f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:818ace90bc281478fab736c6f8ad713bde8edc876c40441e8e87786526e99d75 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9944ab22f7fe39cad155cb35656fa9ba641b8686 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07cb8f37f8c3fb5f800b008ee48cc27f089db360aa642d7498bc09b8314e21c +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5dfdcf759eccc82f7eaacc6b2b752be9cd23fd22 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2422715d9cb42eaefaff21120cfde70189525f51f0f51971cc5e950f1bdc48b2 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..2313e9d53ce32f31233f2d72d8527a688810aadf --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ed8d2ccba78d3a4c3c05e6c3ace1bd5eda7f340ed9a83b911002892e2c722eb +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bd403b6f08905d03801307a045ac5b09b24bc7d3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45d86aaad8d2251a7d22ceaed7ceaf3fdd11acbad65f89fec69e73ba2cf2de05 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad6ad61fcea9489f97b12214fb38093361fedf78 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7a5f3a1c4f5b00d240b49aefc7889546755e6776dec3abec018307942480c7 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..716a50deb27a17799a0d11675263174d3d229428 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6fd172fab1208267ae2028ee008aaa7a330a6f9d89c86a67cbe6ec83e2addd4 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..cf9e5dababa5e2fc0f7d61783573153ac9bd35e0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7896dbc98b38bceecad1a8224f2e390f82f69aa6e91ac2547581ca0a0cd18e52 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..be772cac113895bd0760b95353794f43df943d50 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d611b70c73fe8e6eba72a5ba82b60fd569b34ceb4e7293ddc306bcbd89e6b31 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f2551c35171159334193af92e14b52da6d082fc6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26ebaf3de7a21e5d9522bda710cce50c67f6dd55bf67a743dee91c8b5ae8701e +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b4e2cc6e90ecb5b16e7a48d3c44158983d98520 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60aa5f439af1750b697977171496e97a96c845dd439232a9a82e60e6ddb6d45c +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1ee8240fe2f0f37886d880e51bf71483cb2d0a9c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cec6fcfdda1dfa8d756124998f159ccb939ae0620c1f7e26b08d6157146dc65c +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..2be051e6a996d455eae35c03bcdc56291432a54f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33b24f2a78abbf21cbfbf2bc2d42a38cf7c581a3ebeb6a55839010b666c4e54 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..782f0e148eb88cdf829acd5095a30c4222d41f59 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dce4c7e52b4e6c2a2018b23aafe37204e13dae6f9f1294aa3ef82ada72b30479 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5ac60ec5cbeba9c0589371ab52afe1130066ef55 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529f227fe6dcc789d5e630591de08f934b14595c485810502b41fac46cfe5f9e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..8c91eea25581c7934cd3da6e5f85ee2db0232a17 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c14b6d3acea03c311f93e75fefb892326fc1dbe8504efa50e0ab1d522dd862e9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..30aa01ff8f315da388ac4aaea3c3218b4e112346 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24e315087197a243bb73095a1798240e0207e21b333afae58414f0854ca6bb86 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2b9b21163fe6fb7c4c9dcfab243b6cdfd1802024 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c836480f99d47c2adf0b21e043d62a6155dee5954123aa932b8476ff5cea8e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..2e0cfa4640f3359ec4d11ed9f9b64f59dc1111d1 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e37e732f01681926e9d322ca01b9ad55f72e1c0f4f2e9f448ad6e6780d306a63 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e7aab04a802e2d7f371e54c7eee508227fcde350 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9b44cebdb1661b1457a9cf2bca5e630520bbdfc9b7176ce7704b726b2524981 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..26823f636f1d9e2c3f33665b2ff8b45c4d5fcfc9 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1457d0402e211b3ace67d73e6557b16c2bb570384bcf80a736957f6602646e90 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..867ab347f0bfe34a021941a77aec0c5a657efaba --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be7dbfba76b7cfcb74c3a97c77fecb97f430ba4a3d2b75990e8ba1acdfb00878 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..e8a8b6882e85dcceb1ccb7d7991e16ff566a7d2a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254cc5a48dfce816b905ccdbbe19316fa485986612269f5de5167ea1547d6b9a +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ed04dcea189106e5d987d48f5165ec341e023f52 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5bc2c1c7c10e5c3ad3ba154e41f9165188f1e00e96a529deee71f4b231548698 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..718d38385a80fdb17109749d972d2896fa839c64 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99c13197a9fd4d1233f95ba7aeaff88e06a93d91c95bb771fda4f56567a3cf2 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..ffa008cf3461e58c79e3eab598f5497efbbd2394 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5667d001614e6a4be5333becf2ddb67a2622837264daa78b232e442005310145 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..06d1e1608e8a78a1e8e0f15a5bb2edc9abbe322e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffb48c104194ffa151986c82b29aeefd9c274d8c6b554e659c6eed9b3a84b659 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2d8e51b78b44da4df6c1f3b20e71b82a9f6a440d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8874205a1141bacaae9fdcf35ac12c56211a602ebefcde5e571e9429da90d4 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3543bd7ef1cb7422da56a01f34eccb7df85e2d62 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94666a24f70b695cb2f3a3adba3c2fa3e6d8556ef3c71f1c9dfddc8708fac3e3 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5e5717c9f0ea99f42af6253577feae8f92ca6f9f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eeb23284a9fce1855bd0fe5c5293c7ce1f046dae8b81e3ce694a1de65b64f4e1 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..99c12c19dce213cb80ce398c548040147f11f1bd --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2bbd0a2532ab1e4c986a415ba99482ac0a0fe2e76654ddebff4a360d5b61c04 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f4a346515c3b6c7dd77036523cb0770b909dc462 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19b277401a0cbc2723d6fc65f8c1d4765b0a03aeeb190adb422769425e8f5b3 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5888eb905cb84a782a1e6c7db1758e1cdd57231e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a334788f30267262028c786a630a7602be52ef0d0c87b623bfeb0df6eef3ffe +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5771b4b041f3586f950306e8c3bbd5ebe5cb96db --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff3ba9738db20c02f397346a74db5b99263ab0b345255db8531e6aab4425de30 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..33902a82194b1836feec031e3b67fc4b18b8b532 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658a3e7cfbbbc9864d5a25f76433fea533f8675ec8b145d76dd1f0ee770a0947 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..a66542913366d0ea7af54f6510bf6755e91b43fa --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8f2ac605a52dd49f2395daf9d51fb6f28aac3f49ecba540bd5b011b7667a2bb +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5e13812b5ae290d5d9d8def5a47b506989401272 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2215dfb148782a86a03910e356ecc65a799552aea3fd00b3d54410eb1b1da7bc +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..85e6554a4b74072f8e135620ce71d54e7847313b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c52f49f7109f6b3b8fa48d71e2d0b1c3a6934eff0e61b5b613e10aaa047e706 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..60077950efce8f5e0e44dfb7e6604eeb932894bc --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fbb14b22a924de17fa3c038a274bb3cf83f4f14fd59df75e117c79324ee8fa2 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..784f99b2feae0b38860d59eb2403eb99069978b7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2742a886b16b3eb30a659792bbf0804561d0262e7c5f17faf59116b66bb35aea +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8560c57126c3c4a029dcb3f975f1d2d59d65aa09 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f327cc707dc55c907d977eb0e379e910794574fb36268752913fc042a383b8a9 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..05703bc8bc4712f64b54eac2c6fd4a61fd197d07 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e927f080fa0165f5bd20153cb6f46c4e059178f066236c3ecb65e3d02a468888 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2f594b6eea18e5487002579248203cf3f4671a37 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faa888858b7d0fbe84d0567ce2f4ed85258fbddcc2dd9d15f89dbc891a07fbe8 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..480c357d8f1043b857756317fbc7f93bb43731a2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64d7dfaf787d9a6c7de2ab044a27c9df1822522d18eaff5e5604659b6914192 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..bf0ea36f02310adb3bd1bfcf63dd2d398226920f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c83cb5a88b3300dec9bedff5b81c980a47652ae26afc602560199012eb3c77e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..55698f730428f55b776ec2e05bc2818b1f8b4f19 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43e1f13159a7a13b68c1cf7af7c68157827c37bce093684ea5ded5afa863a5b5 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7952f2604f475d6905507654afef935438b785cb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a62b3e005442b9ac9a51a505347398cd9a43d80b5bedf204ae184f08a8c715 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..9f707a7121307eb034b514afda64c7f6dbdb1fbc --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c280d6adf6cfd97a02fb2e250d22f857a4e33cec6ec179c60bef3951eaf08fa +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0662cef1f96c651319ba8d22e89e27e9275414f2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5f9c88cc97fc66c309c9ee715d0f1dea71d48a48851bd00731e80d693a7d4b +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..20aa1bd99aa57e1318906c52120c8c7107d0cff5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71036189bc6c7101b6bebd0447e5613b8373df5f4687f35de2606e06905c73e1 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a22b25eb7d346578d0f9dd51c19c016b7e247c9f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1bd071925b1ae11c51176d378aa2141dce7218e35df2ee3e1ee9139758a81ea1 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..db4cd4abe7dfd4696fe07ec630d9c2a752a824ab --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8793b4a4dc529cc97c349077c29696b6decaa197d04a57d8e5b92bf9c990785 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..157327eb49a1158f64220ba460111827d57ca73d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21d29db8e5329c358d55a1c4e04b36e7780690771f10e17d46f7a51bfe889ab9 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2354d5c4b7a0209bd3ffb708cdb037c4274eb380 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0fde78bfd9522524f658236e046ecd0d2189aa0a092c9ddfb2577c3e982bc70 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2cb734838949c75e053b2b9bcb088b2a250fc5be --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6748c5a9e08f6ecabc53162c641de2a07f5397116881fe805ed9f61bc1104be9 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f32d041c7d75edfb5bcf0134505a22852680a6d3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37926a4e49ac39512b92deb7a277c1ebc2ff916c5894d57ad2864133b05f40b3 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..13f4242c302a6e69c5e3a39271159f2d3a94e84c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e69d587128984bd0770ccca6d70a0a7a599a58802d3539e6a085fa96d673ba0 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9c4893ff0b9b5e75f8af5a3320e7e4d5fe5ad185 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b684bcc0c65183e127d15e995f38140b7c7fa34626ffbdf52377bfd192205a9e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..222cb9b8ad9a9f2453c4e6309fd5a6e2f3db613b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b941aa63e23d29f9cdfb5e3b41d9856daffa86af7212b151e06751572105edb +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4a204bf08c49122a190d0ecf100ef2ae4391f1b6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b636e697246faedb0d90b580a65fd0a1ad443ed906f864412a077102ee0a90c0 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b85b08ff2ddc5a0d2105567cf3291f03fe9e6b79 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7ecdfc1dfa2b5bf2e14c8e61936eab60a176d4d467ef7b19929949117e9f9d42 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bde10557d18194ccba2aa5c6f4ddc9bad6f1b2f0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9f3d0835b924bd86953166827fc69fbf873acd0dcab18aef17412623d1ffde +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4b0e336e74d3333dd2879317b2d0db8587c2b92e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5206a02260028ee28fbde6edf9df24199656473b0a98f2b038b7fc841608e572 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6c456ddf62e9191aa42176a54587d14ee4128c0f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4bf9c51258fb62d9081bc539eefeb8b89e6e5aeee4a64876cbb49a2f0972be31 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a5afa0268b638a50d229a93961139046cf040df6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d0181f7e8dd1a8c7b07683dd476cd04da719692488f7f3aa1ba933e8ddae1e2 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4944aa9b33a326f107dd23f7df3840cceb4b6830 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a564f99a29539779b4e31ec8e2238c03ccace4c568b8495bd5028f5fc08e9416 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..57c5ef51ceb4367056be6b27ced4f6ea132eb900 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5debaee800b59990957e8cdbefdce2b2689cecb707d7324a490cdcc31334d496 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8c5cf6fe8e47d1149c847cda71b582ab2e82da70 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae5a653e8076c9208e7e22073445d7ec9fc947da8216b57b112a00da89d94bda +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a1d258b32d9d8f79bf13ccc91baff40f14a06774 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948dd3df371302f40faa36ab26de7f6b12e1bc3acb9bb0e7b6c11be8ffce8b73 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d0e79533a720829c34ffebf10e87935bca47680b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e8a09bf880dff609516146d9a2054ed5ed2e9cfccc7dc925d344062c78848f6 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..94200ff03a2b2cafb266844dd1220d314d5afe98 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30515b24a12811cdb4e11828895050d7aa5577bbf53b3c499d37a5737be85c88 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b765d92a13526d3627d2c1b94bf748309fc7a75 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f627c09a596845e3d789efe2accb30b956cdad47f79f54fb9bc252285435cade +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..c09f3d39ff9a4ec979e4445d77aa7bb09b24f778 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25ecca197b6ef8025f2191f53af10ec3ea73944422e8008ccbd1d3b847a96ff6 