diff --git a/.gitattributes b/.gitattributes index 5bde1802e77137a4c0abb7c23494c7594cc8830e..fdbd3454376055504bbe24352679924242364f1d 100644 --- a/.gitattributes +++ b/.gitattributes @@ -1797,3 +1797,723 @@ qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.planes filter=lf 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 diff --git a/deepseek-r1-1.5b-gunary/config.json b/deepseek-r1-1.5b-gunary/config.json new file mode 100644 index 0000000000000000000000000000000000000000..da00b6c6c01b51ad3af55f9060083fd108e458fb --- /dev/null +++ b/deepseek-r1-1.5b-gunary/config.json @@ -0,0 +1,14 @@ +{ + "hidden_size": 1536, + "intermediate_size": 8960, + "num_attention_heads": 12, + "num_key_value_heads": 2, + "num_hidden_layers": 28, + "vocab_size": 151936, + "head_dim": 128, + "rope_theta": 1000000.0, + "rms_norm_eps": 1e-06, + "n_planes": 7, + "group_size": 32, + "quant_type": "unary_group" +} \ No newline at end of file diff --git a/deepseek-r1-1.5b-gunary/lm_head_weight.fp16 b/deepseek-r1-1.5b-gunary/lm_head_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..fb4af3ef304753b9796153f2bd5b599471fbca35 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/lm_head_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cca68befcc8201afc0eb54623dd20bd2af92acfe3cff767e6f8e6c0ddad2a397 +size 466747392 diff --git a/deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16 b/deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..41dc9c1ab0695b778c586bb83ebd9fd020f49ed2 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_embed_tokens_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55610c68685326d482c594ff3bb16141e71a0d219fe729211562ab630953c6e +size 466747392 diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..91e5335bba44952236c965e1d087a417fa1872a2 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1b7be81ea40572ce7b09dec92bbe585ab6a7cb9e Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_0_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_10_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..ca42714370c9e4663825711e822d6fd9b4f3a7b2 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_10_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..d6c3039814b8c0cb9a4c77605f7463e93a3b4c04 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..37c91a27fa24debad38b68b4937718c96e4bfad4 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_10_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..062db56c99f1e0f7bf63d93fa5f28fe511ff6724 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..87742a2fe0b0324b37227ec7682d74d5e4a099bd Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..fc82d2ce243529e924112e93801b2c31a9313d50 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..9017af4926876f597c24e2bd9a435e002d4a08d3 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_11_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_12_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..2ad77dec2867326bc94701462d61e8e7d82f5090 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_12_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..7e1d849ef209c5f6e0030d6978af22a861b8dc5c Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_12_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_13_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..40b686b83607f6f85048ff11f9cbd63cf1b152cc Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_13_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..8908159071055644e0ee977d0b7eeb0fc888d7e6 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..50917599408e20db431e4d83b8da3e33e4772ec3 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..faa664846e9e36b3c9ae43ddc6a88401f10f715b Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_13_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..2eac1d88530fb34fa129684db4bf14cfcc9ff05c Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..e5876032eaa1d29719c88f2b615f066d349e86c8 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..7a890e6b559ac51462e1f4952a2c1a3a3ba89a84 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_14_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b225cf5b31630407d56f21aeaa62e86fb6d246fb Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_15_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f3c645585b3f5cf451c7c7c770159e799fa83af7 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c3981a49073d31fef293273e651dc1fc5863b33a Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..98d270a234a20e9cd20771d295101eaec73317b7 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e2b813fc3e9787f2d0bc03c73674ad124a10e24382e18b0b29acba670d9f8e33 +size 294912 diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c4a9452345d31cf2acb2cb43c8fb5bca0b8cda38 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..104360cea46d7e4ff41f010cb2e807f69af73bd0 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_16_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_17_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..f65011ae1846ecb6b63f5a65c0ddbbfc830647e7 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_17_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_post_attention_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_17_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..00f889b99c2652a77daf31ccc53d9ced249c3ba3 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_17_post_attention_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..879dbcd56affcfbd20af9b3450a827e8ac23ac7d Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8c11b3e37584b9f60aa081bfab76f150119307ad Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_17_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_18_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..2ff9fc8328968f5077b4ed41a2b51418c2497e1c Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_18_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..85b45ba6f4e5167da101bc355ade8b675718a561 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_18_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..56f5b49ac5d1a30f808692813610c02ccef558b2 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f3ee398091f065d7b81aca83dd3f4bdd4d656d36 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_19_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0b6dafcb3699083eab377e291ab7c7db974f7d4b5328d082e9d095667dc39d6 +size 2064384 diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..4a3cb661de572e92ca2eabe5520d09b7c23ea1ec Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f1e1175627aaadb9325d72b57300b82b25c3043f Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_1_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_20_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..8a042895077821880f716b03d5f483d8669cad26 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_20_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_post_attention_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_20_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..6c2e8526f934c429b58d28ac364b320464dafe2d Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_20_post_attention_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c5d0a76c0c2e67fc853bdb88b3effc526c8fb5c3 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b4734c6a402fe4103de6be4a3f8456dbde76dd39 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_20_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_post_attention_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_21_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..ec4f1d9e6e111004533d729fba9ea0804f85e64f Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_21_post_attention_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..de08168d31c1f248630ed3d80e072a2309cec035 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..7c1f3b98dabb03ff3be28c0b03999064e08fdbdb Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..8bda5da79163a0df9f6fb706b134a2f1a567b30c Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_21_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..51103b9cea5888331cf394ba8948f1014a260a27 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..56d475c2e2ec4b8e1c14680aec79de9a493ea100 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f9ebe9c346df0d0631639186f0b6c022e8e1af94 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a6bf2c514bd4821cc4ebdd3e4771816fe0cba1ad Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_22_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_23_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..e58a9cd071083fb0d971e7be3858bccd1e181435 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_23_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..b7ce333521fda2ad7ce68c00fb18795d3baf81bb Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5e4edc27c5e6775e9831f3ce24256853730be7f6 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3f2c4d375b61d03cc2989e5af223fa1e3e0a829e Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..308f588954d75655c4e3a7a9003561edfcca1de3 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_23_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..8a38fe17002304214d00ae90a7bb04de994bec4d Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c42e816d956112f842229ee1c8bc6cf6e6e5273f Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..eb6638a94a285d4a1475833b26c02f53813f38b8 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_24_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..54cc853a0dcde3490d08d2b0ac292c871bb2089e Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..410431ac742d3ccc6fd4615eb565773e2aa1f755 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..7af350c50cf3aeefcbb87b8f51de73037c1e9c00 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_25_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_26_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..1f225c82377611b1ba728ba0580192d4687233a2 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_26_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..50d867d0362b8297ed14f3af013fba84a8d4abfc Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..df6e786029be37d2a1d7b3c0336e50d72b428372 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..989a0bba49e703f8f30ef4a088a69eccd1f5872a Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..68b25dd009244fe8dc7ec381fab0669674080397 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..02ff97b80f4eb7e7bde8dc2327400e625efb6c54 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_26_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b4172cfccfb7e5f47754cf34019afbec99fcb194 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7742df58b2eb17912b598df0a2c405b98498924d8ff2523673d0c4d7137fa785 +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..88309d4eddb2aeebf47e8425ebce13a00235616a Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0de0c21e409ceee7e1d204f1cbf973e19d612937 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_27_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea2e36e56b9467fd54b0e9af4b79eea5b118974ea285fce59c82ee5e53779c28 +size 344064 diff --git a/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..2380f667f41f252cbabe02de56949dd09681da1b Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_2_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_3_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..82fe0d09b0a7eee7296ce5aa2c244e96aff41d85 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_3_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..962ed75cb1c19057750127dc9e49c7a193b23c2a --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_3_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c3c41da8b0d9c25b66e8ed254eb05a6c034ce7af40b1c0fa396f08fed344b71 +size 12042240 diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3c6ecacaa6eaa01ba4642cb7f341b9c6c08fc85c Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..b37dc356f784f9f38046ae8990d4fd72cfaedeb4 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_3_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_4_post_attention_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_4_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3a03ea4fd346e87a8d6485b675c1b00490291f03 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_4_post_attention_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_5_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..4887b4f8f91b6ca182df77fad852de7d66027b7d Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_5_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..770c264cb5354136f1f8a94488d3d68584801d04 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..c082e22b4c111d909b471a70d2c9239336434646 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..384e5550886585bdd202059a7247c072f880b9bd Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3e83b22c90d1a1d8d811f6d3775f594a5413fa17 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_5_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_6_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..97b519b14daa47092d6ecef62c3bfdda0e741084 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_post_attention_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_6_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..f6158498a312a5b3a2e8841c68ab65ff5807e776 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_post_attention_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..d593845bbb02448eac0e08ca8c4102e5478ac7d2 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..96d27f387ec78b62cae9893e5b2c76284d674f48 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..44a1c67cb2d8815f8522ac98aab19745423db987 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c26f42a44f8db2152457881a9bb9c48d3032ded5 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..db6c4087a62ab997ea93da9955d9737ac2c25eb4 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..f1e30e08f1aa099061d720cae00d7ab1a54f0f40 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_6_self_attn_v_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..576a52e8dd0a1e8d80a1cf150cbb1e8cdce0e7e1 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0635d7eeec596e40e47fb5f57ed52995e24b7690 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_7_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_8_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..aff9d98b0be61b53898d1d9bbe1ed129e788251f Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_8_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..32426adc056e00e965249eb51486fb8498d61790 --- /dev/null +++ b/deepseek-r1-1.5b-gunary/model_layers_8_mlp_gate_proj_weight.gscales @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c10511f80436dcf3830d1ef575633464c7c0246316cb20d1b77e83eda9cb92c +size 1720320 diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..1c14b40c16f35425a5391fd050208b5d5d846ac9 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ee7d9d76fb8cd89d756b6e6e59276f5a4c3f77b1 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_k_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.sign b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..66d95813be7a1cc30ac2e2ea3bef606235a0a5c9 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_8_self_attn_v_proj_weight.sign differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_input_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_9_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..34b2ea7c153d35d9b3d7bc9bc90d4025b8974cc8 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_9_input_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_post_attention_layernorm_weight.fp16 b/deepseek-r1-1.5b-gunary/model_layers_9_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..279793aef4972875c25744bf4a9569e950ee3302 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_9_post_attention_layernorm_weight.fp16 differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.gscales b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.gscales new file mode 100644 index 0000000000000000000000000000000000000000..5df10233b2ea981515f5d19e6f5769a33ef2ab6f Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_k_proj_weight.gscales differ diff --git a/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_bias.fp16 b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_bias.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..481af2f5d19a52afd43711747fe2739a46864394 Binary files /dev/null and b/deepseek-r1-1.5b-gunary/model_layers_9_self_attn_q_proj_bias.fp16 differ diff --git a/deepseek-r1-1.5b-hf/model.safetensors b/deepseek-r1-1.5b-hf/model.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..719ca20e5bf68c2bf6be60b029d81930e5ae1e4b --- /dev/null +++ b/deepseek-r1-1.5b-hf/model.