*.7z filter=lfs diff=lfs merge=lfs -text *.arrow filter=lfs diff=lfs merge=lfs -text *.bin filter=lfs diff=lfs merge=lfs -text *.bz2 filter=lfs diff=lfs merge=lfs -text *.ckpt filter=lfs diff=lfs merge=lfs -text *.ftz filter=lfs diff=lfs merge=lfs -text *.gz filter=lfs diff=lfs merge=lfs -text *.h5 filter=lfs diff=lfs merge=lfs -text *.joblib filter=lfs diff=lfs merge=lfs -text *.lfs.* filter=lfs diff=lfs merge=lfs -text *.mlmodel filter=lfs diff=lfs merge=lfs -text *.model filter=lfs diff=lfs merge=lfs -text *.msgpack filter=lfs diff=lfs merge=lfs -text *.npy filter=lfs diff=lfs merge=lfs -text *.npz filter=lfs diff=lfs merge=lfs -text *.onnx filter=lfs diff=lfs merge=lfs -text *.ot filter=lfs diff=lfs merge=lfs -text *.parquet filter=lfs diff=lfs merge=lfs -text *.pb filter=lfs diff=lfs merge=lfs -text *.pickle filter=lfs diff=lfs merge=lfs -text *.pkl filter=lfs diff=lfs merge=lfs -text *.pt filter=lfs diff=lfs merge=lfs -text *.pth filter=lfs diff=lfs merge=lfs -text *.rar filter=lfs diff=lfs merge=lfs -text *.safetensors filter=lfs diff=lfs merge=lfs -text saved_model/**/* filter=lfs diff=lfs merge=lfs -text *.tar.* filter=lfs diff=lfs merge=lfs -text *.tar filter=lfs diff=lfs merge=lfs -text *.tflite filter=lfs diff=lfs merge=lfs -text *.tgz filter=lfs diff=lfs merge=lfs -text *.wasm filter=lfs diff=lfs merge=lfs -text *.xz filter=lfs diff=lfs merge=lfs -text *.zip filter=lfs diff=lfs merge=lfs -text *.zst filter=lfs diff=lfs merge=lfs -text *tfevents* filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_17_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_20_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_0_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.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_21_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_9_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_15_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_4_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.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_15_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_7_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.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_8_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.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_18_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_14_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_21_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_0_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_21_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.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_10_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_19_mlp_up_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_0_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_7_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_23_mlp_down_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_6_self_attn_o_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_10_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text 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 qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.gscales filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.slots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.usign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.usign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.uslots filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_8_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.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_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.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_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.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_16_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.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_3_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.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-thinking-hf/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_30_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_12_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_27_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_10_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_26_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_18_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_17_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_22_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_11_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_24_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_14_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_12_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_21_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_23_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_16_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary4/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_33_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/tokenizer.json filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_9_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_20_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_13_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_19_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_22_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_16_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_32_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_15_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_1_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_23_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_25_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_13_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_24_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_self_attn_k_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_26_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_30_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_18_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_29_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_28_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_17_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_self_attn_v_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_20_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_33_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_35_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_14_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_21_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_12_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_18_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_25_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_15_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_1_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_22_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_6_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_2_self_attn_q_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_3_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_self_attn_o_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_0_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_12_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_11_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_21_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_26_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_8_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_self_attn_o_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_5_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_4_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_27_mlp_gate_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_mlp_up_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_16_mlp_up_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_19_self_attn_q_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_7_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_17_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_14_mlp_down_proj_weight.pos filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_10_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_23_mlp_down_proj_weight.neg filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_22_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_17_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_9_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_11_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_21_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_20_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_4_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_0_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_12_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_6_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_24_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_13_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_self_attn_k_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_10_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_26_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_1_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_self_attn_o_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_mlp_down_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_23_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_self_attn_q_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_8_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_self_attn_q_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_3_self_attn_o_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_5_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_2_mlp_gate_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_14_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_19_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_15_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_25_self_attn_v_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_7_mlp_up_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_27_mlp_gate_proj_weight.mags filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_16_mlp_down_proj_weight.signs filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/lm_head_weight.fp16 filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_31_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_34_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-packed/model_layers_18_mlp_up_proj_weight.mags filter=lfs diff=lfs merge=lfs -text qwen3-4b-log-unary/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-ternary/model_layers_24_mlp_gate_proj_weight.neg filter=lfs diff=lfs merge=lfs -text