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4eb74907679e414cd7544c5822464c25835d6661 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:070a97b829fa87befa3821d68a6aa6641c82cb72f4fe925e2753512de179cfd2 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..68db0f64d31e402df933296b9f0b756032552aa9 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9578a63294e0ce37f60c77926cab85701ef420a7faaa82200671e446ce22168a +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..acdb3d675f4169a7bb59eb8f8f18e19da9e0281b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e052d22f25ca59ca16ab8ed46771a69a892ef8161c02ef8f6bde1712c2366391 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7b267dc060f16c8e288a26268cd1a673ac91b08f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ddbd2b0bc4b186d52ec2d52a16a39cf433ef24f7c36473991a173110a10078f +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b0db4a1dccf512a67567295255e3a9f1c924821b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e63fd23e4b5551f3fec479e2dd079c70b8215f7963c4e64c0434f3d982c126 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..00fd70913a38fe6fd51e7660aa09b3151181c11b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:718df566b7d404a1b5a826260bb58b535953b4964246283ee8778fe1747bb509 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5cdd72bbe23ca5e005eb2fbc1677e3fe16714535 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cfa176f17b9f1b7908867d15388d173fa1942f8dd2e87d2faa6a305a2913ee58 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fbef39b88e4b8aa38009379c0c7a742aee5bbcb6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ca6ca17b076f81f6d3e5d31862f2be94981e36a6162385ca7e41b6aea0760e +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a85476ad468c989ce30f852ab42aaa8ea8a0dbc8 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4b96ddf727cc680c1f0360ff51b143b0e66d45792330cd4e0bb2edfb01ae96 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..0a6aaa688913f70a3cc8875f35a91d44d43dc3a8 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33b4a5d2f35625e25bb030055a6436b237cddb2c9e1a9121b262be610335d31b +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b3d33b44dfd2600b330a70dc676cd8026fba7d87 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:021dad8b19e892acc4dcb55b47bbc7a33b52e7235668ee708ac5dfd085eefe42 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5719d45d4f8a1520d5f635fdb62e5f2ec996465f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f368104b7fc18ccf5a4c19118a31a69a7ac64d3d189eb2a6a814d745a685fb9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..04d09b92596078971ee0d8a32f8a5ea2568c2548 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:293111b659162415dde57bc7a54c237c48e3647109065a69a6a98c7e38373253 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0f0e70262a2d2275b5211ee19725b962a9072463 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aed9d69d8c193ec47b613bf1e9f03ad42af18e3711cb7d18d1ebe5e1272bce4d +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2f5e8e8918da0c0a64ee68b6d11899222d5a9a01 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf4de964079986f1f878f816dd2eb0aab9f1a62a9fda213ee8520983b495442 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ecdc22370bc6e961f1f045aff64402dccd49d49f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:394565412d479da2a5e1adde471addf664e95dbddc5b827fc75dafa2d3c5a681 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..88db8c4f3c3d5b7494390a92acfa3c037f6e21cd --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1af0c0db2c406667c5d8b7c93675b9495e909db4604253b8c76f10fc469e8e9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8c4c2a73d80c395ba0e1a48c5986c085a4d4ebba --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:126520275a2926b23476ced459e26844467cf559a52b7711906356f3f0b624ad +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..e5f76214151d0ed83f78c64d809669b58da88f0a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ae4d706748233ef339f6a0597502d7c6e1a7fa021f367fe99474e8f843fab0 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7513b018b7a363381fbb9e412a08a8ea90a8a907 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3751d8771233a3d88a0d77e3cc2ca815a6585b1390217c94db181f42d853448 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..2eb03bf2e9ad5038c2cbdb4f255126d98823c580 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:524817f3f513857e14f54766c0aa679808e35e5b7127c365403f627db3b23c43 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..10055b466ec85f529e43d314f4ad087633909bd0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e3f9ef44ed1e4908a0de6bd635c4e2498f714c2bc615f97315b04832a875bc +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..45fad4f208ea11dc81ac90bfa70fd9d856dc0c14 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a554b14fd5746bac41c3ef535010ae89c748931bff48458b26544b80c7e08249 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..68c0aab621b1bc6c00afc7ab246e635144d6404e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44e9f93551656b65a2a2c36b75a61f1476d95b8c2c3ffad001d3e1c0f6203c15 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..6ec3fc45abb9bdf122680c35a21998115e55db83 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e700e4ef6b8aad6e2f14dc1285d8d2930df21676b53324ba17f1bc9d516353c2 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4a6c70abb8f19ef4c4dfa1a38b6cc98931cff59f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:26f7c9ecc1ef29ec79856798d2875fd82d7414d84139a94cf8fee9871e700a92 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7bc648b61480d4d8efee98ca25d05cbc8161e131 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc89df5a705e127c12e7632293733fe7834ed756b75e2222e2b0385dcc5c969 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..de75ad9dd623f1eeb5e73edde521a320ce32cd5b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5511a431ec2c39c8ad238da9caf804110214f99d9e30222dbd0279bf710e3437 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..692f8288d6dd3f0d14cc4ebe3372a0f0191b287c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ff2413c845c719b07ab4d3c0be3403978e14764217b54bbbde3b67783198b3 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..025917dcb8006cddd8fcf9f53137f6a0ca8211aa --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bd535f8c4f883304d217ffa1b8ff4a1019639ec2efbc69ca8d45965782e4b5b +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cf33b25d5027ee540a32aba723a1dcd3364e88f7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb29d0b9708b9c82cc65a76153c397f459d3b9eb0c482b2e89e80a2ff33867b7 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..ca164de1e3b8aa588f1fab078fef219daa16e026 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ce67ad4cb6e803e7ad27975e258feccbb45f1f94822f0ae0e695ac3b88cbd4 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..858655c1df29fc6caf9dd23741e38b580ec01dad --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee6bbf6366e086b4964ab2063ca48e361267c626e478c0070f9d9752778950a9 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3eae6b26572f860e4ea119ec70a0a128cc7a7a56 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7809020bf04c489051e22e07494b20557ab1d7b99b6ac74741b55206a6092b4 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..11eff4fa442ff637d879f2194fd9adb53ef40bf3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1bbd7f12b91c4e1f9795a20336e985146ee586ed566676cd6a4e954960ba3fa +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5219ad8b69d3627a68430808591c64a618927dbc --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc73697f7d2c00e8a7ba5c1d7a5006479360a95f8a8860700b53aa831558a47 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..07244f0de18f00bd0c7cb275f162694501f70f08 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1eeff4d9c8f465a45d6f0f1223810e7e43a56317e27339f12cb7593c6d944809 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ffdf07dca6bc7ec5aaad124678ce506a393c0aa2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:762b829d540d74b5cd159ca005b1297df8c50827674000dc82c73dbb056999ea +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..567a3f29f01f8193e05c049c4da50cd656e71ee3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010448aa44fe1534eb246e0934276a8f7abe72cd6fd654526b33f590239a4ead +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..c606f80eb570041ed1afcde02ec48439cd79a15f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b803868f973dab954d9eb92393874efbd6d2f650353a10d0a7637daf73abeff5 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dcd1669ef3529c50b99fbd4b7ce4c456c50f1c77 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3841fa4a3deed727ad7bbd14feddf9b931fa10c645be97f7a41d84cbcbd5b85d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..548aad73191797413bad4f55707bc9e060c3f985 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:259ac4be5eb6265e097e51bc6a69227c65f424a7218c07fd1dafc059b3fc4231 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a4f9829b0c603bd5d6ad9bf7a4651820659c08c1 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a04a4f84162379d5b772eb736221f21122838357c7f701c728b695f7f21f48f +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..abcfa1234aaa6470a5e09442f4478e48c91cf42c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee44d070f4704162396f3b8b000e9d7180d7c05d8ad34e416bc349a70db6e72e +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..0cf6e25c5c77b3c1269ba4c6942013155ec71fe3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34916889620ea3f9c2008efc724720926ef7d0f02c17e2d25f94ce73515e98b8 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e77158ae4d623a5f76eccf8377aa15653ec294e6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23de363ab2a99229fb1cb3b018bb1da93cdd2645c3e516f2099c8c4c540376ca +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..fc8bd4600bcdf478333a279189ff1d8b09e14e53 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecaf658aaf1b5ec6678adae993fb926feb99baf585891f333fc8a6dd2bf05867 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe59371560baa115b55a7b935e80a4de8d985360 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ac6c40f7e941c95fa70bdb6d6de89acf222c37738fc3e9e1d529c5229ed176 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c3baece2e374086d3cca381028452de353055652 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:426047231cede4d2477bac54c01cf176812e8a60254b6c936e774c6cb7722a23 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..a7870c489ecb8bdb030513893d3e8372e193699b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a64477851afbec43150a9263abe29c23556b38a69a005515f792cad409cc9505 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6f7be89666c6a71b56ea9d3ab3eb9f366393a8c8 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431585ec6292217d6b8d7f6c56e402c3a5067273ae6f01ff773f6b546c295222 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..66b8619be79d6cd36fc3cdecb82a339afdee58bd --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe49d8cdb1820dd435b2e2be43b9c3ca00aee1519a0351b929eb206cdb34d92d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5a93e738a363161b0898fdd130afe857f89b0974 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71ba7e910336a8f3aa15ec4b69a14bea7abefdb8fbdd49f30d6a71307f289829 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..56fc5db10d27ac481d30efd51f232d0da9992345 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d4f22d7a9844c265b8737f51512a8b9c3e83f8b3df30a048d2d1312bd89579 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..e5e373c6f7ee56eb1439d48b3a71103d982277ec --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea88389ae526c53184dd45a4d6857177fef78e4cec6bc458190ee501914367f +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5427019ab65c99dfcf05b1e9b372b17f7b3e9b42 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7af3cf1284a0a11ae50a21fc5430c7671bda21157d51bb5ce67c4953e9eac7e8 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e760140a86e30951ea0fa762d0e62e8dcc774115 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a161d226b750496245767146f576d75554387c2831fabca60a236b62c0c1e68 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3d1139165702a621bb4b6157bc2493fdbebaef31 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854c6a40941a76b0a3b916db46652780394e5dee323a633451238bcc28edf4e9 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..191c27e9224a15f07bb25e0afdae4d99ecb334dd --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f502e4334503d12dff1864ef933553f2650e93aa7b2e08a699c2e3dc041f211e +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..968cadb79b8cbfeb206a08fa353d1fbecbc29f1e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e0e73a85ac70626f94ccbbdf5dfe0160a9067cd1ea74f47b1ffac07b3ee38e +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e2008019eb8913e2c4b7b373d763df446a841ca5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264d743b356d1c334878111aa6d1c1fbd184503bb3bc5e09618c4659ef84c4d6 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..6a8101821ebae724b19412b6f98c70b975ba9a4e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22385f3fdd0cee04d1cecc87a14e079caff06735fdeca646c4ceb167746d3766 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..002076b6650522a504a797513beedfed36a9462d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e35b3114a7ca5a0dfdf1b98a01cbfc7fd371109c281002ec4726b6d5033fe54 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a626a86fffa107c2a2802ba32636c7d9d750cf0d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bcf90e3fe150f12fb44938fb4e6d4837e2b673b6f2942a018af7d3c0ade3bd5 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..df69a6ecf3cb99d1b62638b711cb4e90d186d95c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9d118913d2e097c7e6103989bb772e76e372aa94e31b31ddca093846c70655 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f22d67d1729478fd722841e33a6e8010119cb711 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9055c37961318405fe1e1a4682eae84c7ec60c36aabbc07e0d72872516551927 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4d8112016609eaa41dfc821928c22811b2ca0a9b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f48b58398e52c392af7bd2598ac3d15d1593a78709a181d372562f6d2a8e2af9 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fdea8e225a4ab9e8fd57a96fd4c7d24a08767624 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82eb6254b67e39cb4f75ca2cff5178f7958b2c9933640c8d5a3bbdafbc1ede2e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..75f36dfcc77d33dd9a6db601b6ff20115bdb7189 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:889d11e4582305319209d310acb4e30568a1a930203f82f17726f8474e429b9f +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4cd99d3feb54c5dc8adbaa8f062bf3159f34f925 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca09eda29f10b54121f931046c3432e47e930285cf2ec0b9ec936f4bf8d9e7ea +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..efc2dc73d21a677300cce0410453add7ee8c6712 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3118a44fb97e86c419804952360d90ba544aa26269427ec91f77e6cc94f40a8 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6d025c3333f5f11bf7d4b61d6753cb635fe4f42f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b4acc9b871a03e3ca9e6aa439b6d57e8364a974a4ad281b8ce01faef153fa4 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..256b989d19b9fbc8e5ac1b735daea6c1e49eddab --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5025409c19bf7f0311076f2ac7d9643504752a6b73bfc5a9d497693295ca1d75 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8bde7723ed777b1d10ed870832203378eb21e247 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb33114aa61421476fed67f0aed929da063df013130fad7f80009be08532f652 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e2144d72989f5c6b7c1ac0f0b7252f431aba7f0c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4a585a32f0371e342ebb4bee0cf81a3cb7d7df8d4febd3f35b0ad8afa95450 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f30933fe438730068ae2a90ca30c4a6146312117 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de33b54354c1d3d793c14b60bc5a46104453c28c9b381518d4dc2391015e8fc6 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8c3bb3bf479a92d4667029d95d67b24b0310f672 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddba45471e861b67e2ed1cdf00a5e6c5822907130dbaa78f99fc7d21cd50c72c +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fb06b5e44ea2fa909f31a7a7c85d3d7930c20b7e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9650c67d7baee485b850513e817212df813f2c80be5ed5ce4bf3dd8c5c268e4d +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e594cafd49f20d74b851e610ee054fe2f97aefad --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:066e9ba79ea25407df3a675840365a1f5e5364352c57391efd87a04c0b09fe3d +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..556166d452dcf759b9cb7de78a433d2c3a7e29f5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c5c223d3469abf946437a1c4647aef057a6a3b959a0ee258395e2dc9f4a672 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6de029df4661499b78d991b464650576d01781cb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c6c854494e4784dca16883e8cda61720d5b4c7493e93972178af7929a3707ac +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f00efb51c0274828ebb2f4edcfc0f44f2a57f10e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acadc8064fe5a979ab0f239764a43335dab33aad1b7cf3c645355e0abc0b5e22 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..8102c554c45b52daf022846b488b7ca9053c8264 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72cc9867c964092a490740fa87ce609b0b3f12a8ac93c0f94d568adff203c5c7 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9bf94304441d09cb5c4949cf81ebc265dace60c3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c6474f59e0f6ddb7ea7cad0ee161456f1a0e600b35a19606a28e5b4ef2926ef +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..baf9221961a7393153b94142283d105e5df2c498 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154c898127685a5d1f62f4d132b2ddb359cf897cf0567784b03eff0baa5c31fb +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bb9c67184a38030ff858c042c6879c6de401378f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1205721afc83e3e06c4725aefc1ebe9708f44d11e5a2bb0d62779f3a9f1206 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9798872450798b53cb76d19d9b789c9368978af6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f58786212aae211d7b578bbd5f4eee321435b1dfa8580749bc795f0c2877b23c +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..cab5f5cf75c82770cef5406a8b3d16b4860c1e6e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:09d86f06d9b1c85a8aefbb9f41127cc7de7dcb0df380e446bf46d499614a24a9 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1c0dae84a08eb1756df8662f648e14c3e1c86093 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeaeef98a9ecebb9570c8cacf36014660d4c301224549a244b8580c46fcd8ef2 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..96aeb128d98ff8cd0fe50961dd2a1386524272e4 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01aca7cd1bf98f10f42536d02e003fa985e9d886bea4f5da6ee138be6cf2c471 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0969beffd78ff8ad01472819323fb502a0792201 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a48b58a95c368e290da99067ddbe70da581408e86794610b267cb9400b3f8cb +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b57522b6c6ff40011d05f5c340fe6b6e0a2eb7b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774a2f29e2e687db57bbf73f525217559147f289ab18852b086ba29905049ed7 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1aafabe8677fd3fcc8722fa1a4546a23b9b89789 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1affd7fa52d3866fde47522fb5d87a690749d61535d771548a0278dfde52f3c +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d57513e9e665ac902f8321a731f12fc131a13646 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c38b31adb543d9e514e6cb1c4ca6d2061b6c4406150e22fd7ab1c99f0bc40634 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d8334f2f3038dfd5d0cc1b892c53b1545f0ceb96 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cead535970fe45255a6aace0b589ee94e9ccc3daf2499e7af6e07d56599e3c3 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..a97bdd823cf358f93ed6312c9d5b093ce28b1fb9 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50435d9cd4d6f88be25fcb2e91fa9d1aec45e9972937cb49a48965bb19c672dc +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f243ac23f07b6748a6ce8d31431592a5e8631880 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c1fbb97f07e94c43945e4b25616e3039d5398d8886af49b11077e99bcade54e0 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4cbb5ad6e5f6417217bfa1af6ca7c523183bee89 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cc45f5b31b9cbbd8cbe13eeef8525a34715dfef49bf561f0878465e6199f3e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1b22fce17027d17c86998234f24ec1fa2df14b2c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3649bb6fe0c67931bf56bcd48a19b57d5d92895891c3b2351d3ded141cd44ee8 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..43e823b60bc59a675f49e773668080faa609f90f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c372d723f012b9a405796f2f9f02775d513907d31e04cc59e3ac62c72560af06 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8f89222fdbe4450d13e09d53c996f539f7b7e4cb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c226189bbb87071269d4ad03b322b637491172fe6d7d96289a914b071d7477fa +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..78568b318ac493a9908bdaa2dceecda3af66671e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:016f80652a7a8c50fa2fe4a1ebc05883e9eaccbce2d4e470e091724f8dbe18f5 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c0f0e45dc428a6c02c5950741c3d26e15b1b6b18 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:792e6c8ef7aee8bf941d0a48dffb6de23462e843f2aeb291393a3438a2cbc00d +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1bb05f7e72f3d7ddb8116dfbf51fde120d873cf1 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ab91beccbd5a75ff7a1ae04f39e842b58e138fb8b31199659e1f7b3030aaee +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..76ae62f632ae30726230860f3e6f2e31e9a21158 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4ae9435fdf97dfb52c5bdf2357c950cb8748ac53a1c062ac4e93a5aed11df83 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d446b727632096458f20c3a5d4b2bd6858156013 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77fc10913054104a4445c90c867151a7986d7929c312d85955b4b0756b5a74aa +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7cf69dd6647e009397ae498513220e4d2cd640b3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11761f933ffa146c3907301466cde0665cc48ae51077a3eb12e656deec5d92fb +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..adda8071152bc0ecc0b872e84d9eb02dbc651388 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:54f81cd03a885a2262d436042a6aff9ab6a03b82809b26992c0a559e95070fcc +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7449c095a11b7b04713d15758ed34c301a0e4c39 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:157824cd65cb6c1140c8b2e2660d16e1ca65356dfa2939dcc5d1a285bd9003fe +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2870dd8fc996d9f566c5088a68f36b020c0bed81 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d895590e6284c2dd1405d2240c8ad6aae1c796cde290546a82bdebe8473f38 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..ee21357da4edebbe79c034765d41ac9b58b7da0c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa445debfb5fd70464a0e37c26046f7b18cfd1584f1751e4275b43710cd04f4a +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..da092cdf47af03aae6211d4d2d8e84b48fe941cf --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:342d92e7af25f6e3dddd6c17e18ed90b5924252e562edc6b4d6a9560e371f96d +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..33f134083cd0fa3854d858e8afa9366603777a05 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0683d8ec1bf8eb9f5a1df2d9e837cb1ce319e14d49e5082b027c54f17ccf2ff +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ae78115418a195fdcffac53405972500cdd4fe8f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1e412247cb7df7e1da297a8c4619874f862e8be8e5eb846cd91dea838ce87ce3 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..679d7a03ef8ef001fe84273315f4dd4134801e6f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e15b29802c67d6ce4fd45f393452afcbf4f1528745a94ec1e97edd705235fd6c +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bb62eec65b7b573f93e05b95c05a2c0f733378ae --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3327739fa098b0cabe8580fec566128a8cb55060fb2b12002f5293a47ef3f2c +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..8d266d71c75d6f3748e75c9a0f2059c496544627 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c60d043a6fb19b400c6490844b447359e37b1126b639642d5e1e38b3a94c2eb1 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..559d54382519fef0e87df5a591075cf918832b8f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c4cb1e87ce7ab1f021fb273136fe0f1be2abb2e2f2f975e9130feeef426e31d8 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ebcbc6a03a0b38051e288c48351634986f0a34a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84a087a3c34184a09309c0b21a4bc37b5621c648b79c96925b070e2f898ac85 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d48905e900016cf9745e989ca1bb10f0ad8328c7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3b5f50cb38ce55b4a9afe823f4ba1f24fae19573fa83983608b67bb8d927812 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..d35b7c68f2dd7b4310e2fbde52f13fb5fba179c2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ae1f5dffc7e59bcaba45f0d0d2af5b9cf09714d3acd389e32de7289c351f89c +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2dbd7978b810d7ea5135b69ab4a8fcc693346c90 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1893d8d0e465930930452f5e1f1ceb247b58e39e986eeac1f28a307c20201a0 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..317c7fc8cfc5dda37c6e6503125ab2925b26eb1b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a42c4b608f4b352697033b3773b40f170f8afe7fadc56795777b70a0616d9582 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..babb36c3bb2d9a373b708bfdf783041efed45409 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6968973a04db56194d68a232e93606688a679f38b5eff9eeed8fd45115c33c6e +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a76fee3d266d08df1c9bec133863adf22995d19d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1a304248edd39a9d41760fd0f5d5029c19e8b9c30b62f1b59b6c55fe0c3d5d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b393297c38524193fdbb8efb3fa5794f48b48a6f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa98687ca4489babad2e7504272cf8d6d5a987009ae41b8cf5b5fde016cda5d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dd32cf5d71e1dc0a1d8751cfd1d8fe828eba7e72 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f33ddcfe070b8b7aaade7c8dd0f61dd2d6bed93e0ee43548fe5f6d4a9ac588ef +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..08e7b9ab0826f74243f5c2e603ca4375e9dec3d2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1902e7982921f1cee1d119405a2017b9e63ea63a39fdddb61c3d0dfcd4d566d2 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2a36e27851d23ba4213c32fac638b68cc425bff4 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4675cd7e878f3b81d78e32fc7a316022c3e3085fe44c88a38ed929c532b1ba6 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..c74136b14e651b0e8915562e619fb05d03cb3deb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edd2f7412d3d088228e848e1f86fa98a0af50ad692ccb780fcb339855df5ada8 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..94b3527da8f113c78e25fed2f2b2a120db7099bf --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab36dbd527a5043b1f8c0ea223a848c19dc559fb98d2267013c9114bab779c5 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a08ab5cc8dc08690389002eeaec14fa28c01d57a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f162c150955a6eb1b2e7582a717b768fb622d2f80caa5768334a71b942ffbe11 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..3cba545ea9ddf85739e7fdc65eef21585c98dea1 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c844cbed8692557f1ccb1422bbf659a133954a7295d1eed8c59e139dc826421 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b86bb243cc4ea176534eba12ba16b86ba0324f7d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2639dc04465f655b2aee10c1b40a78f672901f2bc61f27e1c8f1654582595525 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..26bf5fc016223d9f135e0eac7858d45652a69b1f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3af64eecc11aa740159ae49934f98fb0f4fd934a3e0c2d634259c321f0fa6b4 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..33b1994a0aee99b8cdc856745dd73e7bb8c976f7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a39be7faea21d59082c0c77990e29dd286683d4fc1c0b15bedce73e893a380b8 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7b1d0636b215b8a6b6b0f3170b928b54d7e18cb2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:241156d937207a33636f8c3f8951631a3169f94070292c87c4785c50594b87b5 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..14bb49af69ba1c4b3377a5f2a9758ca00cf2e2e8 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ce1b399351e9657477c25670f61498d8e08279888235a85d7455eb8220d596 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..9d58a3a14998878614fad168f3749603eaa27260 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8cb0ee22d02c060ee5890bb4296c24285cb0c3c640cc87e1dcbba7fd2b0a8c7 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bed4c9fde392a73a20236cc1619050e5f3d0cb05 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f20e2a30906b2fd503104ac2409d223f3050a598297c4dd7fafaba5d412a5866 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2699081c585d8b5dc09f75b297c6d10cfcf3b62c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b37c8f5ea9f97f53f50e136c28c7483193688af30a43cbd5577448f9c5b3d19 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..efd8fe73b8aa40b82da6d3c9b15a46f7f32fa26a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce8a02262f67698ee11a8cffc5fceab33238bc9b0502de9d25561acdb91a39c0 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..67d1cdb5189180b56d5cffdd149db824d6e57de2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85914f8567316fb3a505d76f4efbffddeda82b252fca0f004b115729fc5eece4 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..a6cf76a6b9fc61891445dedfaaf651efb86de893 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7490187c930e89e02509a16bff674eef9054948c36856f16875ed5251a42801b +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..00981cc6002c15e0706ad076d0290e6971602f73 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df33914df14e8b7e5d563e83e3fe6b42fc7ef7c614eebc00779618ce83e04d5d +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..403961d92200a4e2420544818c894896d44ed54c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c856453fb9ac1ead14db35d6a2dee0f9fcf087e2cbb5f88387dcd188de11b49d +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0e6903d28291056ea67206854be8f070ea1499c7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e72fd80079769400e619b33e91cc62d93cf1c5be447c05d9b5b90842a192c4d9 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..cc8cfa4971b31665280221619e0f4ecaf610fadd --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7767bff8b90fbd314c81bdad8d407998989525b07c4ebab9ae1f804c7660ee +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e5dc53d5dadd64c90bd203b9391f2ef85e9466f2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ce0c7a8083d87d1becff93d5a3f05dd908cf30434b41392b9df3250b00d30c7 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..3e4f443fa415807167339b59a48e01b36ed4c506 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:382f03d4ded816f6b2e3324edb688123509f0f0b8c89a5014a9ee010d70f0766 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bb22755aa39fc8352b3022c28d98e241b76e9918 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5a9d3809fcb3ec3044952e56bca1002af025411043bfd223a6ed6f295e2ef87 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4f9de3be71c5ec1dfd99d8cd8230838e8d6845cf --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222a87faa874fbea24fdabacff0bb11c2e89869abc86fec0b09f5c556c061112 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..00ed21a69091ff528ea5df65bf0d61ce4ed735da --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:837b3d01bd0e877a6f5bf973e2ee2a1e3ba5d7b293ddbec98980e98ebf9e089f +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8ac291846d0641ebe6b45d1e682662746126a81e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78763a472a77e50f6559d5575cc59bc21322f159e40b7ba31a2bd641dde29155 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..34cb9c5845fcca93bbfda851426bf39a45655e63 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13416bd3258b9f68fdc1764a0ae820e60c18e20fe2df5e8bf99e445bbf3d46ea +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b05dba801c8230c85104edded8697c2cb8ad4f6e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71e2b767d703166473e5ba94f2dc98d3aa3876d5130edd9fa1699a974885dc53 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..426c573d753358b912a19ce138c988544250d6eb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e1883be31668ba4dea2a96bb00286e7812c2309c109fefc110faf0d2ac552d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a0631b364652396a1b69f8ab04cb0421c2303da7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6ffe7dbe7a3686e19f0f66abf2b2049b2700cca16d2000e1c745be83905d9dd9 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..d6a38667b5d4496d2417553681012b38169ea58a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcafba2b6819885395c6b6294bc46426ed7d3ac602d66e86e1b51ded1cbfc8e9 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8cc534e4c0c39e882e21ab1e55e8390218b6fb8e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e50e21d170660ad8883193e2463622e31603dc3406e040ded8f5a5ba74d4c156 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6725398a58da59592c86abd7b7bc5e9cd102ee2b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6eb1cde78520b1d0f41f169ef73551a302396b269a2dfb2fcaef6e50f4391d +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..980a669dfaf10fe48840a6dd82bc9e814aa719ce --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80b2e31323ba190e352ea857a7ec8da6564b0c63b321d07f8307a5bc404fc119 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5dd69eaf97a305def9e12d500f633976eea27190 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:525c5f5ce0aa1dbf4ea061913ec642ff0f4bb26e91cc1eada0887081fd6f0e1e +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..40e8458539c7de612fe6caac0d1506a322ce72f9 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0edf66b3eb997bc5168eb7741669000b039a1c1af15f9d05d3ddc53482615c +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..7a3ac3eaa1fea5f5f1804f223626fb3d4f23e5c0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90fddd25de8292d5d7a5d48c6f6933d3d520076b26b60e858afd1fe291363ec2 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..17d88ce8501be1fce2fb903c51d7fd382051c1ef --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7f1ddf96a4df5564731b3c36e60384f0b96556e2d3496531eaea993c4a33a22 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d36d1c2ebb6cbd5a8eb7a25a8921177fc36981a1 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d27e5c15f9b50f5e6a781953c79efe06ce7d7596d476894237df2835027ee6 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..6c53459950f83cb078cadc7fe8ae0f897b64668a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c99f73c3bc55b7933c3a5d37b90d531dc740d27b102f0fa3adf8d01e2c529dda +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fa21e74b38313a6d4c16f6379b546c17ae072559 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49664c55de0ac8cfe4c2c50d2390e266bc6367fef1da5a2a0b32ac2ea47503ea +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..bcabe101a2539b4bf4cf918aa3b872bfd9492fd6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5768cce72cbf4021686bd0de1c8cfee7c5d30e9c52ae96b67cc67c5095c04c97 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..12505cfea223040850aabc61e8679fa53d2c2ba3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13a4973efde6d0dad07d3a0e64b7470b5029f970debb377be1fdef545fca92e4 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d5a5cbad4fc1285be0d5cd82ccb3194391aa949d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9119d5b576a6262380bbf062dd59b12f0b918f2413febf82d97523d0bc8c662 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..857995a50be5db1a0ab2f243337d68115203f0a5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33c912483be5397392a8e73f3e9c54d5b653cd68f3d6a7be42d42baffc6db3eb +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..91e1bd953a9d6a489dc31bf8b3d46451043eb7cf --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc04aae636233c55535c6fe06fd70fb34bdb475db79ebed54f1597416274c0bb +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bad7fa2b8f55ddde156a362b723fb19a27da2aba --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4ee76a221cf00ad3f5a071cdde9ffd9155260d212294fba41298e6fd66beb8 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..487e8608df5e531d5f29a9e76f665be4e92d1dec --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f989aaae9b5c070f1c5236956b2a7a0c0821b0355b6556e2cf0dcc9f879a6117 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..68a0e46cd08a4f97261b454dab440cd56ada96a5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc087b7ac5eedef42cc70ac4806510239ae5b2f800a6e9f747ff5b0a039995a3 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5902395be925ac610cd540fcedd933da1dc7b13b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a72bcb2286ef05acda7f0517c4d43ead5157c3a5c2fd4d67508ec19ca8e5417c +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dd59fc4384c09fc059b4a2e44a20aae992e4c6ba --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3c436e498a4ccdf3285b8ff407f6e68b05d1977fc9e053991f430c5f723856 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..7ec1c389ca8f1148e7bd2948f181c134b2ad4409 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd02f655766ee96da98a1f782e9c59a9d6185e78edcf82d016946f9860bf482c +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..32295651f4451be015ea53133e5fa8c325805c12 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25d9833299ba9b23af5a5a2248e574606a24a39ea9c79f36e05c19ce524a27f0 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9d4c24212fb1458e2cb29fe61010d94d8e88de28 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4910406d2aff7bd205f58fcf484f9abd4b7efb7bb2a5740d5afc071e55cd2711 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..d20e962a93d2e79cb659c2d774124d06af81088d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb7fb40affde765bff37eaf49a63335437d0bd876df1b57fb5d4c1d4b50e8de +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2e485bf39f59c2e87f44335eb08a5bdc067c73ec --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23930c28fcdc6a6f9453b30138d129068a1543bc816812bb93b4d15dd3211127 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6d18284006e739ef206049225cc91908ce5c340e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6acd236a009c2c646537035d07ed56d1f1a7e4bfd8e9b83a2e6c6ecf7c531bc8 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5189509673afa8be5ed0cdd56a8dd161e7376dfc --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41abc91c83a6981e9e85f1a5712410e31a3624eeb5c7c238d1de3c40128f62d5 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..755a418bb1d4929bb6f7b5cc8be6071d8a77dd93 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca526639b2a44df5c6e0ab719ae1bbe85bd440c7e46a30aebf34e8942f2dc5d5 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c5417a844321188a2cbf1efaa7e9af9620da0ba3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2959ca73da13885c8bd2b97eba55955a11c54af86f4ded2216013ef7283830ac +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6bc20eb7a3b7dc1658277fd4e6f18d1beabf8dd7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9933bc2e2bb36d70a4b36932c49f96a26f4630e55cc7b6ebd35a5c952c91e1ba +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..73980aff9112b1c963576e5dbe7c65c0673316c0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2fb6c8bc55f7e04fa142d65589242980c5f51539cd1dd9e614280f41b281b3 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8282e5a7b94d52754dee7f070be4b3296085e4de --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:341360642f6682df1625d71a0f6d470e694460cbd4ed9cc94646fd3523b27637 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..907f7ee6a94f2ee3abe9dc6a4fb628484e3624f3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca6a495efae36e639a8776125e637d676f132e3dad189bc4bb352016f9f19588 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5a5e082d8bb1a00a05d282511f8522bb82e4f2fb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b301a2f3f8cf45d40ec19e6154f40ba13fc09cb49290ac2b725d34987ec5aa9 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d10f37c35d5a1f5357cc4e447316c3e4ac8cabb2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816d513cdeac8dc0605a5808e97cfc152dddd76d3c3ac8451508ba3b140cbf6b +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c47e3db2bc120b5b266135ce961512a25d31c83b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b27b5923d632e5ee232ce2801cdf74ce71c7631c63b2b83ca40122782ea1d9 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..6c0f70ceff68ece9906e4882de6f8a5fed8f2485 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8b9632037fcf6db35e506a542ded13bf6526e1337ac310adaddc8df15f7a1af +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b336fb3e4175ab8600bd1da6a8912c13f0200489 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:475d468f9b9871402c836b4a78599100c1257912556651d4a661d737d3c6ec06 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d82add41ab3145e77b2776f89a496bc68103076 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff2e7d5e2d1eb45e4d6d632bfdd4f4b541720f921e8198927099700e4a6f91b +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..6aeba3db9cb6cfc08f068883a3826ab611678b54 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8a36f862b06fe390739b96081b4c7d17f6e64c616c68d734abda0118f235db8 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a32c141c521038e2b90b68d3eaf01eb3df0f15b4 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:502f05a2e02ccc30c172c31746e06b1839da5ab886bfb7bf6e8239354d21ea24 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..0b0b6c9f2982bf672b54042bd5cafa4e59235f4f --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a620c476736c662d3aad22d86c8bcb1b3bae89bfb9da5dd6a99b27752521ba9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7ac8274054aee3e444fc610882d2910adc1a60d6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3b8fb93a12a2e9411ec693f5e761da80b09734ca758f2ddd06cb83365677bb +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e0aea75be170a90c2c8d74a9b090b5d66d43a93a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53ec28409e38f472cec84d640255e3562ca7b82d662b332e6379eb1fd66c1d6c +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..22a91630cb242682c866977b931964c449c408a9 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9176a482f3fd4e952ac49123fef909bfdb7cd02670953f28851424b4b851dae4 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a7449c263fd960384653ee26361275b3922ea81d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24ac45e8e141b85ecc16f3fc62edef1f02a8668a817824353d899586b4534253 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ee922a410d659781aae32a67b9082a0aa8980bf2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f794bbcdffd07b8719ce97780dab4eabc04d310bbe111dfba7f8205fb80b684 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..97ed98cb1655c7ce9009537fc5b3e948765690f2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:859b0e72ff1c17e8f45b2e68ce825588e7f078d33b72aedbee93aa1e1eee7a67 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..00da8fe85e79a62c81c8874fa491796400822489 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eba0ca94d695788c05b5d316c5624ea1a246db19b037cd45335d02a18dc36c38 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..12a90022c8521c3b7ca0b9c273dc1a34fa7bfa9e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93826f191766743d7070d498832af10a3f28fd35f190eb9bdd1940a4494912b +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3ce8761d4ec28452cb5138688ec911b86faa2638 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ade0c272b61ec903b9817e6441b66509cd6f45e05bbe47ae02625175e64a46eb +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b4c959fc067bdffa241f02df58b32df9cca46c78 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e436d0f0a59775022b182e066d288a2a94af9b6a841e8c061528ca8802311b57 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..13109648ffec1fe0599f423633f6073cb87303e6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e78b8bd099de4d56868405c790850196b11a6c724788e441a0ff6341a9e99691 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6add3d38b2d1d9a1e8a164f079cf0c1ef62ac239 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:082dc967b006eda7fdf89cc81ef5d4fdd5048139757404489f58ce0a12f29b36 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..605fcf39374d386bbf3f3695b2f0e19155b2778c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51b8cd66f1933d4704c6bb40f98d9fb579e284b88508219caeb1107f64b674d1 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..541ecf432a6f11c34120aaf7d2a548c9650a8f71 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c3cd19a550bbdc1e19baad7b8e756bc2e0cac1f6c0c22cc5d4866f41ecb538 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..85f1804740d2fa63cb5919cfc7c5f201e6f71db6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74526432e6daa0d6f46fcb15e7a06a0dce50ab8453df5aade0383b27da9b1eaa +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b4ce0cfabe11b25c3f436c8a6d1dc1be613514a0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4e16269aa526997cfdf2c218c9395f0fc54b822e59bfae4e70e4b2d8e106b31 