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:58858233513d76b8703e72eed6ce16807b523328188e13329257fb9594462945 +size 3554214621 diff --git a/deepseek-r1-1.5b-unary/model_embed_tokens_weight.fp16 b/deepseek-r1-1.5b-unary/model_embed_tokens_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..41dc9c1ab0695b778c586bb83ebd9fd020f49ed2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_embed_tokens_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55610c68685326d482c594ff3bb16141e71a0d219fe729211562ab630953c6e +size 466747392 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5eb31b8c8740b361e59cf3c7c61f8602135c71c2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00bcdd77d1efba3ac6ed66176e829754089867c75fd301c286cf893bf5defe88 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c75e9f7883463882c7fed4e8c9b3f7d130cfe90e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b49338069c9db0f188c0b6e9b2a9bbb1c3ee94d02d186706f7d297872e2711a7 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bcbb6d4cb93734e51427fee26b7365b1e2bd56d9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe6abd5262c850da2f148e6afc5fcd4d33208652eb540f38d0dcffff37a6a549 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad057ec33226dd92818e0221690cfab99a2f7ce5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b1f543227944a1af2750e991457b30cb7188988bc96d74d0a5dd89facf6877 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fa5c3f4361129e89d21fe2ecaff339213555bc39 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:afa7c60db5e54d8009750dd241125670907a01f6b0741fecf14e3983914efbbe +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e773326e4ea0d075505e655752ac141a0cbf12b5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_0_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:556096531abd03fc5e5f04c6d35b923f99fa220b279f136aea4b8d2af372d579 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9a8f223f9fe8fc9869aed75a9dfd41594096bf16 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:16a44f8cc78acaecf3ce04f9c82ae74c8b981ec9c16ab2fc83b53d970cd02d12 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..865768ce455d3cbff3385d2ae000a4977b3fa43c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecd5f1ef5629a25b9431a1fd835a5e3bcd9079e5c1fe51400804ac6ba3c22a42 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..26f42192e9881c5c406f722bf63a924c45a416ee --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:137cc07609c4da4aacd304b4fbb93a179102e1f1a78384d3e4f87c40eabb4810 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b839288367b6c3c203751b990aa4f99def75d85b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ba4cfedf0a1604212d36027351ddd8af6a88917c476d83ab4abe3bebdd13d99f +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4fdbf2d1500d88e97184bedfa89f8e16ba73441 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4fe42ad280bffdb73f427b1fcb4601b4c336923d9c34223edcbd271ce82dd90b +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_10_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c3ad09e684822a98f410b2110734cb279c125d75 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_10_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b507a2b0dbf30279dc7bd9bc2a564150e3401c8179035668eb4c145df1a9fa2e +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..54bad22cde0d4b3f8a378bde113fa147b9b6c04f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c727ead88330ee5121cd75d14445e3aa07be06978c2bacd3eea4417dc91f4ed +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..117fbfae0cf7cb587e2fe681d1ee6623c748c596 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d9848873edf4b27988f8086c619655e03db089cf76ca642c5f0e80c83af255b +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dbd590c37d42aea2d5340cf75e9f0d65947a2115 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9714bd8ca7abd224e326eb6432730715f6c0b72902f8aa74d626bef6a3eb2420 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad6ad61fcea9489f97b12214fb38093361fedf78 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b7a5f3a1c4f5b00d240b49aefc7889546755e6776dec3abec018307942480c7 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..31d27390f346c377f8af1f09d524ac9fc4e0ad1d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3641a11fa104ede3683b018e369651ac41e0dac13e4ed5f945d18fa2d3a16169 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..be772cac113895bd0760b95353794f43df943d50 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_11_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d611b70c73fe8e6eba72a5ba82b60fd569b34ceb4e7293ddc306bcbd89e6b31 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cbd573150852bb5ec07e094bbf77510e41808cb8 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd2bc631d324518a7ab9d865a1a14bcb2455ca1be2afc22fa4d7ce7d51d38bb2 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5ac60ec5cbeba9c0589371ab52afe1130066ef55 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:529f227fe6dcc789d5e630591de08f934b14595c485810502b41fac46cfe5f9e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2b9b21163fe6fb7c4c9dcfab243b6cdfd1802024 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7c836480f99d47c2adf0b21e043d62a6155dee5954123aa932b8476ff5cea8e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..56c5ee016d33712d6b1085b5395020e4463a0b82 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d768ebe0a931e2ca18d2d3beb24784d1244e26687233641b11f33e126842aed9 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c27e719858debc635c1ca618e2b13b301f963eb5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_12_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af94a6ca0fd78fae77ad20bf0ce59ed00a025a1b1bfbd7e0a2432efee7fb1388 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1808cf4f049325947ead55fa0a2fe0440a92b8d5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ac4ea998f7222f318c7a1d062bbe65846438ac245366f65889bef3badf1d251 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7cbdc7734412796cfebca9dd5c71b466c00f1df0 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc7dab0808a2760c705d9c636b64441173a095e1bef9697219b202dee40c0dd6 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..68521e8c93bf651fd7a829721cbb52c9e02530d2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f77567267cb678b75a75436084cd6345d32a1fefcadc4ae5a11f4b7908598bec +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_13_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d8ea8329414447117c541a8c59f6894d842716db --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_13_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17a82c32020db365997f4639298022c9c4880fdf3f73fdb2b1833bb0ca84ddfe +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7c35b51daa22bf475fb7741bf34a926ba5580b5a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e595d9d0e867a57b4edb448d0eb2bf7e16194f790afed240b5cca67eb62e8905 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..bf0ea36f02310adb3bd1bfcf63dd2d398226920f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c83cb5a88b3300dec9bedff5b81c980a47652ae26afc602560199012eb3c77e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..13ef5bdd1a0aafbeb5af5dc9d51a4fe1fe39ac9f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93db1781dd1b9ecd95e44631ecf80ca54d350cabc3ed92d03843694362a664c +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7029a408e555fbf3d71aa3c229f0e29e386ea5e6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29f0ab0d390ce6947e49de8ca8214ecddb5099db59fc779252955da08ce2f96 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2354d5c4b7a0209bd3ffb708cdb037c4274eb380 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0fde78bfd9522524f658236e046ecd0d2189aa0a092c9ddfb2577c3e982bc70 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c4a7e29b87ae473202275c97ef519cef4ee4db6e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f838d911475fd6f07312272c83c1798b8e7c6b23ab61269c490cfab01bb934a +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fd6f2e7c532aa5f7ef590882bf23f97b9e76e091 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0b1d71717a33bae43b6cc287107fa866ebf2d3a053742a709381035b2c234a66 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_14_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8abd9a4f21ce7b615703cf05b289e2cec375a597 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_14_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a7216508d870da5e702bcb502a24ca8c36a998163788e91236265b85edac774 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4a204bf08c49122a190d0ecf100ef2ae4391f1b6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b636e697246faedb0d90b580a65fd0a1ad443ed906f864412a077102ee0a90c0 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..35a76b066459486271db898ff72524fca75ea115 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ba6085ed536395e5b94609f323b3b6be619778f3baa44001900af2ee3d37aca +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dee0dfc79ebff70bc4058d06746339c60db4356b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_15_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fc9b5e5acbc35e5a0b5619037ca5b2a3fc57d187439b4507113dc754b31b21dc +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..96c40baca7e482aeaa739b631a01e5de1ce5389f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b76fee1bc869576a35dbaa183fee07348bdb01b9cfdef318eb40e9b5a317c5f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b765d92a13526d3627d2c1b94bf748309fc7a75 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f627c09a596845e3d789efe2accb30b956cdad47f79f54fb9bc252285435cade +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d6fa094fe8d7e139515489831a3283d881132596 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62f1a21058b9b30a583d9d1c9882f83c88c236d6021a15c3742dea13717da13c +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..68db0f64d31e402df933296b9f0b756032552aa9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9578a63294e0ce37f60c77926cab85701ef420a7faaa82200671e446ce22168a +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7d7386f1db2ba1708cacf4ed3012b2f14aaf7fd2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5cf7a01372745e8edc6303c9dc68b2c97fb4761e0f30116333c044de6708bac3 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a85476ad468c989ce30f852ab42aaa8ea8a0dbc8 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_16_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb4b96ddf727cc680c1f0360ff51b143b0e66d45792330cd4e0bb2edfb01ae96 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e43590ae44367568afc48f987e96a07215f22041 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7167f220492760d30e6bd1b7f2a55195b7bc7284618475ea019ebc6058088ba1 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..445b38859aa91dfee64aa73b4e2e49cba18fef7f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65b662b9a71e1c30f54e9781190dc2c4847527cdecdb022b85b3909d2b4c11cb +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9013e51b94b2e752ea308002ea91969e5d900827 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac8a6966d15f7e1c8cb2f542816283484cac49a2e5b48b9c482d45d1e0300190 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c8412571cdf7c7d7a235d8e4e1e77ac4c5277398 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7057ab1398767efb88fd1695756e64064a78d4fb909c74dde10113e98ea3961 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..46959be67c21b92c4cdcea7996d9466bab78ca75 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_17_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53a1072ee99deffed0ec00408b067daa5a91d5b2dec19fda4d8473ad6808a3ce +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e2c65c00a5393116cc04e9b16dff808510531e62 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff2eac59d2ab99b6cb2e477dbfb84f0398e7180d9d117d1661008d1bbd1bd4aa +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7bc648b61480d4d8efee98ca25d05cbc8161e131 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bfc89df5a705e127c12e7632293733fe7834ed756b75e2222e2b0385dcc5c969 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0d261bdb81071a99b0daff732067af79645fedf6 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:912c494ff106d7ae31e333c579c7dd9b0a420a4b4b737438ff9289dbe5b3d102 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3a7e4174524872129dd9b1f87493b0021bec5ccf --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8da4270e466c8d0be4527cc144f503fb296a5a5707d1049a1f5ebba2fa5cdb10 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b0f9725b406834a08492d7d164664fa27841b26a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:043ea7daa9281049fa820608b120e4c985a3577629f4e72f6054edc745347496 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..75f05c6c9a0b699ca36130fd8633684337893545 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:879f875d8cd431a9abe3207a72c24c59a979e7664f668ac08722a626afe0ebf9 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_18_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..02928e58840a2989f3dde6e85e928b23e47e6e2e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_18_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18056f743e2e52e02f0f503624431afa40496716f53c7eae70fd24aea1f9dc49 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..567a3f29f01f8193e05c049c4da50cd656e71ee3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:010448aa44fe1534eb246e0934276a8f7abe72cd6fd654526b33f590239a4ead +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..17df12c51d9ed71072571193914a6ec5ba89acec --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c161465f934a1e8e12a261009b26bbfb7d8e4a987e017fd44368614886923cbc +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dcd1669ef3529c50b99fbd4b7ce4c456c50f1c77 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3841fa4a3deed727ad7bbd14feddf9b931fa10c645be97f7a41d84cbcbd5b85d +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..45b43301941974e76d237f7100d4173d8aefee78 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02a81880dacaf7192c5d9ead9941e93e74cca31f2a67736b8ded3e0a7918fe7 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a15166f437c54ef923ed6986d2ce820ec5e35a74 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35cb5e72f55cdd68639e1ca219ee818aafd3dd561c3f361457db3b37d85f4b42 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ac696e32552ae74cb9733c994193cca8f03028d2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36daa2a594215b0bc78ec3b65c3573227e45017a5025b718f4ed990ea6a95a52 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe59371560baa115b55a7b935e80a4de8d985360 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_19_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90ac6c40f7e941c95fa70bdb6d6de89acf222c37738fc3e9e1d529c5229ed176 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6738f9ee629493ad4a4c5d4e8f5b6ecd25f56bd7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6695b04ccf6d5c7f73e00343c6e7a4de0c75adb9e3c823f3c31b06bad24b2cc3 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..579f1f7b4696684f5b7a56a7db6982f16897d06f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c367c9b43c8d490e4148c5f0f28930d8837c562c56fe3b7910965efac447f2f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..56fc5db10d27ac481d30efd51f232d0da9992345 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18d4f22d7a9844c265b8737f51512a8b9c3e83f8b3df30a048d2d1312bd89579 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1f797bdbba9fba35c856eda08d1730387b75cb64 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:075755835fe8f1b27a4d0e82b45fda1defd80efdf8398d9a091470bd81f1ec5b +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a626a86fffa107c2a2802ba32636c7d9d750cf0d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bcf90e3fe150f12fb44938fb4e6d4837e2b673b6f2942a018af7d3c0ade3bd5 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_1_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7a215f3a402b8d114db7d241f7d015634e3a275d --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_1_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8d5be2dd950d50e2d7f9363583f579bd7e364196255da25d0ac2eb53b6d0442 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1a910eaafb4111925dae7e9f931869e0d41b876c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ec8930954e235f01a7d18f69b46b26733d02265f548de65fd15c1089b63a8c +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4c0cddcd05a4f0d717d27282d6d99fdba4d07aa4 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:752cf23045d328b7f1f6c188733fb6168012b22156b34547d7ff590efe3855f6 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4cd99d3feb54c5dc8adbaa8f062bf3159f34f925 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca09eda29f10b54121f931046c3432e47e930285cf2ec0b9ec936f4bf8d9e7ea +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5f8793da5da6df3e652f4f0c36ca69fbbb8ad14c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:87b888c79f97026a94280af8c055a196469525a65bbc6c60b796750110110ea6 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9fdb2ebc60145555c10e67adb73eff1c83d5cb67 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_20_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fb6453e714c597e2dc1d7da77c35435b0a38e4a10635f365d88fb7071386931 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..49d20170da9a5fff8ea4d2fc86edad990525d6d5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc3c38c33cd918e082e147cd697726c8c43079b9cb92eaf3c6ba94ce88783d0c +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f00efb51c0274828ebb2f4edcfc0f44f2a57f10e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acadc8064fe5a979ab0f239764a43335dab33aad1b7cf3c645355e0abc0b5e22 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2d205f6633f944c19d4127c671a8de8219ec0848 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00407727cd79eec5fd7c5ac58c61b24b5b07e80f97970de87d74dc952b2369ea +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cabfb59b9b1e526d62739e58cde6cb3676be38a7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18b8070dcadb9630e28ee194bf63f07c4b8c5a2fe4a76fc92eabac3a48fbf876 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..76a6dffe65dd11314ec5764d82aecad61358cf41 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2de5f2a6748bfae662d5f29cc9974111ade6445151f4ccf652d60c179f5d44f7 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_21_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..daa47fbae46daefd6539c26b1c333f5c5308061b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_21_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a46dc54de86433d8f39200993343b66b0e2baba02d454955312991a4a957e6b +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..05ca8666f7c389779e1987c2a7dcf5a9a881daf5 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b1b58579d3978db3de1b9552a8a293af659570a8ebd49b672025d0ddaa80559a +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b57522b6c6ff40011d05f5c340fe6b6e0a2eb7b --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:774a2f29e2e687db57bbf73f525217559147f289ab18852b086ba29905049ed7 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4cbb5ad6e5f6417217bfa1af6ca7c523183bee89 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98cc45f5b31b9cbbd8cbe13eeef8525a34715dfef49bf561f0878465e6199f3e +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..aaf5d1c1a7f1571caa008e26d74bb3456b691a7e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:561ff32d1a0704b1668eab637509bb6fd1fc91ebc014de437473c288af066be2 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0423d3a60992ed6560e1b06e5a8746d7e4b74b98 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bb5cba2673dd9c0714ff7b2d68c4c2c685022b5a334e471e7af1dda414760b1 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8f89222fdbe4450d13e09d53c996f539f7b7e4cb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c226189bbb87071269d4ad03b322b637491172fe6d7d96289a914b071d7477fa +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_22_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..639abe48afa66916f006823785d1dc2c0a3a2119 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_22_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bbc30f687bad26785b99726e3f5d776010988551f9279e79927102e4094e523 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4c0d19dc76d1e1b1c84115e144b985394be5668c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b28ad5a0e0bb1c1e3f14d28bbc4805bf48705842014a6765f2af161ab6a1ad4 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..722fb5f705b753f0d5a7e13d13d55f378b1d34ab --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6821f1ff18f973ea5df17e0b04ee63832195391841babf7a4066574ec3a4b1f3 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8a2ea8590fd2c249cb0960b3077de38c1c44bb35 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14c130629ed73ad14c791220048dcba1db55050be9bbaf9ed84a64b08795fbc3 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1d5685c492af460b34ea5d803dd53b35b1359e9f --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9d75a0c15bce0163444c66d70367cdad5f3166100d42a954a7e3d28950f74b8 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..55a527bb3c1ecbbd996713b8b7b663867ebe5474 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b77a2daacf3897a92ae31cf0ce42214a146ac3839e2a21aa0ebcd531ca44d0a5 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ebcbc6a03a0b38051e288c48351634986f0a34a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84a087a3c34184a09309c0b21a4bc37b5621c648b79c96925b070e2f898ac85 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_23_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b5989e209cf968ca73073472a45eb8ea5d948aac --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_23_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:42b968448deedef112f3686163bbb5608e84e1b170dcb54a1c2862d98ddd87c5 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4d85e3b3b07eddbe5fc441700f44847ecf5a7bc7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88d2f15b9dfb41fe62c182cae131e072f718841a4f69507f2659f5d89a41d4fd +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ff17124f9d467c54aa4ed5a4ef9b19ac812661c4 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86cca1f83a0b656b5b9e895a32797309e95088fbac4b80be1b53df380e4c1b66 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..08e7b9ab0826f74243f5c2e603ca4375e9dec3d2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1902e7982921f1cee1d119405a2017b9e63ea63a39fdddb61c3d0dfcd4d566d2 