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5df012b5d24d77c14cd3ba580b1aa24c6346406e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5504f389d7257777f1fcc688c1626c90d960a9eb59612f3a6877ec2da722cb8 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..13b2a2a98b7c88f0b9092dcdc26134fbea35c461 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26dcc80d69e57f2dcaf86910d083f52e45c1d4c750bdcf2c591a03ee1bd9260 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..be805717b9bc4b9721fb03d0527c794d9829a8d1 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:398cdf9afb46d2151412f2cd3924605b35e848e2bdd4de31759d62ec66e4f489 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..590ab442633f188dcd6d404689e77aa64d18d88a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19c6b8b0ae5aa69d9cb6b05db7a21daef7e6738961f1b34c2313f49606caa41 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1ccb73115585d8316182a6d36dc3b461cf19c905 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c63164735fc7137622205535dd41e8f745b7895cad194e42f6f954bb02bfa893 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0f841def7422b734716c38593384845ab12b5008 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b642da24856d34d4abe69b074c3ab8c62bd5185996e35221c2e42c2daef982d2 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b6d315417c3d50166d4b2fb277f44adaaee4f719 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_4_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480a23f93eb763fe243109aff55a64ab2e83432703a30608c4cc738f638604a2 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1a089ac4bea12e65cf82dce34499a68495af8e18 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8902d35a37c5923bb6584baea80d77951a50faa5f26f05c2ffcf64fcd02ec21d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..190fc680a099d59be62e2ec0a5ace43ea9b2193e --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd4fbad220d5e78601ec49cff08b7dd511e5c8c78e9a6fe6a1372d86427d4402 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d4f11fd2cb034cd562044d6dfc4cd58339429c0c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45fbbe8647edf44b099797b2180f6358914ae23627fb690fcbb0d4e0073dc16 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b47a84dabe3361958946acf29de65258a01530ac --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:67e0a1faeae0096fbd72c3e5bbd26d2c0229d8cace8be9d691e314c94db52d0f +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4facf778454f9802192d92f318d4fbde4c3c2d3a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4b54f2157183039f08fd9f1404db9a8f51b8351ec368be0b2f4a209181a9abaa +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5b737a8d28c18cbcc1b29da860cdea1929072482 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a68e7336430778e9733edc4b4ad39c93bc9cd99b62f04a7ec57c10996cf289d +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..e6f1099c16e9381c3032afcd158e14ae44c8a096 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf8d7a87a2882901c6c5d476b9cc79699f15d5f4960187c926757f39701c4280 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..79f40a1eee78507bb81ba781a17b045fca0a6f93 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:75b8b177a4515a40a455015e2184b5bbb65044804cb47644e5945d58d72bc7e5 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2b83049a6bcf2bef96c73f21549f241c75c5b80a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c20790dbd8bffbb8a189bd894d7d9810d4e3a790466265c64ff8215eaf05cf7 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..e4a054da9b325a066269075894334966af4ac4e0 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:896d0dd05fdba23f91a8d96984bbe8a718f7fe6103915bd35688202b87513723 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6e736966c34c61741f194006c2575a9232b29a07 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ae1939bf6c27ea0de827c76849e85df4df628fedd1f889fe48184ba51fa586d +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1c22256c5a26389e89e2a2a1973e580d01b68fd6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c962dea071db08ab5d272d5cfed77a01dd1b22269ea8d9e430c369ab5ac7d2bd +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..242bacb22e148c059b090f30e4283a2a16d16df4 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa45ecd027694084cf585f366d35823caeb3dca21ce84f0f2b5f2b4ae3d2721d +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..25d138ac7ad161538ce403fcf1ec8d9b3c35463d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea502782ca87f1068f0d34260206df8b18c106eee96ce075fe5eecc7e9382cf4 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c94330e07c060dc0da0a0130de9521f3f6f88096 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd7f80db5ebd84caa2879da07e468a71e8be22417ffcc3160c6312dc936d38b9 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..41f4875b03d2d58940ee70e6407bb65aa4d41d48 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88de951e4d44c2a22c2872802b3dc3053e7f5b200e55e512aaa54d72c4264fae +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f7311c6acf5d285033e11402958ccf8aa6212f32 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e130b2b7987b3cffb18d71554b009c5199110e242e2d4d564a9c61625d0dbd8d +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7f6535489ceff0c44c943fe6782be067f31729ad --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946ab4cebd19429bf274a62cfe4903c99103ffe90478a708f97c589a71e5b102 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..406d0dee42f6d38974000a5dd03efe900b653259 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b26d5a1e5e0be5882d69af7e9620e2d12f103c42986a9f81bc7ec19ff058afbd +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bc7373afb05476d52c0f09b85581b2a432bf6cf4 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a9e9068dce90806f8a6fcb91c473c85926641c0ec5444d91cb4a5b88c30d655 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9cdee53a2f1714ba63faf4d5d106c486b0b05943 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1940e1c5c0ec03694254094fffaa692ef5927a3f3e47872358d279dc42d539b9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..838c8ef92eef047326b2ee145685bf37bdf6294a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:228198a1ab2a5e2f38467bcf642b544a1c0697a18a1908c056595a486f9c32d9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..72c05f28798691e9f47a84ce0ad076c4e1cd45a3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac08f9f1d20b448a545ee5b3d4ba5417536eed3a1f9ab700c5b9ddf5164afd81 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b4dfcf7aae336cef3f02364ae8f9825613eee319 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ca7fb0ca658df58f5a45bd29f694e9638d658d8b65b29d478bd6143e72d652e +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b67c3d71678a98f44c5c9ee5af7c1c35c5e9e01d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:254db9782d2d4fe286eb955f96726cb00603a744bd620452cb7ffad4aacc53f1 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dd0f784b73d04762f550a4cfee4abb8d767eb103 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d01e4ee171edbf32521fb4fb4600773ab6652c60971be5f497e97e41f7e911 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..79f5aa15a33d4a6087ac5e914162b4c978bdd345 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:feb9bec5f7145c4a2e528e6e07b76b728e034c37caef83eba3e6e14f1ef31e7c +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..fbf66b6e27e514baba73708ae882d7a9f7802ec2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b1681a17d444080cb99f426fefcc0ab058670e77334eeafc2f6ce531f096d75 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f9db2c26f0e44f6f0e929250135fbcdec5a6ac69 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76b932b72a92d142e8b6a0569a66ed12c822f880c66190740535c68c0b62df33 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b3f8e109c5c9d57a7626bc531088aae692931220 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48300957c2065873f34300d91cd3f6e6548d2827a4024680c3ccba75bbbd293a +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..62ec9fd69362deb52bd890b71376255cb1e1db98 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92c151f1366b4259e7245251c65e70a0abc7a559e09074d12bd28608ec81d3cd +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a6c5e4385c187a8f2065bcf9137411a718bbcced --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79fe31df34a6383782630419070de16a9e4cd73a826f20f0c2fc6b2457c3adb0 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe5ba90dbc97bd5ce02bf72bcbc6cb1ab7d3acef --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223805c699358cf801143dce8f18ad68d2c74d9083b891d4216d4824d1a8eeb5 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..976f3ad26ab81c64b70802699b0c4db90d3beb9a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2ab4961a2d413d7a2cb958b85f206423027f19c220a17f38ee78647c0da47711 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1208160f7118b842a1834bd3cc3dbd0dcdb3db21 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:772667504b0924d6a7986502c1a5d45cd9ecc18acab066942e38db122c8ab974 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e5221dfd05d56a5c83ee43118c6bab160b98f399 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92fbeac6498e746890f6db2be4a654a071bfe2a692191ab553e33de40da8886c +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4d6433dbbb230ba3c9bb6fe2ad65ebe996566e12 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b8961d1cbe2020f8bae5485e7b78fbb1f950e54ae311abc242bc26fe868554 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..74a217697b44c53dbfc557ac6636b9ff3cb9c464 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4128b09bbed217fa20ed3ed64908bcf40be25959bbb0df0a2c16f716249ea633 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1cc0688dd27f0d211a5c1dc846f88989aebd8e04 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:249ffce2d492f1b13e108334edfc3f2688e271bc9fa7c9193fe5702d882c140f +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f713049bb1b187a439cfe722a045211f66d736d7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a5b5cffd9abf9e776dcec2ed086233b57a380d945224d89db712f9b04cac2e4 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1004648e1bfc8f902f4ff96c877765811c3554d6 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e295c4b4e06b9ec589ff631eaf9cb2d2f41a4f778f78aba6f7cab419ec212e8 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d5022b9a01f5bcae7fe698e6ca2909f00650dbb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6f24414e4afc9611a2f38800fa26723f5c774be244dac3330acefc141cba18 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f1ed3b39abccae77acf02d7c3f302be499615938 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:639c81615d115c4c85f66f5b49d4afb7ec71a4fcba6f7b891519ae441924be02 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1340a1447f132fca9c0a97810416590739d77829 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b147df9cdc62e23e654a6d42c51e2c49222a600a0e1755db94b087bd17c3f00a +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5e747f1a71c37cd0d5c5c07a4d0fbc3ba2fc71c9 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16e97df30bdda7a1bd77e30eb5ad80d25104ae465cc8876bc4c2d3f4ce953ae8 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..df5724eb439bda59c8c48f4fd072eda7ad18e31a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2318183c58c16a5c053a8c466493189c26f1271b1d6baf9894aa3552efbbe87 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6cd856e61b79e2b67a3acccacd108895063741c3 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3f6aa79044e0dc8b68a383cbbe079719694dd1d5d0cdc3b5b41a12fb68288dc +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b837026cd586e43c93db00760d38499de5b3a02d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8961500b8c9143b1e22c771ab7a84887f6ebd4c664d1afe2f4127f32ed9fe836 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..68674163fa6751712de599f69f17a3dfc8801891 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d8d4bad30315183c7d07eab2249605eb11ce51931e895c59c238607cc82dcca +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2e14d9f33f9f73d367ae25a934ac2941ba4aa07c --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:687cfc82bb216fec07bedf4675a3095d92eabc35d4576d76b6ccbdfcc02ceed4 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a585069c982ec6830f80482e7004cbd25ee16f16 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ab3edffd1314453ca9dbf8f4c4dcc8ce603ae6691e2997b71f8d7c2596c963 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..41b9fecc57703e54d7cd3e33a904689b32bdc245 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e769b9198adef552b6358eacfa9c2d90c470aae7cbb167d940daa51fa2f3d05 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..0271675fc2f517133fde3c026d41d8bbaa80ed0b --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8844009b4b4aae4325d796693b310b60820efbbda2ef1c04b06eaa8ec0e21e9 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8ee4ee400036ceeb2424a22029a7b85384701bde --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183f4dc7071f39c281ae75ebc315a3d78341fd143e2af80c38726e17df818d42 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..2ff878f1ab512cfd39cfc10d14cb7b61fe36ddb5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:755c0af402963fcdaba9905f2ab88ff6dffbd17ec3485cfa1fdcf699846b5623 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4842919a0fa18571e7aeb8532cb60d162e42b0e5 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:758b74b25cf6a4538c0bf455387bfcb9206438dbd77a7b42996e1b883ac9a8a9 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ed617cb33adfad64ba79a154492eb4216bc6010 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c32a9787b099b2afbd50f74d79759336805cffc85ec9ff2137042c5e98c88e +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2ce7a5b2a8ac515ed1a45d65dec5e7ba4535d7d2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93f79fb5d979f8874f60fa0d6797694e1d87415715efb87b46cdafba2d158ba1 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6b23d7902cb40d7d8ea83d221cd2894883a95d6a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f125038add4d7f7ba79af7fd1067d156c54caa304de922e0b527a588c8446db +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..86c4ee5c681983fc51a9c0b26f7a22bac5bf9b70 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a32b3b74cb1857a6d5a0e9c0be803e811fc653bdf22543c9e67a1bae14d9ca6d +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..799bd3f620d0ec65ed822d1b4e25a07aaec93e47 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d70a30229d589b220d7c199cd5562e332cf0f84104fca090392bbb006c8d0dfc +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ccfe0f57eb08abcd6eda7eb2354339f613aafe99 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2e93deef26f7e93b816182fa5878b23796b77450561d71cd2f730e7f2e3b67f +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ff555c6990890d3a9a81b32d497804f35e4c903d --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91af6e41c19a621b5ee612fac26f7c279f3904a4d4b1943494fbed07d6af268b +size 344064 diff --git a/deepseek-r1-1.5b-unary/lm_head_weight.fp16 b/deepseek-r1-1.5b-unary/lm_head_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..fb4af3ef304753b9796153f2bd5b599471fbca35 --- /dev/null +++ b/deepseek-r1-1.5b-unary/lm_head_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca68befcc8201afc0eb54623dd20bd2af92acfe3cff767e6f8e6c0ddad2a397 +size 466747392 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..00b9eff242aed922bc2fd3d9a1a43d333f81e97b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1a1f8ae5841ebaebc632a3236a6d926bf880a087918c9e40656b1778591aa10d +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..97c721e54a951aa8031e3d0665a92a9b47cba088 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf601ab6062858b266017e3ccc33f77bb1a6560510ddb28d0bddd9822adbd0b +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..297e39320459a07da013aac58ce192730c39473a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:555b2cddc48a67120e4f475669c6aaa797b43e766cfdaa66b1516cd0c186bfc2 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c99a7c46bcf58920de333162f348de51d7bd16a9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a14ccc3db45974d382df92d969830ce228c26caa952ad3847088db07b34d21b1 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..75923fcd7483cf2de75945a3f94bdaa1dbd72d6a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edcd696fe139f201943de2b21656d5c20eebf39069db8fe58dce238807102dcb +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..60f8b9f4f5bb7e9f5eceaa5958c264c802356f07 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d894c2e6b8a97de1dd5e40670261f2908bded704c1cc72fc63d26ceec3109b2e +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7a09e94f674f967f120dd2f0984281b08932fc84 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c5430535790e7ee20be30386c6fa4478877dc3885dae5ad930fb9c09a1eeedf +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b107b97e3998c7da1e6ae2ae66a4f149b50f4a91 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9dfd82d95c24e03f765ae6028ba086efe50a3d9370530add71bd39c42ceb501f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7eb934ddd552b4c4f702d1e295c99835c685997f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daf79438adff7a7e34b3423f18e65a79cf66adc37b57dde51ebfa9dd154a2882 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1d50e783243a00834ff0fc7e7090d549545a7469 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8d38e33a29916b3a384d78f3154474f9b47aa396ce1f0b4ab1c44518164ce8 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..58faa37ea0623e488828b559356599fa01fd3c07 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4549726ed6328f80919c9ee655ec0c1e8f3e0ddcdb616f74bbc7a43a540c5c3 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9944ab22f7fe39cad155cb35656fa9ba641b8686 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b07cb8f37f8c3fb5f800b008ee48cc27f089db360aa642d7498bc09b8314e21c +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5dfdcf759eccc82f7eaacc6b2b752be9cd23fd22 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2422715d9cb42eaefaff21120cfde70189525f51f0f51971cc5e950f1bdc48b2 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0ceefe3a663e86c686252d04a9bf9f4416faaeac --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f183750dd6465451a641aa787fa6dd4fdb963254d27da70507d6c5bc0525fcdc +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..986a75079b5766c6a0eac816ed1babbcd23f0c9f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412c7cb632d6e2fef5f122d80f86a73502197ebb12412d5f21343c2e1201347b +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b4e2cc6e90ecb5b16e7a48d3c44158983d98520 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60aa5f439af1750b697977171496e97a96c845dd439232a9a82e60e6ddb6d45c +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2d6480b6d89e73e4b6d09de881826eb870abb277 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:383f65a7ae2ba933ed278a23e38e67d4aef5507a9f84cae90249376a117eb898 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..01d831615df3421842b833df9aa21ee7dc478029 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:618d053ff27eb6175a3902eb46b9cd28f6a98263685755baee8b586298350581 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..93b80fc22aa949bd34d272d8805eaee74c21c7da --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4128278548a82f332dbe56f6811ed7bf2737bc9d39a74a3893332a7b572b6a8d +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..26823f636f1d9e2c3f33665b2ff8b45c4d5fcfc9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1457d0402e211b3ace67d73e6557b16c2bb570384bcf80a736957f6602646e90 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..51ff0f2063302e0a082a9a2cd1e57e4e10965158 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5dbcb15eaca007036cd5fbcf8408adf3004ba2c3243a543797c8c705d90ab33a +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..718d38385a80fdb17109749d972d2896fa839c64 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b99c13197a9fd4d1233f95ba7aeaff88e06a93d91c95bb771fda4f56567a3cf2 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..183f7b97cb7b49749f8a80bb7b0020eda7a68cb3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:814bee002c9b8cb25c0d6f75d45e59c1dd5738a1113beffb70a6898626cfe3a3 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2d8e51b78b44da4df6c1f3b20e71b82a9f6a440d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa8874205a1141bacaae9fdcf35ac12c56211a602ebefcde5e571e9429da90d4 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f4a346515c3b6c7dd77036523cb0770b909dc462 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b19b277401a0cbc2723d6fc65f8c1d4765b0a03aeeb190adb422769425e8f5b3 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f34e32381c1af6129bf0b2e82aff3e6310670be7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9c809f799c9ff82e49257ea19d49224fa34f73f4c8e266213de8e8126ff0df3 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..33902a82194b1836feec031e3b67fc4b18b8b532 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:658a3e7cfbbbc9864d5a25f76433fea533f8675ec8b145d76dd1f0ee770a0947 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e7716ed9e5717aaa29c504e988d26ec049d7605e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0c28dacf36cf072216e5143b16511a55c32bb039249deae7e9ca804b1605377 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..85e6554a4b74072f8e135620ce71d54e7847313b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c52f49f7109f6b3b8fa48d71e2d0b1c3a6934eff0e61b5b613e10aaa047e706 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b108a2306239311da3dec54435e20cd2c8e576df --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bed710ee2aa8fe432e139eec272d5fbf7f1f771944545cad1c341a542d7f656b +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8560c57126c3c4a029dcb3f975f1d2d59d65aa09 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f327cc707dc55c907d977eb0e379e910794574fb36268752913fc042a383b8a9 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e9b32e080cba9dde0d8f9e4b510282e81c66dcd4 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087d51fab235759b473685642377bf3f9868c2256fec0994300a7802cca117d0 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7952f2604f475d6905507654afef935438b785cb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6a62b3e005442b9ac9a51a505347398cd9a43d80b5bedf204ae184f08a8c715 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8268f18fb336dc07433f04cb81f13629c1c0c632 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f863bc7a24545a4a2d73d2405b978925d6eabfa1c29565b6450e6fd83051454 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..20aa1bd99aa57e1318906c52120c8c7107d0cff5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71036189bc6c7101b6bebd0447e5613b8373df5f4687f35de2606e06905c73e1 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..55798b2b40dc334aff0a72b50074d71b3d9c211d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c476b28dca0473769333759ae46cab574d9572efe6194fec85fea4e03a79eca5 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7eb129e75ad00fd2fd8561a7adfb4ce1fb0a61a6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb522c0a4d8377f12f409289f02034d15835a0adc24524bedafbe927a9bd07f9 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9c4893ff0b9b5e75f8af5a3320e7e4d5fe5ad185 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b684bcc0c65183e127d15e995f38140b7c7fa34626ffbdf52377bfd192205a9e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8eb56da2e83898735f6b7fb3edc6cc2be8aac364 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77ef6a68044b8ee2ac257748ffdf6c424f94a12f506e93bcad650e5eb307a24d +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8e1bad6c168244fbadbc15bf575233671304104f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c64a3819f02136b10366a185e85b5f24100c1a6ce6a5402f82cae49894dc6005 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4b0e336e74d3333dd2879317b2d0db8587c2b92e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5206a02260028ee28fbde6edf9df24199656473b0a98f2b038b7fc841608e572 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..89307a0a1db13c30b34e50fe528fe7ac848147d8 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:698cbc610da404ad4e0c7ba36f288d6bbceea736d65e99fe56a0f06f8b9e4299 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4944aa9b33a326f107dd23f7df3840cceb4b6830 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a564f99a29539779b4e31ec8e2238c03ccace4c568b8495bd5028f5fc08e9416 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a1d258b32d9d8f79bf13ccc91baff40f14a06774 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:948dd3df371302f40faa36ab26de7f6b12e1bc3acb9bb0e7b6c11be8ffce8b73 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..23e000e39fd9441cb6b1bb5ef540149720f7f56c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50dc86d1c8bbc73a15f1daca69cc844a4e85f520ce522b4093182a5d6f31ec6b +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f375b967b794143115719be4725c201f09d6aa5a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3eaaa60b5c7b2d65a93bd56520e7a0145272a87778d10a6c78e4d7d5f082d54 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b0db4a1dccf512a67567295255e3a9f1c924821b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41e63fd23e4b5551f3fec479e2dd079c70b8215f7963c4e64c0434f3d982c126 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1b250088821ef663dff29d5c5db7d6325cce23de --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7fe7741aaf4ec61e8cb83e8766a7cd17f5f1d1093fb63ae2ac9dde58b1019bfa +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ec6d6792a1d8435f6ed2d6b3173ba072f2f5b499 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11e9f817522ccad5f3e347457baf638c60da117be801c3d3f663dcc937711bd5 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..98d270a234a20e9cd20771d295101eaec73317b7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b813fc3e9787f2d0bc03c73674ad124a10e24382e18b0b29acba670d9f8e33 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c5f5aed67d464fcc03064959f6c5916375f47eb7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b97524f8c0de7883bff2d503b0e3b62359aa64a2267aff2c27ef1b8a8d706f52 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2f5e8e8918da0c0a64ee68b6d11899222d5a9a01 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf4de964079986f1f878f816dd2eb0aab9f1a62a9fda213ee8520983b495442 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..21b98c8ba4abcbc8165aef41d2fb4c93089cc806 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a335249be52ec289e0a6eacc812ca51b42266ee13327820301128806cf555a5 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..88db8c4f3c3d5b7494390a92acfa3c037f6e21cd --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1af0c0db2c406667c5d8b7c93675b9495e909db4604253b8c76f10fc469e8e9 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c60c9dde9a15d672aa262556571276798f308b42 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9195e439344141d2644afe4b4702fe2fe64946c474b10a7d4f28d7c441cdee0e +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..435505b8069e5eb1d3cea3473ee6842b361a76bb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e409a2fd62f5305e98e27a89aa08f0b0f0123e9785e556ffa5004635acaa818 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..45fad4f208ea11dc81ac90bfa70fd9d856dc0c14 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a554b14fd5746bac41c3ef535010ae89c748931bff48458b26544b80c7e08249 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ba8e7b6f2896c14c0d45f6c95d5e98f12db70f6d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91d6ff1506144e1c8fdb537282e4c90a23090d6a78c73d920fc89870aa1aa086 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9acbbc4801e888d99f2c8798e882a852f525361a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93bab22b50ca411b4516266c62dbe2b38f96f1feaa9fe0b20ab64b82eca62566 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dfed54c1a27ae5aac5eda0f632a727e6643c1225 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:020a0a47079e517881d08340f558c95d50432aa2c0cf43ba1a64021d98927a42 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..88bd34d5e0c60ba33ab320ff4ae21dc920c43852 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d2961ae504acc3c433dc553cf88b412f650597e225543f877e943d7f978e12 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3eae6b26572f860e4ea119ec70a0a128cc7a7a56 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7809020bf04c489051e22e07494b20557ab1d7b99b6ac74741b55206a6092b4 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5219ad8b69d3627a68430808591c64a618927dbc --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cc73697f7d2c00e8a7ba5c1d7a5006479360a95f8a8860700b53aa831558a47 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..db8a4e3df2dff58a1d58c214a3f13c9adcb49909 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18209e3e01b9704084e087f8ccbf56b74028586ba86a6420625faa22239db0f0 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a4f9829b0c603bd5d6ad9bf7a4651820659c08c1 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a04a4f84162379d5b772eb736221f21122838357c7f701c728b695f7f21f48f +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e77158ae4d623a5f76eccf8377aa15653ec294e6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23de363ab2a99229fb1cb3b018bb1da93cdd2645c3e516f2099c8c4c540376ca +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e18e5c35dc538504cc2f1b99310d8b365a10e969 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c55f924d7ab8981dea2279863be17480980d49fdc6d3feef3ce883e8149b0353 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dfc285af1a767894c81877fa1a3cd1915ddc5b78 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7634f64a0cfe5dab51f88d78468fd0d1cf3af6ae432a41711a29e1441d9d2528 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6f7be89666c6a71b56ea9d3ab3eb9f366393a8c8 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431585ec6292217d6b8d7f6c56e402c3a5067273ae6f01ff773f6b546c295222 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e760140a86e30951ea0fa762d0e62e8dcc774115 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a161d226b750496245767146f576d75554387c2831fabca60a236b62c0c1e68 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9af5146afc62f75e9c5d4c4803a252622161535c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cd19dfc5fc6f99cc7d1d315e77ae80e64164740b7f6aae0e873f7fa6c471dd8 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c52871157f36c6aedf848e61e191bea12c1d3790 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd9dbac81d4857b20f88cd6d042b9c131bbc2246d0cefd004d8555affe4aef75 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e2008019eb8913e2c4b7b373d763df446a841ca5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264d743b356d1c334878111aa6d1c1fbd184503bb3bc5e09618c4659ef84c4d6 