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a08ab5cc8dc08690389002eeaec14fa28c01d57a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f162c150955a6eb1b2e7582a717b768fb622d2f80caa5768334a71b942ffbe11 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6cc7def654085c1a1ad2b8f9af7bb4bfe41f9999 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_24_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:199d1651fefb50979951c220e69ddc0ced9ed54bb009f321063ed9b03ef0417e +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0345a066f367d45ea1ba9166330b3bf5824e3030 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:925f1e1ec8887541c938f15d65257842c94f11554c75c9157c1f35146a02a2c4 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d1952b25473bab416a95eac95403f93ddab23991 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56ea2fb74c527c9a422496b1d76bd1d153e2e148070687bd6706e4dc32f524a4 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..790597e871ef47670fcfb0a69f660b8237dd5635 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3f1a3adfd0647dac211d08898fd4af5be64514a93bec37119d44259754d98a2 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8de29a211f6e3abaf52b411ded69087f3d412d91 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fcc5151db230d9c109b087640a8b26265005657fca5e55c4ab3ac64488e28fbe +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..00981cc6002c15e0706ad076d0290e6971602f73 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df33914df14e8b7e5d563e83e3fe6b42fc7ef7c614eebc00779618ce83e04d5d +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..35926f5afabd722c14416ac819c7732e4e55afdd --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d778aacf7399ba73a7f9814d627a0c1989b21551bf8c44aba0c7b42fbbc359e6 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..cc8cfa4971b31665280221619e0f4ecaf610fadd --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_25_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab7767bff8b90fbd314c81bdad8d407998989525b07c4ebab9ae1f804c7660ee +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ed2e185a32b697f7467ecb426e164ca7d17f7374 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c24eee5fa756366a7543a7b602ef7393417c39da23288375f291b0054a69a8ec +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..aba690445bfc1b3297968c72541f27f363144b14 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02a72ffde930bf0461badc3f1812dd681973a46a6c222970e3149bb39361df8 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..34cb9c5845fcca93bbfda851426bf39a45655e63 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13416bd3258b9f68fdc1764a0ae820e60c18e20fe2df5e8bf99e445bbf3d46ea +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..426c573d753358b912a19ce138c988544250d6eb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92e1883be31668ba4dea2a96bb00286e7812c2309c109fefc110faf0d2ac552d +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b40b53c3a200f6b5ab1aa413ff7824e1642fe502 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ace9db55bc42b65e1a21d30773eb03bf5aed2b329bc193a5f489ae570f9d612e +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..da8ca9a7dba89bbd223d1e6388348043de4d9a73 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eed4e015c5dd0a5cb46140979323f9f0e5cf28f7b8ef819fb3cd46222d777044 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..efa6edd3a260dfde31f724e0b24f794570a0edcf --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64cd45387e12da3c6e36de138ee43d14b376ff1d9e29a5c578423ced5d588610 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_26_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6e4f88472b2042193dbda80045f8aa41862064ca --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_26_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0942780627729c1cfc24c53a0d4a84f991aa35757e190aeefdb9982f94365a9a +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..182b5698adff91e306bd031526bd4539a82bbae3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_27_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e3f5fa0528da2b880affd4dc6dc445fc46fb860838cb040211cc83c2cd34b92 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9cc05620a09cd646a15d441622c5fce78bb3b3ee --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f416c13885c0a5f0d69322fe54c0de84b465953d35d4c366ffd0bc84c7b29627 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ec855f8d7cdc1e0bf4d48f1ffd258809702eca72 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ccfa6f6a5944d8239b1c691d9745b4eb241007ab466d0e8135b042a2a66d3ebc +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6d18284006e739ef206049225cc91908ce5c340e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6acd236a009c2c646537035d07ed56d1f1a7e4bfd8e9b83a2e6c6ecf7c531bc8 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..aa16cc61a1a8e36f5ab3d53b0853de49c9b07b8a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2e79c6f10544688b70574294f9e446cc0393503740b64d2c9750cb5364a7b7da +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dedc1ef084d019c2871fabc2d811b83990c74081 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_2_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b68e9039d9c4eac2bc530a3c6f30ec6b4bef42514ad763d6426927b5ef6245d +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d82add41ab3145e77b2776f89a496bc68103076 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9ff2e7d5e2d1eb45e4d6d632bfdd4f4b541720f921e8198927099700e4a6f91b +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a8a4a34f4627de28681a7ef6baf444341add0356 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71f770399800a7dd1df24cc413f67013848e44dd3c181d48d80aaa11dc45202a +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e5ca55555212d7248ea4f1288194bbb28018fefa --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fc1bde7a713c1200c37aa9faae7bf72a9c39755d64d526c35d277f08c03396e +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..df96d255ea11797539f3729f541e63954afbddf0 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf191ccc4cec337af1db510ebbc07a55fa333070121febad3c8de05549b92d7c +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..12a90022c8521c3b7ca0b9c273dc1a34fa7bfa9e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f93826f191766743d7070d498832af10a3f28fd35f190eb9bdd1940a4494912b +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_3_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b3b803354acfd025bf1e7f250fea3230356c0739 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_3_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d40569a38bff3ecd002428a9ca316727cd2647b972b1e549de4eb16f3b914c05 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6add3d38b2d1d9a1e8a164f079cf0c1ef62ac239 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:082dc967b006eda7fdf89cc81ef5d4fdd5048139757404489f58ce0a12f29b36 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..91cf5446a4d8d2925644b28b7278e6b9cc77865e --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0bfe10005ecd42479829857071fc28dd8380128f0b6171e54860d9cbc13ad16d +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b69d3f3479bbab7a26ddbb5af802f3850632fdcb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005d65f1af88b7f23a83767d394b4e507e6b03a7b4bd83def4f82cc3f0743d55 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_4_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b1f37df92d1cacc6a644c071454bd38193320d82 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_4_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca685cebb182d0775a588468c4dbd5975d959fc6bd3ce5cf588dbdb93c7bf16f +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1affad19cf38c1b92ef7183872790985f0a0e621 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ce97bcd0fbf64eacff5cd1d13808bea8fedbdf99737ac5b5dd626820ca3835c +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5b737a8d28c18cbcc1b29da860cdea1929072482 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2a68e7336430778e9733edc4b4ad39c93bc9cd99b62f04a7ec57c10996cf289d +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2b83049a6bcf2bef96c73f21549f241c75c5b80a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c20790dbd8bffbb8a189bd894d7d9810d4e3a790466265c64ff8215eaf05cf7 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8fbf82296bbef0a992370e297a51621b8775cf72 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70ac2334e8767ea4330f87657e288b94cb431f99b96b1a989e3cec7782dea4f8 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4713697103e199d6d1764fedd842080e3feecd59 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_5_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c011f8749c3f0375bfdeacd01cc0543cc143243520ad81a832540af962e82e5 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e4882b0043e660094b1cf9ab0bdb1d881a72b9ff --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6bb8840dedede160fa6ecff99e4e2543cfd91db8ce887982fd0a5b7f84fd197 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a4522534f30a0d66f0283939078d336d47edb3fc --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98f0ac95294bd8e16c7b0af42855798afc9654d6412222bac5a742f1f9ed9adb +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4efa1ba0a0818418d8100943433e79f8532e40ea --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37d33709c502641f073aa35f245dbf6d0cf1476003e40b205adf392cc2850e22 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..51920927644129927901a5d9ef54aef739489ddb --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f16e6ad352bf0ea8e25384e197b205f203549650b4df46df3007d423069b7370 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_6_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..72c05f28798691e9f47a84ce0ad076c4e1cd45a3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_6_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac08f9f1d20b448a545ee5b3d4ba5417536eed3a1f9ab700c5b9ddf5164afd81 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f2bc88d3ecc168172d9815944b90a249f1f3a15c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:087599244f33e6fd7a31116288b6b30df58d20c8976398a921c514a79c77a640 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d18791cd1d7deff3a55b2a6f070d468dd27e44f9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8902346d42372d9522a6c4ae40a380c6efaec66e66c02d1e4b435d07b97a0358 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0b036614298b6551b5f52aa8d2ad8250c8ed1df2 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e1fc0b4198a8a3a6dbf8b9724f23b1cd27461fd6939188bc426f0a92ab12ec06 +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe5ba90dbc97bd5ce02bf72bcbc6cb1ab7d3acef --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:223805c699358cf801143dce8f18ad68d2c74d9083b891d4216d4824d1a8eeb5 +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5f4143ae4a02a362524e418c5ded600853ee8554 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4221d9208b17fa79d297a7f9eccef5286bda45ab8f667e5ebb07ecbf5017c6b3 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c30148f348c837467711b3d357e829327d9b6f1a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:513fa914376fa2f68a22088ed685cfa5f403ece0e020de0efd2843300b8fb0ba +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4317211761b1e83b5112d19e59467e8a51bd1c3 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0f5174ef1e027e26b7f72c9decec1e1cd168ee0abdcede355593c9aa2d0955 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_7_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..de4648cf6ad041dfc316cbb9b269b0d0c96e3acd --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_7_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88e2ad92bc3eb3f6c3212fae018e10d31122877f288fc633cb631aaab32db6d8 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bdecf036c70e1d18e8910653f05e956f70ed3d3c --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:69f114a38c8c94d7de22f1a3d54e6b5fef5c8e0079a3fc75fee1649bf623421f +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..07475a022aa9e40340b72371e5733d11e6c3bdff --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6891c8d1db82eb2c9ad8ee94ffa35cec094f852b1b165f29cad5b384a6f220b +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..23166f78fc7398891dc4b7a225fb238bf2c1a4c1 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a8181b7d57154cadb33048e837aac7f6e569635e65c142365c909cb3675662d +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3fa4e4ae23e01dc0e60a45f5b176345ab73aaf00 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7de5bd27cf921b688aa49a598e6bd78be1da2180e1a08b6c3364c685737e3f46 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a585069c982ec6830f80482e7004cbd25ee16f16 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_8_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c0ab3edffd1314453ca9dbf8f4c4dcc8ce603ae6691e2997b71f8d7c2596c963 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1b3680471b530d0abe434d87750062f834b0c493 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af969bef7b4156cfb5420aa5d022fa76d6c244b48f55411aac6f13fa92ff827e +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a38c1b3fc142397b42f1489efabae8a67844fc94 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91dfd63a606fe9c2aab4527382d96d4922ee8cb109aee5cafd46b3181d0fb7db +size 12042240 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6b23d7902cb40d7d8ea83d221cd2894883a95d6a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f125038add4d7f7ba79af7fd1067d156c54caa304de922e0b527a588c8446db +size 1720320 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c56f0ded77884a8e6a3cfb9e0ce676e25cb9816a --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5eafc3e31673bc8fc0a3b3c91895d1aa599d18a837c06cd2f2ed6c479940b4 +size 344064 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7779f95a229a2f7df437f13048d611beca13a501 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:086eb2f7afe654b0dc8994b401a412e911b5a95214c23afcb78fca520086e017 +size 294912 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f9aed32f97d9f513f8b0074bd38ef88251ecbfe7 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12872982aeda384bec33b1f0b64a2d448b8abc77a2f5487669c0493207e04bb8 +size 2064384 diff --git a/deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..df93509d64067043b6f37b652ff5aae9ef8f6ca9 --- /dev/null +++ b/deepseek-r1-1.5b-unary/model_layers_9_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b073e52123219e49d4c0d15a9a4f5f075c5d9d8d6171ef8e0bb462e030f00a +size 294912 diff --git a/qwen3-4b-log5-unary/model_layers_0_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_0_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..7d6a6d361decbfdbfad4cb43a425cca8a93133a7 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_0_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..2cde1b3cb2c0eee38a48de5eef2db814a8d19666 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_0_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_0_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_0_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..ddf2325d89c2a0c2969bef8d0733a097cd8ddd92 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_0_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..071580312faba9f56e8c68ce788cc563eb9ed011 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_0_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..06fba07a9d0ead4f6807caab8e181fac0adc2a8a Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_10_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c7e6edd1590d032dc050d0fe0f0f63e976bfe8ac Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_10_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_10_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_10_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..5f85f4fb5160a0ee82d91d9ce572e2016da32f4c Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_10_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..430f24cec80aa428e5d67a9dc757dcafafd7e009 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_10_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_11_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_11_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..52499e93630e7921e0da2fe4b47f4d798fb1d83d Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_11_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..8390515fbea5e573c652af55798d86d402965e47 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_11_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_11_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_11_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..dbf915a35ef7d2e1bd2a93fcf15751d4343f01f6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_11_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..b49fe61b616954f24e41b837afb5ef3f415ea0ca Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_11_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..3345971d8768af3148afb9748e98bda72db7f2c7 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_12_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..78cee70f802f1d88aa2e38463a5b6c0bfd8b0b3e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_12_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_12_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_12_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c72775782c008188e316cf30a6b6fdd14c1f5b5f Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_12_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_12_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_12_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..504ad300474a7a2ec467cabc7699bdd8e6f8e8e3 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_12_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..3e793f36395f48933f9e9080c36d791b2a4c7588 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_13_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_13_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_13_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a570d2e3c4bfa60d0a58d8fec2e2608a1983dae1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_13_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_13_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_13_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a3a4309775e29f06791a78a779e13eac59d8ff86 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_13_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..3b6c721fc78f589e3af254eb83facbde74503aff Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_13_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_13_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_13_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..0357fa9511a40947398e985cb9b6ea2460abc227 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_13_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..5265090d0b367e2490fd9e2725ee07cd05bd3ed5 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_13_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_14_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_14_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..11da36bdf7e6d2f8df7ab1c9445f5190a41c11cf Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_14_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_14_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..b081241e31201fc433b5d2d1af7ceb760ded4ac1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_14_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_14_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a236be9659b02635488cb8616abd215f61833a76 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..ebe6556f03f3c4291c1a33b76bc68e74699b884c Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..750b9493230a0a68cb4cace10020962926927e3a Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_14_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_14_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..e1d32eeb4ab1cf6b1cf0caa601e86a706d23b032 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..396467c543df5757260409b8f13d7fd1726a63a8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_14_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_15_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_15_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..e3b334b95d9efcb5153e0b6413ad7f09c1dc9ca7 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_15_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_15_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_15_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..766c14e53d76639c9ffb39ca01a9cd72364ea5c9 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_15_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..7cfa191376db04d0553d3bbe8f78b0eed1a1e243 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_15_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c1673e307819d1e24016a74581d50fda66efea30 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_15_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..e7b87cce26088bd87573cc365e4fddd021dd3c36 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_16_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..0dfea3cac6a7816b5c7b40d708c79eae6938009e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_16_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..9c4c136ee1ce5d05289b48a595ce29a61d2856cc Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_17_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..6d7b9a948849c8f7a7ff2495c4a6199fb6ba041a Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_17_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_17_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_17_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..42ab2ab5978bc6d932b93d44f49bb5dbcbf7c719 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_17_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..ed18b26936c38f7abaad7927cedd980db087a2d6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_18_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_18_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_18_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..d3896479d9b1f8a80366bb11ba7c7595ef41c974 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_18_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..165776f620a5f86f1efd44f0aee24133988dd457 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_18_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..804ea2fdb0c2abf6e2c790eb34aba5de4a615b64 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..61dc48479c624d1bf992ed52b720cfffdefbfba4 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..46c66fe1a9f896ab571cf4af47894e002586cf84 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_19_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_19_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..48a0376387ce163419853ff017fec3d0851c3cd8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_19_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_19_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..78f5543a43c21d3d55d0542bd414169e5f1a596b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..8a1e3c7de257c15f5aec6c82b67653ccba81ed0c Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..edffd6d167292ff586dc2fb06d9932775adafbba Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..ba922b42d8f807a9f4228827089c50ee6ea65850 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_19_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_1_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_1_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..6cd201175102c40b23a4ee170ebabb7e90a7671f Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_1_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..7608e26ce674e5878f9322061973f57b3f1757e8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_1_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_1_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_1_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..696f1e824dcade6562adf0da8bf4dca4bec97fe6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_1_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_1_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_1_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..ba78fb8ed7135d6aaf3af1d7f6387d4e910ce335 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_1_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c77c0d827786007ddd0a2b708196cf1c19b4d520 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_1_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..d2083a60e541b13d22b46bb1f98f100e4a4f95f5 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_20_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..2d79f345893ba269a17145a2483b7cd76e347531 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_20_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c08be2d044d7f9dd6b4df149fda3be938f23f17f Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_20_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_20_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_20_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a6f409115abd170d3cec57abc461da23ad034b91 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_20_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..4cd58ffc93708a753fdae8e1e8e959aef5a4ca6e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_20_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_21_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_21_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..89ba640f90812ed00faaaf6604cfef1667fe4bae Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_21_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c3449476c49088f0ed0b2d1e860683fabcd8ce92 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_21_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..8c6e529592f3219b87ec57d2d81fb0445f52b790 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_21_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_21_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_21_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..40b4535c3b1ef638d1ea56083a67dfb0a91acca1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_21_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..fbf0a3f7916dc0fbf0e29712e3a98de63dd82cf3 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_21_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..9339cbb07b6a63c619e4f5857c284b7547b1c0da Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_21_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_22_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_22_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3605aac990e6a2b83c209737024d39b3544f0298 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_22_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_22_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_22_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..77ea4121ce19ebb37bf749bdb6c8ad56ad5a4a22 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_22_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..fbff9ea67ed67d075ec864fe34845406b512b5b6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_22_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_22_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_22_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..b928f52858f39b005286bf4aebb42e827717e90b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_22_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..5f76de08395b637c286cf07b8c748d4bd0216b89 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_23_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_23_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_23_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..7fd7ed66bf2f9531dcc4d402dc0d29c127d00833 --- /dev/null +++ b/qwen3-4b-log5-unary/model_layers_23_self_attn_k_norm_weight.fp16 @@ -0,0 +1 @@ +=è>@ È=(Ø=ð.ð?`?Ø?à=:è=8=Ø:¨>À=P:è>Ð>˜@h@¸>è>h;X@Ø@@¨@@È?p>C@@X@¨@ðC€@8@0@x@Ð=P@X@ @È?°@`G°@? B¨A¨@¨@ø@€@Ø@@X@¨@h@Ð@ AAø?2`9à=¨)8>`+(=0°=ð?(?0@P@(?X?h@ @à?@˜<(=(@H@x?(?˜>°>¨?P@x@€@¨5@@@@(@È4h?Ð@€@0@˜@H@p@è@è@(@Ð=x@€?hA`@pABˆAx@Ð@@`@`@À@À@@È@ \ No newline at end of file diff --git a/qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..4a55524ebdfeff40ae106721dd946e0c8b2349e1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_23_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..2c383636f2626f90cb545f6cc0f34cac390a624d Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_23_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..707a05603333b1c6f26988f2f146d421bf85ba71 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_23_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_24_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_24_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..499bca17c6570dd89d46baec16657cb680cb7bb6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..84ed0c8323d78bfaec4a27dd2b61495b31183d18 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_24_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_24_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..0412a21ab149581679de6bc4fa643b8549f57bea Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f06cf774065cd9f9e662d2b3847c7623b21670a5 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..95dd60cb917902ea93d930640dbc81c9f4e129e6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_24_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_24_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..f5f6c18bc501e4b673e235b19294a07b5fea6902 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..818ec39a0dc67ff792af85efcad2bcdb61eefeae Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_24_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..8ac519fe5cb2538a0e86bf6a08782b36c2c24b26 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_25_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_25_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_25_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..463a7b6f7d23c0fa7b1df9b5fbd15808f90b6f69 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_25_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_25_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_25_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a25d8735a35f2b0380b40819df02211332d6d368 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_25_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_25_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_25_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..59fd8bffaa290247c5719a6d865d5698ea39f2b1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_25_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..d5c866deedbe7b0f4c3997d21e5f01a20915eba2 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_25_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..5bae91625bb8f7b416c3b61970a4c2a5ca49f224 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_26_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..34f523b46a423fa7de5c40543bdd84735f8056f3 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_26_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..8e0cf2a134aca5a8e6e95b6a17610692ea26e504 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_26_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_27_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_27_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..476a87d7a409eccc97de9c91f423371ed0ba4d1d Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..3767f5a92ff5ef815ae653699357d2dfdfdc2fe6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f37527a53686c815e461eede3693f9638cf20260 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_27_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_27_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..cfb8971084397f0880a1bdf1f2c254a021dba92c Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_27_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_27_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c5b854db5ab51c3b337c4759ec972e70bd3c9ab1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..690f292c50a1eaddb75bb3d4e1454ac0cbd60e83 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..a324058c92699d829e14d1cd4cd3e5664585a731 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_27_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..30fb199d854d89573d5d9b08de47301da115fe72 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_28_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..e7307d2fc4914b6bc7d382406007dcb44c248866 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_28_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..223fddbf60737bc4246296f7b72ab1f07cc1e1be Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_28_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_28_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_28_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..c9160dd2efaad195039cd73bde743aa826a7eb74 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_28_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_28_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_28_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..f23764e023fda3642110cec97866208f90479f7a Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_28_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_28_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_28_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a0ec838b134222936aa4a98cd28de97e9d1ce8b1 --- /dev/null +++ b/qwen3-4b-log5-unary/model_layers_28_self_attn_q_norm_weight.fp16 @@ -0,0 +1 @@ + >@>0>è>ð>hØ=>?ˆ>À=˜> >X??P>°>8?È? ?ð>p@P?H?¨>¨>ø=(?h? ?h@? ?Cx? @h? ?°??Ø?øB?(?ˆ?P?8?€>ˆ-X>p>@>@>h>È>>8?0>X>è=8>8>à?P>Ðp$(@ð<>x?h?€>? ??ø>ø>À>¨>p?°>è>˜=Ø>?pÐ??Ø??€?è>à=H?h? 8h?@>È?@ ?à> ?À:(??`?p?¸>ø>EÐ>˜>P>H?¨>À? >€@€>¸>>€>0>@? \ No newline at end of file diff --git a/qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..886728144f59344803141d3ed9a22b92993743c3 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_28_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..96926b35772fad08376deef2b744b61ea51db237 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_29_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_29_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_29_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..d703bb82504f382b954d1629ce3947993e05c5ca Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_29_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_29_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_29_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..9167a6d95459f03f8c698064620b7c4d78b06296 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_29_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..a8e9c0ff0d01558196a946e2954739a598a54170 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_29_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_2_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_2_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..52fba755b6dba7d9499687ce8c6ed48409dcc802 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_2_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..a4e23a85f2bf4080e18053b453e188419f49a719 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_2_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_2_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_2_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..a2375f141a0dbb68bf7ac76f2464ca2375d7e11a Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_2_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..0fa5ce9200ecbd720d5f68ff558f547e3413c313 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_2_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..7f35bf9e7be325b26deb9bc46aa9d185ba046845 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_2_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..039ab9eb9ddf14805743fb52acf9a94771c7ce0e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_30_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..74788c3778d5e2c5985c4ad54dfa31637f459fd9 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_30_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..194451f60c17d1b0e1f9dbf28213cbec872d3983 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_30_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f8ce3fe07046713bde7c3b431fdaf3fbe0ad704b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_30_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..94744990db34f4ac17e8413a6005f19841c70966 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_30_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_31_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_31_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..4fe8cd33e4fa44ae996077beb1d68e5cf53eefc6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..cf13b507c29e4b3e3932732171b67009d5b9da39 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_31_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_31_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..ac52a7eb7ff5a36cc7ba29362d85815128c8cad9 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_31_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_31_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..48b113f902d8866babdbc9c8dd4795c3483d72da Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..e8f57bd585f33afb8a2d766a968c10ad54bd835e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..eddea731cd04c4f0d29bce218a64e5717e581350 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_31_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_31_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..5d92b235223f457d6749995796b4dbd224273d76 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..36af782131fad70d146e39cf299906ac215fbb09 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..b50468a5188b3382ffb81e7811b238a7622e8eb8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_31_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c2a4f18b56a9351e5de04aa257422df138950b00 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_32_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..d2e6c4f75d2f2f675481f6750003fd7297f6b484 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_32_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_32_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_32_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..997df4b79ca9bcc9221be8c5760784ede4d5a055 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_32_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f2f3757e371c15d4ce02ca05ee184e71897273d7 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_32_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_33_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_33_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3fe5ead4ccd0339f1678c5fec34025ad1ca1bdc9 