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..32305b0d91c36c844a0619497b6bdaed401a3e9a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:716b1065a8805b41044d351205a45aeb493e22003a485fe30c1c107d017af34b +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fdea8e225a4ab9e8fd57a96fd4c7d24a08767624 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:82eb6254b67e39cb4f75ca2cff5178f7958b2c9933640c8d5a3bbdafbc1ede2e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..93f53d5bbf7319bd82d1365da64995b2b31783fe --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e96c1170175d0094ddf28183c8a1250ef7abfa37b5c8a5258fb9e2a7c4a97633 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6d025c3333f5f11bf7d4b61d6753cb635fe4f42f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61b4acc9b871a03e3ca9e6aa439b6d57e8364a974a4ad281b8ce01faef153fa4 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..122e9a64a98096b2c145788818e50e48dfe8536a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c488fd2e3039f5ad92c85968e8711a0830c469673acc7cf59c7383c7a914b9a +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e2144d72989f5c6b7c1ac0f0b7252f431aba7f0c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a4a585a32f0371e342ebb4bee0cf81a3cb7d7df8d4febd3f35b0ad8afa95450 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8c3bb3bf479a92d4667029d95d67b24b0310f672 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ddba45471e861b67e2ed1cdf00a5e6c5822907130dbaa78f99fc7d21cd50c72c +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5bf4720cf3561e24ed034052570f6418b4b76fe9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5353edf0ff99251d61a287881f73a196d70a78d4352e54b579ca98bfee76f4e4 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..556166d452dcf759b9cb7de78a433d2c3a7e29f5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:73c5c223d3469abf946437a1c4647aef057a6a3b959a0ee258395e2dc9f4a672 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..89fa718d8a79c35b66a3c5fb342f43fe157cab2a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f56265f118ce8496cb2de044b4f672351b969827e5b76f5d513900805736b4ae +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ba229e3677b2f7426e5d4a22f1887159ac168daf --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:546723d2d954ae5597b52e1f71ed23bdb46b5636cd9220fe911faaee9dfcd6eb +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..baf9221961a7393153b94142283d105e5df2c498 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:154c898127685a5d1f62f4d132b2ddb359cf897cf0567784b03eff0baa5c31fb +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9798872450798b53cb76d19d9b789c9368978af6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f58786212aae211d7b578bbd5f4eee321435b1dfa8580749bc795f0c2877b23c +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a74c102c06f295b1ad23cde0a913ea95c755009d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fc2ec415f165adb1d8769f1b428ffc2f59deb87ab867a9a5e01225413806cf8 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bead9dc56d2a8241e42069bba61e973ba462f24b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6aaadbc430a016d2b77b810aecfa8277bfddb0b78a16277f6ac3107f34c65f8d +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d8334f2f3038dfd5d0cc1b892c53b1545f0ceb96 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cead535970fe45255a6aace0b589ee94e9ccc3daf2499e7af6e07d56599e3c3 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..54b15fb2d090f51450825b0e56f745c815788983 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ad1bf1d1c0f98f4bcaa9f884ae0d59a29698fa09cdeacf0af56419850fecff8f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..521ae5d65ce0baf9e811a4415ef53a8ce4133f37 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1fe94bc45657a8640c32218a618c4a64aaf4ab900dc854c6ea3bc4ab55b50606 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1bb05f7e72f3d7ddb8116dfbf51fde120d873cf1 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6ab91beccbd5a75ff7a1ae04f39e842b58e138fb8b31199659e1f7b3030aaee +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2c8f52a40cf206b859c41e609023f6647841cf79 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b226ab781db85f18149f7faebaf8ae9a2dbdbea67b5afee79cd9465f22df1d5 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7cf69dd6647e009397ae498513220e4d2cd640b3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:11761f933ffa146c3907301466cde0665cc48ae51077a3eb12e656deec5d92fb +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2870dd8fc996d9f566c5088a68f36b020c0bed81 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61d895590e6284c2dd1405d2240c8ad6aae1c796cde290546a82bdebe8473f38 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..33f134083cd0fa3854d858e8afa9366603777a05 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0683d8ec1bf8eb9f5a1df2d9e837cb1ce319e14d49e5082b027c54f17ccf2ff +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f7b17eb203acb405062b23f388187c45673e7cce --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41b37b20b96afe5529962d225a0d1b3c00078144ab0ed338a8da419009cd3264 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f2151bc97e51ee48bdc7294dc737537096cf8115 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89ff65569f830557ea377c2c17fc7e29a16adfeab6a6cada16c777d3e527b17f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a76fee3d266d08df1c9bec133863adf22995d19d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af1a304248edd39a9d41760fd0f5d5029c19e8b9c30b62f1b59b6c55fe0c3d5d +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b7c6615c7a19cefea46d9c3e04b1157783a1c959 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ead4720c1613e91735f33ab1c25150444fe9a02fc548234e4eeb5d41a5ab06c6 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7cafa778d82c42834ac6d29832bdff0aa65859ce --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c25991222b46de2d199c91d3994606689d0a7186d6a2c585c1df27a2cc4d2027 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a9f7baad3b0e620bec8aa15224e61b553380424f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:738d438eb1a0a44892b16e15978aca4cc765c765f2a6ede4a06d677dc924f574 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b86bb243cc4ea176534eba12ba16b86ba0324f7d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2639dc04465f655b2aee10c1b40a78f672901f2bc61f27e1c8f1654582595525 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..96e1d80d1702ea9d444c94608889221215a45f2d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:457097d0ca0acc8a3c44fea63c831f0dad40073e39b873338c194f58b3a5f7c6 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..14bb49af69ba1c4b3377a5f2a9758ca00cf2e2e8 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8ce1b399351e9657477c25670f61498d8e08279888235a85d7455eb8220d596 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c6e6c0c8c94aabc164c8b41bccd5741ed9b2c12f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:706beb6637c8a153aa9d267903c62687233f51a3069bd0caeaaf05b7b6beecb1 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2699081c585d8b5dc09f75b297c6d10cfcf3b62c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b37c8f5ea9f97f53f50e136c28c7483193688af30a43cbd5577448f9c5b3d19 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..67d1cdb5189180b56d5cffdd149db824d6e57de2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85914f8567316fb3a505d76f4efbffddeda82b252fca0f004b115729fc5eece4 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..667498db02162e8d5d9eee5441269c27c3a3101a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:520f25b368308d0d3f2568c22ddc50f60a2a1688b8798a72198ac317c92135a7 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4f9de3be71c5ec1dfd99d8cd8230838e8d6845cf --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:222a87faa874fbea24fdabacff0bb11c2e89869abc86fec0b09f5c556c061112 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cb1bce988b23c5162d85d86e1ef9bf001e820715 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f850b3c0b1ccd35cb9936ab00017ac80ab056e83a99886f36a8d7c94980541f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b13708238dfeb4bf45a5a4020f5ba34aabc42b53 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba14404e40beff4009f70d140aba001987ff3b767cadbd33cdfdc8e4a2c899ee +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6725398a58da59592c86abd7b7bc5e9cd102ee2b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e6eb1cde78520b1d0f41f169ef73551a302396b269a2dfb2fcaef6e50f4391d +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d36d1c2ebb6cbd5a8eb7a25a8921177fc36981a1 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07d27e5c15f9b50f5e6a781953c79efe06ce7d7596d476894237df2835027ee6 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d631e63789afccb84b1ebaea8473af59829d247e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f0db27c30b4e272acf21c49c616b5728adf3ad896a959465324dfd981f1d1b4 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b4172cfccfb7e5f47754cf34019afbec99fcb194 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7742df58b2eb17912b598df0a2c405b98498924d8ff2523673d0c4d7137fa785 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..51b0af392375533334599936993758089d2b3e46 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0bdff32bef2112fbbf391ba3216289301d6fcabc648a5aa638e4bf8643fa721 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d5a5cbad4fc1285be0d5cd82ccb3194391aa949d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9119d5b576a6262380bbf062dd59b12f0b918f2413febf82d97523d0bc8c662 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d2f263793bdd04450895b38fa7195f4afa533c6b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38d08b94e3847898eab05433abdc515328e6e06a194720eb6932348af33e5113 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..93fc333cba608063625940d04abb046135eecd46 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55d9a147194a9d5071452b3f49bfe723c12685f9a1f75707f20e5822bcecbd59 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..487e8608df5e531d5f29a9e76f665be4e92d1dec --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f989aaae9b5c070f1c5236956b2a7a0c0821b0355b6556e2cf0dcc9f879a6117 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7d2d2d468cadbed0b1fa2273aabe037003adac94 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be6cd58bacc37a443633e05a3cb96a5317861b430ccb2d6f29b60cf3188fc51f +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dd59fc4384c09fc059b4a2e44a20aae992e4c6ba --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf3c436e498a4ccdf3285b8ff407f6e68b05d1977fc9e053991f430c5f723856 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6c9dbd9011191a133be9e4858001a4c102d99655 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4064404abf582a2371701dbdbb6e13e936378b16494c73b4942489079c50ddc +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9d4c24212fb1458e2cb29fe61010d94d8e88de28 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4910406d2aff7bd205f58fcf484f9abd4b7efb7bb2a5740d5afc071e55cd2711 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e06e56d044de157ef91d10237f1103db56ee9bbf --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9535f22f0a02f872b661205f6c68e65193b6756ff3e29de12a2bd8ab3270fb94 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c5417a844321188a2cbf1efaa7e9af9620da0ba3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2959ca73da13885c8bd2b97eba55955a11c54af86f4ded2216013ef7283830ac +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7c73e1e7713a7776863b2b3cf22ff003f9e6d0fa --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd651c486c4e97944a4e9884827639f4e09a1c13d317321e9bd2baa4059cf783 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8af99e68b43d6ab7232103314ab5c82f1cd245f3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f267307f47d66e417f6ecadc3b10074110eec5a3e7fedc8742a242b4af8e640e +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d10f37c35d5a1f5357cc4e447316c3e4ac8cabb2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816d513cdeac8dc0605a5808e97cfc152dddd76d3c3ac8451508ba3b140cbf6b +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..90e684d080803bd6aa9f0a2d473531e723de550d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f589d6b1276958160ea773310ab626ba9b436513c296beb1cfcafff7ab4f197e +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b276a0b38ccaf7379fa0ed7864fea626cc63589f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab720a906e2d987c53e50d8297a9dc13f298c782fb4489c52b0ae9adc329e49a +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..026094d4bcd746686b9273120897fcae351c1314 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:042e74ef45224c8d01a3e37aa5db52f5003280fdd33c0a10ef243a93cfa6bd15 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..931a6d28b0b606cd73c22726ee67def730e00fed --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a98d225e27712cdde9494e72f4be233cb6cec52c1bf563eef75ac9532584dcb5 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7ac8274054aee3e444fc610882d2910adc1a60d6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3b8fb93a12a2e9411ec693f5e761da80b09734ca758f2ddd06cb83365677bb +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..48493b21a92630f0f7bf7953c8ee89766d883ced --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfbfa48952ecb4dc77c0495cf935db5e9a4fe6f99226e922b37963b1e7d76e85 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ee922a410d659781aae32a67b9082a0aa8980bf2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f794bbcdffd07b8719ce97780dab4eabc04d310bbe111dfba7f8205fb80b684 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9722c88f4a780b26b75a0c5f7f3a29cc72d7c657 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c380e92bbb4b6c782aebd33168c57d0b59aec9ad12aadf41d99230441e6b9ed6 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..06ae68486b2d2748b9fc98f75c5298c56a91545f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86833e40c07626a0cac521451638c919d1b6e70c15532d2eb1f6f632cf4bd462 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..85f1804740d2fa63cb5919cfc7c5f201e6f71db6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74526432e6daa0d6f46fcb15e7a06a0dce50ab8453df5aade0383b27da9b1eaa +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5df012b5d24d77c14cd3ba580b1aa24c6346406e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5504f389d7257777f1fcc688c1626c90d960a9eb59612f3a6877ec2da722cb8 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b2786382adca6aff6ce3036f5829c1608111476f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d23aff235badb85dc4de58531013eb2fe0d96e85e6d6d4fb71686b1e2e4f3e7c +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..590ab442633f188dcd6d404689e77aa64d18d88a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19c6b8b0ae5aa69d9cb6b05db7a21daef7e6738961f1b34c2313f49606caa41 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..feb6db594ef2b7d036822222b570e990fcbb3ca3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5297eefb39f92a728ea7a2323c235be92405326f966a4091323f3964e6f8e5 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b6d315417c3d50166d4b2fb277f44adaaee4f719 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480a23f93eb763fe243109aff55a64ab2e83432703a30608c4cc738f638604a2 