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_33_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..3cb33ce4c13a42568463eb9a2d34426c10dc47fb Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_33_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_33_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_33_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..fd384281bdda70a6e9e8cd505d2acc5f2614020f Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_33_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f4ae8857aa2a14e91c672a2fa17f6b2b2c45c9f3 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_33_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_33_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_33_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..fa9a71517e9feec0697a24e10277e1f8421720d4 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_33_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..257f80ec59455c75513c7a9119625afe36033891 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_33_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_34_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_34_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..014235ab06f94be27f860d77b91bee6ace5be35f Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f30f62fb07f9c090bc738d9e795f65ac155955e4 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..d15ceac77b5ddd00ce0490756754712355178e43 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..e14ba09f18916730006463e1d40c212f7a79f02a Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_34_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_34_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..8d108355318d466d183957adfa48ab05dfba8d52 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_34_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_34_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..617190809e5489a3aac619a27247945faadac639 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..77d340bce07146fdd5742b5a01905563e4d30d0e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_34_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_34_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..8f05f363141cf1d049ec9ecced011934b334e94b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_34_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..57b7e97a09539d0a058b83027dc0010495426ffc Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_35_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..1ba657637dbd2024eedf6bd3798c4b31d4ce281b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_35_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_35_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_35_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..db93efddc4cc82dc5a9c5d8bc065e57c9720e85d Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_35_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_35_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_35_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..0482506bfd67d164f3fb3e400046e9928c31d7b1 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_35_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..57e717746102451b43b8f29d5efd8a467a48f426 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_35_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..25966fb360186ecf2aed140fb03487e0ace30879 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_3_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..714ed4597d4dc6b4f89c404b873b09eca8e8c013 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_3_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_3_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_3_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..3f9c8834a881d34023e4b744ca9d59995da81a15 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_3_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..ae16fda62d9ebf286d4dfddb2837c8addb32499b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_3_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..35ee61cc5b1e9c2d9516082df5eaff6bc5c79d68 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_3_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_3_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_3_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..50ba44e8887376265cb4df8a761bd3c327395059 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_3_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_4_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_4_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..e44ae9067c229054114f6d04946dc6981c4df6f8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_4_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..b933288547ca973aa881c469039bf73b53a73d3c Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_4_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..17bb30cc8fa448093a84346904b7c29d48a02653 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_4_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_4_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_4_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..6debe817ce6410c0d06405cdbfd9835a72fee41b Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_4_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..6919d9293499b5a7fa4f1a89a256fc69ee7f2fe8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_4_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..3c608f12baf2f3b2208c2ee68da60badbcde8030 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_4_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..fb4020d655f692aecfd5edffcfc6d92c3d6714dc Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_5_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..e32f7b6d91870426a6b0146e4c19c69bbf91c5f8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_5_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_5_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_5_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..b7a74aa61fad1efeb335d22d927ad2b260dfe694 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_5_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_5_self_attn_k_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_5_self_attn_k_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..f8727032d79fea0119c084cd0f28458fea2abedb Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_5_self_attn_k_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f0ada47b6feaa38026e5da6e4ea84c5b02faac57 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_5_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..f3c5afbf29d0f415b7b954474ea0ecce6d2d7bc6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_6_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..03a7ff0b98ab8dcb9eaf831dbe8ac16888f2768d Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_6_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..2bb21c66a4ddd8bf80401283f930801e77997135 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_6_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..d1e9475a4f1640be9fdcc58f8729a6f50fc561e7 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_6_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_7_input_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_7_input_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..bc8320b03cb74164ca2b8fe4bd7c7ff83651dcb8 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_input_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..b1d3412fe21b1f4e593176d44caa1e43a9b4b4aa Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_mlp_down_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..15d31e7be8b2ff06c4c060d9788035741dd607e5 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..770ab5754da0424c07f0d0c9ee7bdb425f51b88e Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_7_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_7_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..1bc37e264ee9dae20330eeaa0a9ec2572d0de576 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..56b840171240b446dce6a235a81457f2a093b9e7 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..d9f065b48e1148d6ee05471c4d125bb0a828877d Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_self_attn_q_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..1571f31639d7360783d241512345121b62e5d6dd Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_7_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..a71afee7a91abaa7d041f399800be3bdb15f77d9 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_8_mlp_up_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_8_post_attention_layernorm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_8_post_attention_layernorm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..461f3d92a416feda72f3e42103975fada160278c Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_8_post_attention_layernorm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..4af308c13f02b8c21cc995e8dceb46df4b438026 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_8_self_attn_k_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..c3f9df8fac2c2f549ba8b0ba8cecb15284232171 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_8_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_8_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_8_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..569fc6ded356dfbd7222bbee713514d14d50b68f Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_8_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..62096abd4493ba316048c9f4ec36da906f6430cd Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_9_mlp_gate_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..de0037d5e071524f24101501d9f447a63072fc67 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_9_self_attn_o_proj_weight.scales differ diff --git a/qwen3-4b-log5-unary/model_layers_9_self_attn_q_norm_weight.fp16 b/qwen3-4b-log5-unary/model_layers_9_self_attn_q_norm_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..4cc2f8b46a2d4070a2bff470095454e6d52195d6 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_9_self_attn_q_norm_weight.fp16 differ diff --git a/qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.scales b/qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.scales new file mode 100644 index 0000000000000000000000000000000000000000..84b946bae7eb8c3e91618462e599c8d0219c9589 Binary files /dev/null and b/qwen3-4b-log5-unary/model_layers_9_self_attn_v_proj_weight.scales differ diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..cef84a5ed0ad7c0196a543d006c591a2a908f738 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f985b6e59b19294ddf70a445cce0262541bba9a40d6d829bad8e15724d3339 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..a5403bba7901c5f7796270a2c3fe72adaa99b7cb --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d94256b278ba4edb7ba36c4824f06d835721b28f6c2d3c53063b15ca3a44c6e +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..cef84a5ed0ad7c0196a543d006c591a2a908f738 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90f985b6e59b19294ddf70a445cce0262541bba9a40d6d829bad8e15724d3339 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..5d3e5f1962731192b5ccbbf11e8444dbac643b31 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_down_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e899512f232f2584a8c4203a5e692dd89a0a849f09f2642f51238048f0fbf715 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f93b8dafab214e149a194d59bad82c96f9bdf1f4 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba77dd3654605384e2d94b219094091fbc16af03d55ca04e8a6b03cf37d5a0f +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..3cf4cf4a9dbe309b3b04a3dc5769d5d0878cdc20 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3f2c190bcc01c7b536cbcc3e0178042643752292592e51d6acc6a2111552024 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..f93b8dafab214e149a194d59bad82c96f9bdf1f4 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0ba77dd3654605384e2d94b219094091fbc16af03d55ca04e8a6b03cf37d5a0f +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..0a00a648ef05f18e4a8c5798c95c57cdc0221d2a --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_gate_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a304e01fa663c938d332ef55eaa510b5d49df3f070ac64f29ff018e62fe0a92 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e3a44d0a7a88671977efabbd8b25644581a6a9d9 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f71259814adc88bea8b9450bb76f8e8631253d350c629f323be5a6048edd55 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..dbeb0658ffd17ce35b4f4e14ef15ead877b10e35 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:476119239ed36ed173e95c03832adc8f11bec493cbd019dfed0e1e36c2e30641 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..e3a44d0a7a88671977efabbd8b25644581a6a9d9 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01f71259814adc88bea8b9450bb76f8e8631253d350c629f323be5a6048edd55 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..f8c468323d3d513e324a93af433f33c0084eb059 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_mlp_up_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36620b6a9d6d4e37d3ee369486d2f966165c1d841014826a3fccd8b48e7ec9cc +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..312c1e61f80bf18b40a03e46e2acb545a8da2f6b --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6dad74ec9177efdd27ea8bf4cb199cc8c863b8fb15bdabe606596674ad8678 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..8ff1fd9ec77d797c7e4b900c75586f710d7ae452 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f5efc0a474bfd3dffd73b9c5565de80edba709978fa86aede2023c70e714c9 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..312c1e61f80bf18b40a03e46e2acb545a8da2f6b --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0d6dad74ec9177efdd27ea8bf4cb199cc8c863b8fb15bdabe606596674ad8678 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..09f88cf208f62238ba40c27ac968a34d3eab084b --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_k_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:25dcfd2e576612c5e39cbc385e051facd1ebd68fe4df40a13ced34e78dc97c8f +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8ad236818940cda6733b7701422dbc7bc3a7880e --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4876ddf0c7099de13029562e3024fdedae3182a633a000bb42333bde2c81ac7d +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..e5d1ad9bac87c6c2b64cefda806497948be7536a --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06a67760a6ff6614eddd87477ae89752ad44f621f11900ae8547ec6d07fd7f2d +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..8ad236818940cda6733b7701422dbc7bc3a7880e --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4876ddf0c7099de13029562e3024fdedae3182a633a000bb42333bde2c81ac7d +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..4545da0d2d54518c3e650cbd529aa11163e139ba --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_o_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8a02c000c4ac52b30754c08eac4faab525132514d9227957caf3607f8f4be73 +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c2af36b64a5569b25e72fec7fbfea47377607df8 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190d356ee092b0da9d8a8fd74857d070f35f06a41bd023c901876f1c3af6041f +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..96188fde408fa6083f8a1e58464b93fb83c63604 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4422d6fcdd39e15992d63bbcd51f4fbe67b181682ca0efebaac7d402a1c1a469 +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..c2af36b64a5569b25e72fec7fbfea47377607df8 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190d356ee092b0da9d8a8fd74857d070f35f06a41bd023c901876f1c3af6041f +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..423b7cc94e46449146a000bd109c0b4b73485944 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_q_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92f321062b1f552f41d6cb29f4643e66e6594f29d64d7e139c39355b2d6c445a +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.sign b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6ec27e988fe131e7f43c2cfbe2046b6c16021dd5 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a00f8bc2befba979edadcefa328a997c356fa2409fa7642129c7b67a2f40488 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.slots b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.slots new file mode 100644 index 0000000000000000000000000000000000000000..0dcda90472e8c693050086bd398b473d5d138c9f --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.slots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e18a2fc09817d84ee204c8e9308709512b20269b0de2e837b502a6950f877427 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..6ec27e988fe131e7f43c2cfbe2046b6c16021dd5 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a00f8bc2befba979edadcefa328a997c356fa2409fa7642129c7b67a2f40488 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..79d0079b8e57da97f03f18bd0b33292f8762e7d4 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_0_self_attn_v_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e910b270fbb381766d5180f70b2284b2b6a167a0bdcbd546b2df3c40eb2d0e37 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..cac8cbdf1d30e7527ad6833bbdc186bedf82e3ef --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d406a860ecd6771fe801059d677585f5ccbea7d1377c6c9f2d66f302971f68e +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..fda60b71d5d197643dc17494a06f59f1dd5bdc95 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_mlp_down_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7723b429fc453cfee2c66d704864062a7bd134409cfb761f6f0b31b20afdf244 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..3aeab28c5ba93fe23d7946bb77c52fce5e82d8f1 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c3a218b920d88e90b53427d1544040dc66b27296b947c4e1958215e70a3ca12 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..f58feb5a6002eb2b1f77875da462cff89a77dc50 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_mlp_gate_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4e6745b9b99a90b4c01af1583a3ebce442903f115e025e61dee831e99a728d03 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..c8187ed35634c1622ef60499b0e3ab152cedc42a --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ee9eea2991a527906c189a92d2fed28ece7df363c023f8745cb793846d53ce9 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..9fe2296b9b96faae9d6d6587473bfd644b0d4841 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_mlp_up_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa8869573560f04cb04537f446fdf6daa510e6d4ac6c620923d8b479da1aaf74 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..877bda7f0fb6c773ae7086da0b4eaa0698928936 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d78986e1b63547dfa17d3a6aee4e25b473d4df07fb6f03c252c9d4ff0376d6f7 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..4824e9d5998828d40d25cb8aff60eae0688981ff --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_k_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff48091b92ea342801ab4e1ba2dff33a724b9478a4aace44caa7695a1d593eb1 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..2008cad1b2113ce852768866dde43a775413080d --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01913af73322c732cb8dbe5930cd4ea42b0d13ef026ca35f22976da2017d0b7e +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..d7fe0990febb5750ff67e4e09b4c289a1fc96447 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_o_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:de8de988d23c051ce07648f13c076d6660f5924b70ef40c7f765f65dd81b8f53 +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..0cf733050f7936cd73cc61fd24fbe4a84688fb82 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b36bd8c6d458cb7764b698dd654235bc04cbf93b4bf27e315f573907c083113 +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..e2d0670ef9e409feb9cd34c65bc6d2b425bf02f5 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_q_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1426cdff0bd6ece4a1a23b618b02c950e06a9b61ebc5e868210f5f5da6399218 +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..94327f6ba7f48da068844b79e332ad4751f44c2c --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e365d2f1179779ca8218430656596528491073a60246374bf5dc22797ebe89f +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..dd32af78b2fa45cb13a4a9e953e50393d1a10141 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_10_self_attn_v_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:751c45cf9482e7e1e63d57298a955a7b847780c6299e7fc225352d68e950a983 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..1c63a4ae3f376fc847512fcb3d547c66239e3f14 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44f00037430bd0017b3fb0f5729819476a0a6d4225133cfa4f75535cdf0308db +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..6cdec95239afe1c3cf007074ac87baf716a395b4 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_mlp_down_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d98776f9817252db0ceb69f0e8608c411a6459f65dd13f2a24eaf626daf3fd +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..fb3f468c707d82a5108fd9ba258b338ae51d4434 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:206dfb0a1a9fef77b6512e54388efbb5e7d3bd55293262e3e9f8e8c541a4f0ff +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..f5825a7dc47fb153ad110d087afaeaaf861e7a65 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_mlp_gate_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ed17a2066260f971eca252323a171cdda3b489362aa0850132c904cfe3bc4f1 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..a687991b41c86769e216a9687c356a60ae97094a --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c3eba95d78370ab0bbddee4abe3f78e59ad6c2683ee069ca94e83f8bd04fbd0 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..68a4397484bae331e5fb7600c90263ab41fd3150 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_mlp_up_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43100aae6ad76a1f0244f074ca524247e4d3a12ca06a0f083aedb3d5b56b2677 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..63c4780e5b2b6307625a3e3e73611e0a2d524826 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2595b1c26d49f1414359ca50020b012d8da3be823837bc2c05a1538750953e47 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..b0305ec091c608deb04e2562e8dd4ccbc322915e --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_k_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c17719271330adc06dcf7fde03d92429a408043e92dccfb44453dc840f79db9 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..cfbd0ba9c3e3bb8c2f9460f79d1f2b341a21fa80 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcbc1c2df4dfc2dd33aac02f8ca8ba3e11ce57f78e2e1e2e9d9ea0e960c0056f +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..c37ce53a0665a0d39af7a9245deffa92b21ede8e --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_o_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efad0b3e3e6d008d192c2f3299a3a32477af1f226c1ad4a8e0a3d8123aac17ea +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..a4ffe73398de504bea27f0c7359f63f765cdaa49 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f5b14d44f6bd01c4408d5ae19ae32505c4aa6e70de6cafdc4c6e14a397130c9 +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..77686aa9fe605f94a20d0f01664f7c744a438a59 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_q_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b0237c5128d991a6f50427e70233cfe93d5ebe46f04b699a04d94a94953cc99 +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..877685c9b236e2a7550020cea72399dd490549d8 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e87d5a00ef433fdd248124a1b201c6041c9ed24d25417058bc9c22cfa9ace38b +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..fde4851412fcf7caadcab3a3fbe25a6a884b8097 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_11_self_attn_v_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e44fcd0ae36750dac48ba1d93f3ac97f68d44e2973242594c6ea7c05698f072e +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..06522a8dfd8c9b025d5785aaadd5c207a2cb066f --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:85d8e84f4b3e5e03487db717f7996ab0e1299ff68b8d01595dac06dd4f22ec52 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..5562d4c3fa2fcc0f8782db54ce913647aff84335 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_mlp_down_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f2afe61979aade8bb636f7e309c841c58bfa0d046fd71a5f8b97de044898e096 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..93b9c1ac2919c82bec13930c55fb88dbb3c70c0c --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e333461556e901ffac2e7b73728d51305ef66b1302f8679956c967cbdcc7f498 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..40bf147227537b3d6aa609b9f29028b9a6a297e5 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_mlp_gate_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdd1cdc80a0009ee7bc2d102c09a4d66ff7b211a2d3ad963f24a3354504d6916 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..968c9e4f2f646a3b9dcc4e8abb586fe978d62963 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b8498db46b09fd79028b939f3ecfce9b3a8d9dd801ab10774ca0226c05cba73a +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..13d5870282acbdd9fce5ee27213035fec8289998 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_mlp_up_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38f61c35d43c126a8fcfcb99464c78a77f557d648cf3bb0d1a1773077f0ee42c +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..7ac55c701d60771eaed0e0acc223fa4b9872845f --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a629b8bccccaa0a6d7b1577892449cbf8b6383529c0e5a4d10fd070d352abd +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..9d8690138f7855ee5a4d2d6075181257544a4244 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_k_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36bd19b56ea4323df35e4e0f6d62cce820cc7d317ab6e17e87278384173e8e9 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..82b8c0ec78f5b25c11cd47a329647c581a43156e --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3537586568d4a6d6be1f6685ee089ebfa3a954d7fc4c015b96f0a6ba9dc485e +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..fb7fa18f5ae53ce01ecc55d108f95052fed5815c --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_o_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9888a7fd17ea2adeb7468d402c327a17affa0d835837cb3bd812420faab0b8c +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..7f62dc8c799db6036c6f7567aeede9d34075e083 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:80839361265d93a3a74a682b00c7f67a24e562e6b9f8869e0b4e96c433a9390e +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..9d4aad2cd1479c4a0399f914d6177729a4387ab0 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_q_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cb261effb14d6bb43e155c73d5ed758a95f15f6716501b1d063f1ae8593672a +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..780c1e66305cb0eab6249df36af803078709bba7 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:02d7b0fb0ae3f15bda72f6443b79dd59f1ac8179d363ab60fb3c832cfd6c5661 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..60721806bed62a85b7ac49cff81bec6bf7137880 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_12_self_attn_v_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bd88a5b27439761e13322b3acf9ec5d437f4c098697bb21f6cc83c6a41941ea +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..f9e3477994f8792a65e7b3b6bd243b36d133a2d3 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3caf4769665e308406f70f35c76adf895c5b430742b141f1161e2e4bdc4710e +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..1d2bf8aab6d413acd7f0232f7343920a8a5f760d --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_13_mlp_down_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:584f2dd8a0fa54894ebb4cf0fa91fc7312a053e77cf949412459ba73f58cd9e2 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..2ed0024837351772970bd68a4aa1a9b9e66a76cd --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7e78e7991d4746e781bef95f6a517c699ad4158b95b382a2f741a13edfd02c0f +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..12731c7bcd7a34504dfb471e29dd286a5bf0da44 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_mlp_down_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70a5e09f8613f2bdede9ca26424ef82744894edf55c5bf7e53b76b2222cbdf80 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..817e3358d5297d56bd9df539493fdc6ad7103a23 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc95b6d227e19389ff78794cf4f184295eb9571a3ec338f4554e0d444553b2fc +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..939ce8769daba377d210b57839056636041f8585 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_mlp_gate_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c2acddfd0e133fa46be3309b7f2f7925bb181ccfe134dee50d82ed802b2e386 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..78508efaa91461bd19a25e9185bace27d89485f8 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:412fcbc5059b17b7236f750164d3524b56e175cb247bdc626e125bb84c821c06 +size 3112960 diff --git a/qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..d783e27a16d53c3f7a866c3c34a55006aa91788a --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_mlp_up_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb54cae9e47c10a385867c312e9f67131d3957e06484c3a219a844a7d6176445 +size 99614720 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..0a171e6e0147500601bf72f28a166ed9af5b7f00 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52e98cb6df23a895061d2303ed43f1dfd797bbef86b80f30ad34d37e19e6d9ba +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..728c40abce17ba239c107f0b28efa6725fe4e856 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_k_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfffc69438fcde4479c3db09f37470e6191453b3b6a10638c61050b3eba02f13 +size 10485760 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..32725f17044f3803e999b1f9a1e4c5e4c9219c1f --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9c5d4372d9f6d5dfddc7a692b0ef3649074a02d09595c16f40d24e26293677fe +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..cf48726454f2b18afd60d3ccb6f16a4a8c9f9501 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_o_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8135542989ed55f838f8924f906f3769c45aa5ca99f5b81f56d3282da3c379f +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..87911571dbd825e63a1023a6281951cc2d78c24e --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a3305e0e599d614bf3c29e12281f04b06d9fcfa35a6925471ff1cd0e1fb4374 +size 1310720 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..46f17238d31d92dde7561ac2333b521f273dc29c --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_q_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f793f2caea70da3bf942cc6b713718a09a28879b607fb936dd10bc4e90fc91f +size 41943040 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.usign b/qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.usign new file mode 100644 index 0000000000000000000000000000000000000000..09683a64aa69cd85f4e53fdcaaf709c093d827cb --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.usign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f439ff1402d9ef45c6a58fa1430f10965f003dd223484ca14fa937e2acb0d354 +size 327680 diff --git a/qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.uslots b/qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.uslots new file mode 100644 index 0000000000000000000000000000000000000000..50301c323e063a36ca53c64c6aceae8f6747a4f0 --- /dev/null +++ b/qwen3-4b-proper-unary/model_layers_1_self_attn_v_proj_weight.uslots @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8e9827790531e0df00d6d6174a75e253b17ffe9bb4df31a93b146f03e9167a6d +size 10485760 diff --git a/qwen3-4b-proper-unary/tokenizer.json b/qwen3-4b-proper-unary/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/qwen3-4b-proper-unary/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/qwen3-4b-thinking-hf/model-00003-of-00003.safetensors b/qwen3-4b-thinking-hf/model-00003-of-00003.safetensors new file mode 100644 index 0000000000000000000000000000000000000000..32a2211a0a75b157ca6a0dec8f1f3da16c5b0788 --- /dev/null +++ b/qwen3-4b-thinking-hf/model-00003-of-00003.safetensors @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3cccb84e8926f3f18c334465639939a68af310b0729938fccc2de66a9a31953 +size 99630640 diff --git a/qwen3-4b-thinking-hf/tokenizer.json b/qwen3-4b-thinking-hf/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/qwen3-4b-thinking-hf/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654 diff --git a/qwen3-4b-thinking-unary/model_embed_tokens_weight.fp16 b/qwen3-4b-thinking-unary/model_embed_tokens_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..0e8e116074a78063e54fe3e480d8e73dab1bede3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_embed_tokens_weight.fp16 @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:306877428a6e2a0b343ec77faa07dc7ea85c83af3ee0c23ecfb5a9796b3f0464 +size 777912320 diff --git a/qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cc6697d671544b1939586e4db20eb5bc36d0ac3b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac17dce8efa06fc8cb0c7bf8d620c6d9ab3608474477dcc95afd06d7e5195e70 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..21e028b7c15e178ee1607b25d6e853c467a4fd31 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c93b8e15ba4c69fb7f9b7fe1a18ae65c4cd372a848314fb1d22b61d634283a6a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b1888f076cb08c734de85d943a51390076fb8a6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:490f71e2cd2222a40c23a6e32f71c67f79fdf1336d838f10999eb4269b874d16 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7be83ea42ad59ddd726f268b27b95a3388608ffa --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6759b069c2836dcc72163d9a519f6e953f361e3e7f2b01b1f22e8146d238b6c +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..becb4ab7417004e33094aa2d1d855a4feedec1b8 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f8b1177e2a51f725cc3e3ef25f5ecbdb693c55d379489619972f3614917ca26 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4473a6cb9f3e2811856f8f92a603001395ad97e1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:56e9e9f921910b8785ca18b0c81fb9add0bd0cccc58234ce2f9b554abc41c1bb +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f3fe9ac70596bd74250c75b1ee99a479000830a0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71c5f6dc92d9bf8d8b94cee295d663ef5c7026165d20801fac8b159e8971b1ef +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..390dc2ee0d29298903423a44fa4d00df069c4018 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:41a36ed73619b195231674a2a8609ad3d4b1386781518c39d5ae51945896d860 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..43f7b71ad66d102c2282c2cf2fcae859bd109f08 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77481c90b7704b7037b44f72c1bbbf771ba553bc3ab71aa0a1da13eff7547fa +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..41f614a881e82c9c1df1d559de088c081d189082 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c00024b275c7bdc888474820c7f2aff33e776922975fc796b99032b9704cfdff +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..95d08a30ed656062da88eec0737f299fe51e1530 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_0_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60ebb9918c73ac0902ce2b641f002553d4cee435cbbc61bbdf3f7fd67acc772 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..80db4eb0bebbdadeeda4c4b9abfcaac546c1b86b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b2277b60cb1057d0032dc9064a10ca2e61f516ae2aa84bff6f5cb84be66d25a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..61f2503dd06d3df459aa42b2031ae79e0743e374 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c432ca79ef5b94a2e2d171c90717efd9f926f28a2a9c3bccb4a2cd420965fe2 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..de6eccf4f0f5a84ad1081a8ef20ed039ba915eb7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a6bdce27c764796a14b8a6122f9b07e2a03a9d87a7e97bb6b4b439792aaeeef5 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7e2f9bfd06ad58b84c32ffdecdfbec227e64b0c5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a831d9117e46d9e2826960f14d2ed14b51017fb874ab9e82efd7dac0700b2bbe +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..579dc715d1578305ab0970887d55f1fea96045a3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01b2321ce4c9b805e7775b821867ce00ffb2309d38904ad0c99663a763654bc4 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1b7e89d0592cb7c28efca15a576015dc2cc92a3b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c7844208f6a5931ec77fd3d33e62ef3782bdcd0af7ede50f565c1283e84b52 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..618c11f0bbc7cefb0cb6d84a157fa1ed901f5b00 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57755cebabf3f8a59e49ce00b5b37aaf9bd685b128244e4ef8decb65df0d385b +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c86f16d8d0c947f794686798dcc61c2efee57488 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b34704d0163871e7660cb2d73ade4690d7d94b32db9c9da2be1db5cb24df094 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..775c88be350262f71076a6acee5a7070c3269937 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4559de8377ad6f31a57d42345ae9c52ec6394584203c255f7bc6551491cb875 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..88e001021783d25d1fac6102dea636ac129d2775 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9fba9ed5e9b86b7b9868ce5fc217020ecf17a08058b8103537a94d5617cb2a5 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..289f240c3878b7b7c62e7127b3c61cdb4d8a0cf9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46100eded0575bb5eb2410aaf1fb1e2d2295679f903d465f60106bfce1ef643e +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3cd54d3e298d28f402b0b4f376638bbcfa9df001 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a835f577873799d42c8e4a2500ec6bb85c866a7623906cff14bd9578d554cc37 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c4de653308194d09126fdf93918f61a0c2a22f9c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_10_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4beaf6e28e23c6396296a1acca7288bfe6adbb04542e05ae5097fa002460c396 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3387dae969b89917ee4d799972a294d6b1a549bc --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a86971d333243aedf3bec6a6f2ad9f57d35076e6f0a309289f3eba289429ab0 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..13881a6f3aa3f1c28b0b2befdb5dfb36b9aa3fa0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:928a6f81ccbe98123293bff03fae0e78ffb4913740e65926ae1ac3e721cf97c7 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ee9ed46eb91ec56ef332791cee4af919705c82a5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6c4a7e4c0f4461c1866b8cb8b062d00d1b17d6cfbac4a8a93f957764f332adc +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..33589166c27d4e758b35dc038ac48d3965fe2936 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c1d2c0a0283892bba7d4caa086ccea3ae6ddfaac8a8d535f7af5ad362f4cfad +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7bde4df61ac704513c8fb08d8abf9670e49ade20 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a09146055c54063c3eef2eede6cede39d399d21eeb9b779dbe152ae8b4503efb +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad7eb7ff38ba3d869acc8b5df48a3c9a5e92150e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fac276b99179df639ba035746ccce6935c84b756e633ace2f5be500a95831d95 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d2adc0cca694a8fb7937aa003d587f3f4f9e8280 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe220d3243589720602766fc28a7cb5e0ee22da41018e442598f16a6a6e4d163 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7d2b83489343c7ec3eb4cb4348aee7aff5820182 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ce0e57250f312fa09beac4b2716c20ad600b66684edff1bdb6b8e74ab4dc85d9 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c5c5a0f382e43b32b8fcf9eb89afa0a31e88eee4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbdafec6be49f7214dfe6f088cbfc38400ec62a5cfc2ba70ddd7cd8aa62d3de5 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7d448ccde5fb6121d96cba3f7d825c53d77e7f33 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9847a1404734ad7262ee7fae05d01f9b998336870ba6d382981501636f9570b3 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..895d737f47c1f443ab219151220c6ac53408d999 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9a3beb9bae57be01fa198efa34f24f1553e9c85f71db35da0709ac613b8e7e8 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ecb342c9ffa9b4b2b5708d3cb0f9f4e1a7d8d560 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a5831ed9effe8a0fa0567fa3dc28fa724c2a9d4dd5103c7de9d0a883e14fce64 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..464a301cf4aaf16e01789cb8ecc4e904aa4e4295 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_11_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0a97abe8c7ca92cf90f506eb07c5256ec3a2c6cbd0af843fa8fefb7baf37ff +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e8a885a071baac5dfa754e8c6eb65b94d9ddce84 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c47da58006cb7354d318c77b44d1075da36aafb2ad26e4832dcb21a4a40088cc +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8a25ad8bd20cdf0644975c788b3aded5ffb6364c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3370cdcba77e2c436256eb176e6abea6539606770e496703b90451e7c54f190b +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..21e50a189c460bda2986486ceeb3d4c91c6100e0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44d478e86e2b8f637593fa20eaa9dfb5a69b0e98ad1552b2f948aabc922caf94 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6a93f9ab6b679926669687d684b607971fbeb671 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fe35f463a3d4f88faa4a8cd2dae8b85f12e32387be3b4f7706c3cbdc9946614 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c94953417441abf9471be091f4712d5c23446fcf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f2396f23feba32cc2cf92905876e5841bf73f133ec6368318036ffe71eef68e +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8fe3d7cd9ff325b9a54581a2d58f5015b19d7392 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f63f05076a1e0fdcd0d0f49c8cc894badcf8cfaaaadc37400983f33157fa476d +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bff38884cc288c499ce03f5779c32b2f5076c0f7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d8026dde51e9ed207b353421ddbaf35652253b4cf67a3b91291d268d6fcc0adf +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..72cafcf4f84043fbf273c453e0770e610ee08fed --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e36443b048823652a7239b714cabbfc853957a524b44a76e8993fcca83d7f717 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..103db593af10df13525850c45e8b102d04282f2a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9908772a92b1996e99b841b2158125ffba7a9cb676f1520f2c88938777dbb1e0 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b153bcbfe0e665a92cc07ebfe87e6226b3db64bf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4510f86235ed2ab8ff45e5582e89da938218700b14586cc97801ff3791c60c21 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c910aaad0e2b5c770c3bfd32ad8e7af8bca03b17 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6e18bb69b495f894411439333054d96bf77d899f3f0298c91b3d1f61e706866 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0b71bf4eaabf9191091ae70f89fbc2fc348cd725 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1a664b43ca022fb5d20f47b83f7326f74a562e4fd860d7c04ec989c85cad999 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7d1a973fbce18331fa37334aa05fca8f00d097f0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88cce9af8baecfafecf1ca2c491fa29a22f254b32198b14e00a9c20f840f4819 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d61b5a6f0ae4ba86377375bae666bbd05953b671 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_12_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b045d0bfa0c0fc2790c29ea7c3a3c9089f7920fb4fc63767fb155100715250fe +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..111a44fb21479363d479f6c66c06daa4bf3ff399 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a02770211cd9c06ad0ecae18f511e78ef19297b15db61f347a8ddb665e17a957 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..47ee6ac0be64714160219e89db0d6377428fbd2b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8639c10129aaff1571e9e30592fcacd137b870f60edf1656229b15ed06ee17ca +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ef91704f0f43b8d6094ca749f3fa1430c6b28b35 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7736112c04e9887964664028bb541e51b90e685a0c18fc1fa9f4288fb1d7fd3a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1b4cb9f8ef3740fc07a74119bd92a37012213be7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3e925141d419358743f165a219fc76da120411ea0f412bbebb5e33e6f5516f0 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..345d6acd126302b96e5af9c48aed2c1c6fd51e35 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8bb61422b1b7ba606840ba8413fb375c80d88880cac7bc32844abbeba9d8c9f +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..482dd7fd757d15040690641cf101dca8cc36d24a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e2a650a4f2610b62a3f89a9044c90f8090f21d8b723fcbd802b865d845e58c +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0aa470b3f4fbd73d40a91722e1c36dc36ee8282d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a8f08eb186c4a103d58e4e19e82dcf749b962a56ab6ca860ba24495fa6da6e4f +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f06fa51624b14b5827d7deffe27ed045eb4db9e2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f38e8dc93780c6025ab127767e3396f80bfbf8e6b64ef1510e1699a9ee788abb +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9a0830d5710e92c26291174006de84688c483af0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4968c7b80812d15715fb702cb0ba7cf12209a631a42e912dce85b1204efb6dcb +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7a96927f88da3617bad39a617107a82d89c94a13 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bafda9c57b23bb9752c6afe5a59bf5d7c8fef87ef57b0779a1e6a52caae88e61 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..477847e8c4bd5457120f38a3046df569a5bbfaa9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27509ef920586f8ac68ad0012756b0c857cda4eb6a5dd5ade136d646660b0e6f +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1b8126792ef0a6353bf631e413d0f25848bb13e3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5242d800e171a119015eaf56b5850c392531d2df30a4c235bd89d964fe6c3ac6 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2accec418b890b63733276108d02faa464b44404 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f0b095e5f371dee5a3e0f31d417eaf0172c33a378b730ab5045a2e16c978ac02 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d5e14542eb2beafb2cdaa5ca4a269b089603df52 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_13_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:faadef5dab098a3b2e30238a8858420117131fc73ff7dfe77a6bd515dd74971c +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..67f8869f554d802871c521d4ab5311d97963dfa4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e998fae6cab3dfe9da3d778d499efcfb892c24b65b4fb08ef802620b51e79ab +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..149f922ed97c550cc496edc16aff4fb26d032a29 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:111afee7a16f17418600cc900296bb8f31bc3ce16ab3da3f0ca909197ecd3b81 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1da8286f97247f22cd6a56a02a4beb0f66d7d3a7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:acdd5806262dd9bdcedecdb8e245825df7a3ffeb4e43c51c5f0e11d12764813e +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a8905ba7dab5f856f3c454bcaaa839ab1a400307 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1cb451a284902ebe5fe45373e302f6e9774cac57b720e6cbbdc7dea83c91f96 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8576b3bc62e7fda349ebf092d998b5342dcb3963 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:96d95891775bd62730bfb378afce53b1b86da694804d60b4c34bc5f42c9ca3c6 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6d0d17572f96ae24aee8c7cfd39506fc3ec2867b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ab05f472b84c78e3eb45ef027bf950efefc92f050033e8958a07a067bdf52910 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fdcf12df75f37499b81bbdcf6c280daf7e45681d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4a603cd9b5a7837f4eb053c822f1889f062445d6afda6a1cf667366335e402c3 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b94cd7fa720b80314be705e85915796e27d9a3f9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:33d460ccbfc3caf5c7110ee1db5644fb7aee33b4556579adfc1aeb896f94dd12 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..849536a8fcf495373a8af4d5874ab035d0e50ebe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29a113e848ae9c57326e193a18b82a9cbb91ba5d08c0020f3ffc28137fdc3da9 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fa57c8edd3ea0b1a8855dab5c8d1bb94ec3261ee --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:17be39f707145717486f34597b500be7a1d66ec8c300c1147c850b0d7b47f546 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0c4f40b4076ea6e7bf5816b2fc810f43bf6982f1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72f9d50e2ffc92a300c886bd62ba89950f1c2c2c2fe1d8cd61e3373e4ac88424 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..491364e00a16e1110acef047cea14163f24850d6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_14_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d86c207c49ddf067f31f9eb723bf86fa0b9cb07056adce68220e6c8fa66db82 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..987ab9e73950ad24e3218e356ef1cf92f9797f44 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b2d8f1005e0074adc53842871000e1f7bc2cf762267a30bcb92be36b3791c2a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3851d78f665cb26b3be96c6edbf59a1cfb472243 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e7c8735d7783d7eac2280e1c10bcc147e400f26a3244f018c3b37be3faeb7ff4 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1e1d7f8cac36214e129882975d036f6826b30afc --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5101c767d9545ded20b04273d20c507f1e2884eea22eeb24931fedbca5cf68dd +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9a978f6a8b737e848422d8d5450e5a4ae5b86888 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2b358f4f7c6e6dcb880bfe7cf18a624cdd525bf0d6a845815bf13f24e4dddba +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4e8349b412fd92dbba6bb7b8b1180976a8d3c80f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37893ec0f616099d9598a8971b51e25c82750efeb4816c5ddc1657ce2cca893b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..32742582b6d1d0960c0f279196065c5db3d26d16 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b464e76003584b0cf9b7d52d6d47e66bf16297f013a1b98ded9460ac1e5156ff +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5efd31aab52da6de295916c565c1155856e4d3f6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ea0518cb9d631aa6b42259b50da7d18a2bd43f0b89db844a3e9b83986eb19a3 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4090c4e0163e371547b51078e7f19dd172548bde --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:551332ae9a46dad1e6bbb113d88ae20cd6b0a12b7cc8c9f0dd2652e67e25b131 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0a89eb0e41f1129ba13ebaf65ae8a674d133ec52 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5ad178e4c484616642e43a2236c174d8fe5686f544e23c72ccfba60b2c573d56 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1f82acbbf2eb8be45292cb798999c08508d64965 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:00c0a6f6eee672bceddff5cded46121f5d9202f44de8d4d05d39e0cbc3adaa78 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1ae8994d8a5cf83b4b6b125fcedf196ab1ba89d6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:278065f4842a839cfc0648c2c63fdb600e9f0b41187d7a522bff8ea5cf9c1ffe +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..70b1240d9b626f12fe4490b902ae77be6c589191 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b685c7de3b21a185bcfbd9e2108c5cfdc9c23fe7a323d51f76102338a4023a2e +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..72ac12a2ce543e147db906f915cd55bc8a28ff4d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aca3d1516a0e6447216ad70d73a877b840f2ea68d0b6538055ce2b7e78b606d5 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d30a1e5ce813c555d898a1f9aa3584d9a0c1fb7c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_15_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9d7400f703aed29c503b77046b81803b11143cee4b84aecd9dec53969f1b2c1 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6b4d8a86ec6abbac4569554fe7b99fb8d7369588 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3fdc09d2d3589877d0784040c88477abe6368f0eca8481c51c8eb912d0610fc5 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a3a2cc2fd01d035a836e7f8b7cacc9ab6d8b8b55 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8750489e1e3987cfe0cd06d036ac02a4b7c737377bafe9ea26736475c4a8f8b +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..74a512a62491fe3c5b7797205b233f8bfd675e98 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:319fbe89e40354fd4c5bb47e7ba22ae2f48385d214fb9df1b7b5c817fc507e05 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..82ccf9945eeb52363544b857fa995d3a9b611f36 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c974d601988adbbb8ed536e0a629800039f93a0271d991eace5b42801d86b45 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e07ba9001e62536474df2822761e965bea929b94 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f97978701f33048dc17d46992be130d79a87703b63b61a635bd79bede5ba6a7d +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5a5693899c7d4db080abbb6547375fbf46ac7ca0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7c75af271627731601c1f4d86f11215df5e7245a817a0f547e6d1ddb302a35c0 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c64d8f0cff0aa673ffce73b43797775297190e4d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6c827d5939678948d7aef57a082d0c691a231159133343abfefb46ee7c725f9 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..98f7a67e43e8f0910d04d0892fcf05f50d9f2b1d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:023059a4712b3f2398a7952fc5ec1e0737c41a9845fd3da281dbbe0fa5baaee6 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..73c2043f37e89d225e5926ee6e59868ccedfc6a3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dcb24487f06b0ad940beec7934282ba4005383e5462f835de0663bd0386c598c +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d997a7f49d826b80788f3da8ec4eaba84dc07de5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46b768b210fee199e4b0a294d8f16ba8c61b3823e70698956afeb661a26a45bc +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ba974cf9f66a28b1f34a199ff5bc7e87541ccee5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4d6dd83e50db84ff0981f59ad6cd980289a71d87699f07b305030401d8a4e41 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..bd0a412828867ec7d8626ed3b7a407a39f416b30 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e11432359758b540a4e85c067a51f3c6e23d722e53d172518c89796568ef220e +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cc2fc00421695b006a81d1058c6ccb04599d7550 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd832cc4aacbcbf278615cb2b04104a308cd63cb165b18cb7db7460f3c5cb6e +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9b008f68134bbcd341ac484c48fda35d68a345e4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_16_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b5c9122a63f24483e99b8ffa41a2c1538b02785faf4c5ee48f8aafe5faff9e2 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1af9f52dc6fb4a867b00522a5ef5ad539f95716d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aabeb02a7bae1060744442d9ef641306547dab8e1bbb5ed18e0f087061e709d1 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8e5a5bc7c2e63e70817372038172dffbe8b8a2f6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b7f76d252071ba3c0a18f03105643ebf86839adeee50fdce88b098c55117fe25 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..41fb4e4f7a6369bf76d643b42f2880686ebfa9a9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a04170848189b3347c0a51fe54f3cc5460224819fc0759f8c3cd9b1674f78ad +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ffd0795c735916bdac930bd0f551fb8c6277c591 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2f6e5be14b99237b539a871cfd2ec1485e0b86b4d814bcead9c5d8b8f73326d7 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d953edeb8aaf14885001050c4c8fa0c47167592e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:112b6a42f023147d128d09f08d862fdb23dc1f8bc121887af7267e6f2abc0e47 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2f2addbf1f74aa2c06999d806c42dd032e1cb5bf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5910960b71d93dceba443230afbaa82e32b6ef1725f04e6a975a5b0dafe55f33 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4b4307c7a58a6c8659e810059423db34abfeb0be --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18cd2d907956c67b928c3b7812e32023aedf33c292fd6247bf0dbfbb7aa156cd +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bb0aba3b7ef7536b47ee143bb3c0845fa2a05744 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e9f298838da2785624e1d1a8bc2f8a72c841373c6ffd5c9d58eb705240f64e +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ddaaef85e93bf54c66621df3b41964b495bdd5a3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eb97e50bc847b1bd9da15568db32b7ff384450f24df82c4bd8b0485dfd5f0048 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4dbf2c2ea5dc5f714af174f4e12e276f2bdbeb3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:021583b0413c6b8f5349dedfa77535f7ff8ed0a14882f03de24865433cb3748c +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..79c265a7d4a250e4400262bb87d2f5eede4e871a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6d90850d4b731c748d69ff9b7912048218c9070529f1438768bbc77cbcb0179f +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d8b11795fa398e3399f6a957b1d15f2b0359ddb1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_17_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:273a67a7a80843876cf0a2fcd0d2db7bf2b6a7d39aa13a5780f9ae65ead0b961 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..364dd6221c5f3a52861402d9f9eb13512ecabdaf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:456904c569bea7d614c0b64eef7c1bc07999ae16e3be8611ee294f27efab6beb +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..60b3a6ae81c51dd275c19628736ed6dbfbc57fc6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf396ecf58771a1c53b69db19cfd706e739e88defa62ce1647eb1dc2ebcf3059 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e783f4b4916bf51d544ac0391f22e7e995b9fc95 