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d925e68de8909a3463978eb161ebdbf4acf6d3d3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b6b1c3b4218d38949a27f090b66fde1a4cb4ae61ed44eecd958e8e50f7f25b0 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d4f11fd2cb034cd562044d6dfc4cd58339429c0c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45fbbe8647edf44b099797b2180f6358914ae23627fb690fcbb0d4e0073dc16 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..00c083c347f3ddec609ac5431fed0117bd4ebf3e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5fa2d9dd49e15a5abbb551f536ed2b7968477aa16a08df987c2fa1ec03a79f6f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..952fc48dde6b8a854841d515638304c4cf1aaa6b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24c6d8dd3a312a531128a19151281544424c328bcf0380af8e2fe852f50e278c +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6294a490293c7b8676a30251e4d35e8b95e07da8 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5147bbd562dda32025d821bd626ac9b2f653f9ab6e0f21b6f2aff1b3734afae6 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..25d138ac7ad161538ce403fcf1ec8d9b3c35463d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea502782ca87f1068f0d34260206df8b18c106eee96ce075fe5eecc7e9382cf4 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0854c92ed051d40bd69a3d94357df38ba039fe40 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee911e83d8327805819b96f1347e44a9eed25fe52941285acde57e2fba8cf194 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d1c24891c81d4ea7e30f12dd4e01e82455503885 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a5d5676a0f339ec3ce8dd7c3a4a7f43aad25d320ee933c4549e2bd3ae645d23 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7f6535489ceff0c44c943fe6782be067f31729ad --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946ab4cebd19429bf274a62cfe4903c99103ffe90478a708f97c589a71e5b102 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9cdee53a2f1714ba63faf4d5d106c486b0b05943 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1940e1c5c0ec03694254094fffaa692ef5927a3f3e47872358d279dc42d539b9 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3b78b8023a9842cb41e096f676b11e10dbe06604 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17258e1feb7ac154a2c53ce734ff9c90c580b3f7713dca2da12a3498908f7c94 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dd0f784b73d04762f550a4cfee4abb8d767eb103 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d01e4ee171edbf32521fb4fb4600773ab6652c60971be5f497e97e41f7e911 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..54c374f859ecfa3556ae137a6bda8a66dcc2d1ed --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:346ce3d1a732c31ceb2ba4c14b4260f116be86d7e473d3b712970ebffe5c013a +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..185e6db2ab4540f930ea7832b181ec1190342db1 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55e8207bf5ca2ccc322a9920100a1fd55c4496722fffd231f7e98dae245ee1dd +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a3367a36ab7f510f644813c24f9a2b238cb6ccac --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0ae7332bcc2b6ff7c3ffd6ada8fdf58e1578d9a2d69e36cf0f607eb81faae5b +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4d6433dbbb230ba3c9bb6fe2ad65ebe996566e12 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b8961d1cbe2020f8bae5485e7b78fbb1f950e54ae311abc242bc26fe868554 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d5022b9a01f5bcae7fe698e6ca2909f00650dbb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6f24414e4afc9611a2f38800fa26723f5c774be244dac3330acefc141cba18 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..369ffb743ffa23c448176ac449d06cd3f6cbfb76 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15e7962be2a89ea59af65dc7af107e29643ce0456adb5939a2040ed3fa8593f2 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1340a1447f132fca9c0a97810416590739d77829 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b147df9cdc62e23e654a6d42c51e2c49222a600a0e1755db94b087bd17c3f00a +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..20a7cd32ae43dcbca369b0d1685572121121932f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89235e26970d942b4f4755c2a4a30c623ad4ebff62a5208af79c4fb7faebb340 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6cd856e61b79e2b67a3acccacd108895063741c3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3f6aa79044e0dc8b68a383cbbe079719694dd1d5d0cdc3b5b41a12fb68288dc +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..53aed73e16cb9bfb6c9800e19407f00b7a66947b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63accd891c96987a179d98748112add23761b049f8727dd54f5b171d22b984e2 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5b65de37384f1f7d3a9eb5b84e64a3d8564a6a26 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:358aa3b97c5baddc738d60b468d36d91f15d3ec33b44b0416343b61fe2160037 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8ee4ee400036ceeb2424a22029a7b85384701bde --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183f4dc7071f39c281ae75ebc315a3d78341fd143e2af80c38726e17df818d42 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..09cb8eae37b7be4c44ec692c48ec2ade07da214d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab6d1e0dc0bf3c63896c12e6b790aa8d0bf5004b59ad2175631610c4f84d092f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ed617cb33adfad64ba79a154492eb4216bc6010 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c32a9787b099b2afbd50f74d79759336805cffc85ec9ff2137042c5e98c88e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..da9c295d39ceacaddb805e3eb41996cc816bdd69 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9902fed81a39874ca3acaa80108f743d3cf4ce4da40615188749826b04d40a57 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a1a027fec7eb7a53330d7834740a64b0d8c4f2df --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33f492a8da52ca814923b856ee23133631cedcdd47b4e3844d8860f9288caac8 +size 344064 diff --git a/qwen3-4b-log5-unary/model_embed_tokens_weight.fp16 b/qwen3-4b-log5-unary/model_embed_tokens_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..0e8e116074a78063e54fe3e480d8e73dab1bede3 --- /dev/null +++ b/qwen3-4b-log5-unary/model_embed_tokens_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306877428a6e2a0b343ec77faa07dc7ea85c83af3ee0c23ecfb5a9796b3f0464 +size 777912320 diff --git a/qwen3-4b-proper-unary/model_embed_tokens_weight.fp16 b/qwen3-4b-proper-unary/model_embed_tokens_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..0e8e116074a78063e54fe3e480d8e73dab1bede3 --- /dev/null +++ b/qwen3-4b-proper-unary/model_embed_tokens_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306877428a6e2a0b343ec77faa07dc7ea85c83af3ee0c23ecfb5a9796b3f0464 +size 777912320 diff --git a/qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7679871856102b785725205128762c2aea2d574b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4a97a19bfc6481e87c014ca4a709d19e83a708a5524314723f4882a3b41c24a +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bb92be11de3834cf5888160d02f158c54094e5b5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e46dde0a662e9c943eae218898c0143b26dd7dbfb4b0b0326e2ebb776ec1ca60 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6ae0d858115137a14e6eb798897f34f5dee3cc7c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6227fe3ac9eb57d894b4bb4c5cefb44b3fecb654d410eed680f9494257ee1098 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c9592733fd66a6bf867b7af310489dea3fd494e5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:962a2da92d36c649e8a9657955d15de81deee43fdb78f7226b5453001811c9b3 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4d9bdbd96766a8f267aec6cf08cd9f26c67c1923 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4320eb4ed32b2243419f800610b5aefbce617129b4d645c091d8ce780e39328 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3137a2fd6a151f47b4268204db23e1936cefb7bd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2bbff60e2d6ddf2ff4336e2dc3a8d47c920fa7a216e667280b5503cdeb242ac8 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0ebb41bd4b1824ea58b396d4ab7e01be9f20d054 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:606ba279e3a743a05a1c3f929c916bd571f5fc2c4f5d33ec510e286fb356d8f8 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a994d1453d20c4d2ae1b5a9114c4261a7dfd26c3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df97eb27dcc62965077a0a455db358d989941cc6b15350bb49ab19e8e49d3450 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c8a6fdb953fc3d414432020d40618703bca141a8 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:757e9baf3f222f935e81bf5548dcca19fe1130fde28ee2c6ac1c396e7f44b98d +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..adc5370d3eaff148aa121ca99b11bfc2a960d35d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c226c372f61fc6cd680d8237cb7398b32b45e52f9db96e75c14305c097c435b2 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d365b683712c7c44dc20a9e03998811a6b1cc863 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0363eae78ec073d1c712aeb3937b4da6924243013162bdbf5851e0c38d8b0883 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..011a542ca82e6abc68799a5431e2f96177cad71e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e713491b6593d09a7bd8b8dd90ceb0208c4c9ac8b11dd00ee194ec58c4c15da5 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4bc51d3518827c5fd5edae59930dcdf094403426 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7eb4aee2f8629d4b04beb6a5e7e6cc85f386438786929b96111866fe7bb3ca +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bd4deb1e7d745417028170ce33aaf9997acddaff --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f7042a2be22d9f093b6a6154649862e23d44b78051933ebaff424d05785d95 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0475e55046d1e152a19c1241d14739a2c97fc80e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cc1371fd675dd2db174437ce8e7bac1219579783a05dd4146c6a5b8d426c9a0 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dd1d660fe073d5c502c45e31710c34692d0450db --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79efc25d79c4655891c53e704117eab298b0e8600aa861b683a77d9175c38654 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..748aaa6c88e53e4d2fd593f366698bc7207b4fc3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e9538b906d56011373695280290823b60bcabaa7d7a9c5140cd44349b825bc0 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b3b073fdf69a744e6b81a15e94b50948b64105b0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8c2099f37978fdc36420b362ab6494a8b56870e5c0ea522b36bb2508de4cf6d +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..57521289ea0ab8778ee17cd30eaca91ad9e19d06 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4c4d899cb6131415472fd38b4eac422e28f42d6e959bab225f7876c5958a274 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..da539ff5c71a6f07abe3fe0135ad454a81afc11e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af088b441b4d9f875fe23f065d26e5fc593c51b4260c46f21d2e5b9d7881fe61 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ea839c089318eda1b87c53500b621483d4413b25 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:140c0672a8583307402f4f68caa9d228fa7aec0fb95fcf3f4deb2beab7778a3b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7fad3d1da252096a664368cc8c180a0cce46caa2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fed2c4513082ad2764ec58e22ad282f295ca095a219a40c88c24475567cbea91 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..65b39b53efc1c7a579064c9b6807f0cf8c7084ee --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f21523a2cade3d759c47b7ca5879b28847b7163005e47353ca75bfb99015a912 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..706134d9c4b405c6035f3d6f6cdb10209228c8d4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a378b59f2d881c729f9315062fd08d6500caf8b5a7861689522ad183be0c904 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..808e06cbadd0ca5e95c507124d8c4169c88da4d9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bad98f67997315019c2d24a2d6002b1885a46c0f9e0e1d4c465ccf221e177904 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bbfa80fd674238906ad7e23acc5ce6a6a2621c9d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f45b1507fd6b02779147d731920be87678b51e3570f3c8c827365612a5a8710 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6fed57926cb3bfa33214814bf366dea439a1ab28 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18028873bde06384eb3c969fafe9bb889115d5f89d6f9bb46ce95684ee94b744 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f7f0b1bafb1abbb5c6dd9f03d52f27e3d413d51e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a33b89cfb3a8e8e310ff2a514975af9bab6759e504fa72bd07d01f88eb0729cd +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..447633103aa2a642dbcf7009cb6d994fd8f472c7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0b3d0c951811babbd224ef6dc0e3690c6fc49297a4273572a943d0e6b0bde21 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1112ff374a59205c068a24526e83e5de263e86e1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:710fe5dc4205d7d62132a575fd804893137a0433aa1cc64b5b8eb5ac919cdf71 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b5331aacc34fd3077c3d078768aa9bb5cffeb4c9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aff238bbb0788ab1f10d2fd5b2ede695b776905b96a1c42a0b2d23a35caf1f9e +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..be5d4759db6f57e269194132b9e391d9e35478a2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3ca3bce9f21e1497f5902d1c3d4e7944fc22826018c21d91671034b4cb1913b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2c9dacf970c3b4f7e3fbb269ce68cf7cbf832b07 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dc89ff872186118bc6cfb43982124222ab60ae1244d9ea5f8523a554de281b6 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..eb7996ab1e623f24af016ee5be8492bd9d2c0ebe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f8f5e1faadc59d8c1c011415fa0d295de867639a453bf535dc97e881b8ca56c +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9729643d420fe4d5ee2f16349d0267e832c0b398 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f31e9462413516e7267d21613db4f74012b375292f57c2c049a39d833a64118 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0e51789d4fa7366cf9f4b4b969f3901dca19051d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0173da72db908e9e82068f2e40a235845074fded687f87510e439cafc39a32f3 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6269712ac010e01ebd65de86cd925a5ca1ec0b42 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:286c5695ca26770ee53366ff1680c99ca2050338f8ece3d38805dd1588e8386a +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b1cde03af009db8d6438b31c790076d8b26a454e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50a810d5407e0a25c202f67f2eca4d20be3c8d4963585192d2e8bbf1b7bf7791 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..309438996274ec25f453597197179c44a8fbdc14 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ced0f5f1d6473aa72ab0743787ae9bfa8081995ad54775db9fc8a1b1001c2aa4 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..400a2faf22d01bcf3a471054e2ee3906ecc460e7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdccb08cd5b4241d83c6a76ffb25eb796d7c0445ff14e380a35e40e14a61a11c +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe5250168f84bf68e5fad8712e27db203460e641 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccedc1549d32487108bd93fc75d794213897b6dd902069668160cbc44bc6f6d0 +size 327680