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c2e5f1e7f2b8a83e1ebeb160771df2956810ce8ad9a7d0ad6028386bb32838 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1ec3cecd8b0768f9f55bf287c16b6ac2ea815c80 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b44667dab35354b60154e78869a5de9c7a12289c08f4fe457f8ac30824849fa +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c832a4f2c4f415ec119e979a5955bd7bb52ccf54 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6fa4d7b3942de74d32b712d9b12176cf7b41d16d7b4de4d2ee107288643af63a +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f71830a0f66cb41afa6db43b6a085f448cb8076d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e5dd2bdea93e1d97f466de6dae2cfb34d1e5e8bc142265cf6d21c1c50ce3bd9 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..566b8159b9e9dff4659a1f2cea31f6b2017a2a49 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6543fd1abbe9cce7e0d0400845b81a6d9292fb905c20fe942244de24b250ccd0 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0470edcf185556f8e6cee8f0b1c1010248c4dba0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9610ebb6e7952a8d863ab5dd28c8d4a61f341555fefa42ebac28392d15348b2f +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6d1d021ff6c9d60fde2b4fea14c3dd2dfb3de777 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4cbf9ec5e9abd749c5546cddf5cf167589763c985029d3535e49e6a28332a9c4 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5f40f4d10b7f479fb1c5f72f44b9e8f3326dddd7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a9620daaa66dde0ad890dae502a770789b946c74688a1e48b896655245eda24 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dcedd3d134adb57340f48d9020e1a198f7cfa9a6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e2e5adb24ff882b886c23135a3b9cd876bd908804c15524dd291e4fa264888b +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d8174d4fea7fac24043360452e202503a4ab38a6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_18_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ed16f08e7a15ea7bce603951f24bac2b78ce2902fa2de4f62342058541b982a +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..383e2c89c3e428f5bc8a43c343e66962e14425af --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5323600fd4fd2c5a22c5cbc5262b0e69e0f4188c8df158c448c37047c1112579 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..93c193d60e6480f57d69ec2ba1e6c5a433b6a345 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c36a0c049d053bd618992d3d05ec3f6c5e11bfe3849c18daa3d23bb3532c995 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7b8443b2a6f2abf83d956f7b16ac449beb04623b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b0e9344923bd8c5c47e3dff27b7eb3a8254cfcf31f52d3442c7268879c04909b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..183c9bfe7c09ff9a58e879e7dd21285410d3fe75 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6e14a909feca7fadec0b5e0ad0e36c10aba57c83d43a37c04251108642016f3 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6b3112b55cc39da44bfd77fef36114675b76d941 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:92788707e39135a7bd36bf436d02298ed860b51a514ec2dccb610ba06bd626dd +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7e4f78d89f5ab072b88409304eb0ae69eb886e86 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ee5876bb7738320046bd4968442128f6ccbe8b196846f6a166f571d63df7cf5 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e4e24b67c5cd969e85893f721ddbf004480077d7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac86333878454efdad08e76bb386a8d740181d5ca9d622b4c4240f21f46ac496 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3e7d1a5186ba72bc366962145050f7fb49947eca --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:32e2f9089367fee9030237af643961e2006c99045b9fef8e958ce708b920ce6e +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..deb4d826cb5bbb74e664e940fba9e384ec9a47e1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1704fd24030118d0137a52294a3d5a81740d058af5ef341a67d1b0d180d464d6 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b92788c31c5777398954152c3211bd9f95d8e5a6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7f3973d927c14ca877d75db8e66037b894cec6bf589c8a6c0f6f6841438277fd +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..51e975f4237509cdb08dcc4f1e61970a66e2ba04 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:190bdb05de8d9238e5d0386b9ecdf529a0f3ef9e4405e8f35355e0aa94366eb0 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..eb194cb945621c2aa48515f379613ac1c64ed20e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc56c280f38b820a4e9116517ccd04f01ab8cec5d6f044ad6eb0f580b659454 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e1b6f83a6f6156abb41c0d55ae870ade00e94941 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_19_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d1264f5998a0528aeecf2c1c12ead23b6b2502cc570571e85b958e6eddeb6290 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..52f40a8d1e7cd1a63a3d5504f2baef29516f1bd3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b6244a96497854af4f841c4379c7546bb15c2ded8298b82f2b2caaba722f5715 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2fe07f6279c471f35df240825015b3e0881f35bd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee62eadf7bd3dfd93df2e7990ce468e3c581aaf648e60ced98100fb09deebcec +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..be983098328e4d98635f4a89046fe180e04fcc0e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a9b9620513ca3e3fcac50d54cdcb5da1451b5492a88407afbdffec93a368acb3 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b5081c8c3cd697a7b209f455f491cac0b1e2ae23 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:239cadd3a660f93e08fa779019d2c6828a4a9dd3ff6651cbb2f423a7d18d98d6 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c1bda2ae262fcfc83e96f0b006a1014cf69e1a91 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:350242bbd2d580c4f2cc06af109183a1fa85cfe3ab4ae63bccecfaafea20e744 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..47760fcf6ba47eb1bfabfbca01d017c8daa45fc8 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:934ced2d8edd17deae047accbf641e1d0e36d5f3ad982ccd17a5dcf0485617cf +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7b75f02882cfa977f609401cb9b309d8f10de222 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c3657ba0324a09c08c43740ee24dd6b0f20946fb97e4af6daf4b8073721f94e9 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8075eb2139e19420ecdaaaae711eaa6f1d840d04 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8243188495becdb6aecb53f81791e29e1f03b85869400a66175ed2bb68100336 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..eb482f5018a2310e989283952d56a836dd13e24c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bee9db4eebf9bf0ace9ab66115b01eefdcad66fe8cfedd0acccb1025eb3a5534 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d90a4ba29667edc31eb50d8d204ae0d9e43a8d21 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f39c3b6643216e6547de5b566c39c09b3084f37108c3ff52a3c5967b01777cf +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..203662d6e5b197327aeb2eb5ba160afce651bc20 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3390122823c815bd0e0528c1d6d5cd5010e749d7dcfd745fa7dcc9ad8ed10ee6 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1456a2f94bc7f4d5e24210a537771f827009b31b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:90097f7ca6246a9dc9a3409933ba3b43d243d06da6d0a3ca44a947d0fcd5ed88 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9b771b027e24f732d0cbf4f9d9634b59df9ffc6e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_1_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:66ef0955b181d5fb6229d2366ee2de61422d0ff541cdf8ed4d7466957885ea61 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e555fe6e36eea1c56e95a9fcf31faedc8e7888a0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6df7180b44d7b0d3787c1d116f9ebdeeb2d0c14836218769e716bdfe77cfebb2 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9cf323170b72fdada3482aed9747228a239b7a6f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e327bfa88c4a73b71c3c54b81b3e5c314aba7e1a7352fc4a51e94c10c7bd3f +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..58f4e614eaef10952786cd1116e85366955b9df6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:53371affa55ec451a68a48ff137858c32acfd57c867c99209c54c42a4bb7eef1 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ac23f309a84fb42925db241dcf7029ce0f60c86 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60a5a080597674aa0778a24d4f7d9e937ac3673606ea853f68a51046ce36d3fc +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..72c21e0300a1b80c59030048b50b68f7f0ef83bc --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f9f7267e22e80a86e8ca01f75b76e87ebcd47f36e54b591034d2da7196e92e8 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..cea4b95bc40d682fddc7f2a486185c006113243a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d37a97a0c761c65a5de6245097972b4ab2df2250c54d6e5751f9963e9792791e +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c4c1178fd436fdc4e54c4a7806ae64ac1e658823 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15cb632c56c6723b1bf73c70fb7890bdae477bc0c36eaaa9b95c31de63d5cb74 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f40624549fcb7ab9cbae9fb6aca8f25f6034277e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ab218b6e63d2ee377cd7a9c12f28bc7ada0401fed421e71ce8ee43e7c27d50d +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3200ada1ecb577d48391945fd93c4e76d6a75a43 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af2c84d4cc0d868fabc41dc9e9309bd3f0857f256dc8ef96ba52e0d1a90bb89a +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1a8769811f2b1223490e7ead2a9d6f3c6b2b28a2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6dcdfdde33b6357455aa95aee82f61edabbc3158254620c1d447cc67d74f438 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7a767d6b87e2a12f93f09a846c63951c90d987ee --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca9c66effc23a4c0026d3ebdfb1f9eb4524252d30def89ae694d91f0be770418 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8f9f7fab570b8c5e399156e4f853da95b1dbc5f1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8c7afc9b82d283e4b19416332e9585be44d37f9278eda2c0c5b84f15ef6e24ac +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ca9742cdc83f32ee5daeff79bc7f31aeadef2c25 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_20_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0b1a366bda9a144d60bbe28b665a27c1ca19bdc8bc84a81164e4f747696d9a8 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c9db13234c96a179bda3303dcf3b65af5b6a8aff --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2c14385740db94824e4596dd16a6252046b43cd9de10f2dbec78d341a72acd5 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5db4cee2f9b445262dc591f8309004b9bcd3809f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04fd41462aef4b008e941564c9bb99d9827a3ede5db04a9998376a3b11d43f93 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..75653d12828799a756e7fbc7802dc4868c0c4f37 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f6393f6e63828607c855e701ad84c37b25dbbe371bb70ac5fb32ef10251443e7 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2d0a039dd3f712751ed460eb0f620406003a822a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24fe7f7457759c4b612a3e6a4f3b6aa2573257b98f3d0e3a547cc6ed28028923 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b8754b3a73b8790189a181e4f2dac53166a9a2bd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ec2ad4c7e3758297ce70443218ffd969bb27c0a115ce95b94e0bbe27e1e153 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2c1ae5796c1bb68c3eb69ddd69f6f3e8acd1a529 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffc9062904ac19ae482f9b105331c5f23b6900e148d729212e500c2c3ef41f6e +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f590727130ee6d45536955880c10d579512a6aa4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9208b1f0bdcbb7b4c0c5394232030edf9b2fe05cba962f8ab9b8c835a4f757b +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..62dc277c3fb7f3c84b3d3a06aa91696be83e3161 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9f09625d1b375c3e4a6d1992482d7115935145752eeef75a0b9dae257c6b69b +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6a71757ce706309b2e0df3505be6706754b0506f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7dfde33edec05cb9fac7818dc35cc30b98a12cf90b7bd84fbf1b7e78e5eae9f1 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8af11a657ab910da2f64f94d0b6baef0a5b7a7ca --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d18f129546ceeca503e2d2cfb89b3b4638ed2eff8cbb1aaef00513ca265fb1db +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8063a9f0275a58c38c49aa4e8d8ebccb0479240d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65412cf66007146b2c52ac853099989694e34e23006e13da83778b87bd0dae22 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8e3f35a494b2c93f1745f43d8aa4b5083067658e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:367e040180281d62fd6a9e546679326dad6272e997b4c2f883ef3d26cad20f5d +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2db21292af98372e536d3f5b25d2b445d79534d6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_21_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:744d3cb31c9414fe72bab716290d7e6f432959971fba16f8da23f80876eec2d0 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5d2360da4afec0c96c3c1bcad30e33385d2fca76 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e8eef6e4df4fe73aa49a2e38b7f27e904c3e1d997fbcf48524040c3f316c6cba +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..bd217a6e2fa6128b736d684d2775171afac7d576 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27fc823e60c863af5b128f5041b877361858a9fda3e62a4677e2cadbfedd80e8 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..457017461155751fee05ecd67b679213798d03d9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:045b39d7fc6d4bc22ead763623faa2c47e637eaa0c03d76e1097abe57254b13f +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..043d351e73bb0098b455a304cbdd66d6a7192c9e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a60da4c46877aac921b51b9e183b7dd1612a8af62d858a5d9399cc7e07ad0798 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..331a3d792c0995f37cecf1781bb60524b84e156b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:37489f9200ff6d411de376fd0ec99cf1797a2b06f2f03a0fbd978d90a1c07cea +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f2dd1eeebc73393ddad339bd21647e141233ff12 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f3947eb37b05e054fc2600f6f9acebbeef145a21d4022d58099f8e4566a8ead4 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..bbcde2dfa549125281702e28eb3c2c7a864eddde --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62c2e5a3981b178cc1f6256c3cbe4d8f5d63988fb09c1c46b24496792ba0bdd7 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..41eda9b9e091099423f049f6324067873e806928 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dc3e0dcc386842dc9776170498e908d1b968035e23955e4dcf4ee586b019a40b +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f0cc833b0b264abca5dcbc4fb4d2799193eaaa66 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b75054c34b76ba19287e1b733ac268d8dfb37c7948eefdb30b7b0f79b22d325 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a86525f26591b56236cd106bcaf42be3c4f6a657 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6901ec8b0b4f8fdc99818a8e3a3a99414438b880a680d34d0da4f48c041622e8 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7b9c643f014963666da7ca083de5e43a32ba0ede --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:507e291021a8aac4bad21d6565bcdae4e6c39c5e474932aa9f02f5ab5421137a +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..21db9276e5cf7f427ae6a79133b310fc1d017cd1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b22737d4317260627af08722c6fe648487708a758b6f1064507c7802912acad +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..74e5f99e438f55e28add0c997721a0e5daccee02 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_22_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:870cdfabb0abcc210f3db98940420aadb92dbc8c2aaa0880bc939c521db64639 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..99154c55120095027cb04ea15ff6a3c7861cdd42 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fbe1bec06b77a43455bd54885c268c427599b3d9298549910ccec2522a6fd52a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2e1ccd1deeaa9cc58e366e4eab11d7a11e6e03b3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:76a13e2532a8761010cbd9378f43c33e017cbdc3a025b76d5da84662a5985e1f +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..08b28fe4d9099d3f722f60fecf4a367384a0ca40 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a35b00f342d08b30844b559d12cad794e01ee1b2dd20b38b3e09ef0abb5c45f +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..19cff66c71129375887b93368aa60c548c797663 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a443077eaab7f858b980c3656481fb87ce651addeb0be855fef42aaa313caf3d +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6673c3e484dc6a14a8a2f400f441dcecbf792afd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d03263f64c7b75530659d9d1db3594eed8d33236a729cc90bbd2e87040486f7 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0d58673d76d9bb996779a80e888a7fd15373cc72 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f04256359871947167c2fd9b08fc02915058ac9f70adf8a213d3dbeab44dad68 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fad53dead7106810f5abfc07396e05fab3d00aca --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:40888f3eeb8d07308c1527a92cdf0a0c5b042b6ef538c3a98abc0a2aa3ef48cb +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f2eeb3bf6ccfe57d02683880b2b9f59860c49e3b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a034e845f04bbc0a6b7a70732f361333b2efdf4463e91c91c4be1fb9b72ab89f +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..51af59323d2b6d081dbe8e0280e141bd426d31b7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d60bd6738aae6f608b60a61f2d79f3a908852b9c70a391c720a481bed4969dc7 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..52c5f847c8f7781428ccdcb8c122ed0866a15554 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6bac288a65aa960f8a339f3a17d0008b3a87140b7e3dc8fff8077b38e696edaf +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..05db8abf8981237b2e204a23e1b28798b41de66f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0cae1168d1a681b2679e2c5a60a1aef5a03a9692dc33199bf3795a62db54ef1a +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..27a275f0d2f867920370dc13b914615f8fb2f82b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f1b1d0b33793fcf98fe42d19ba45e8f6d74d15e870a540d5c68b9ea846f79f29 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a29eda6e6e837bed6a6bc615de7de152b6673a10 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_23_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cdb2bd25c1f5bb2e98ec820d73a901da6ba69f3821ed467d06a4624d9c4d3ee4 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bf5dbc38478b7b506c5113e695b17e6eaab52647 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa5ae9e89c2ecf3542941c430959a239cebb514fd3c6d3fd6cd6f82fc81ecc85 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d21a2cb942e781ca0c9c3ad7c359715c5d12c1cd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b15bf36cdbe26425f03193a69e81d2a0e0f05f9aea5b496b0a18b8e27bf248bb +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ecdda6acc34bbfc21574b55aae1bedd869808da --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7d47706c34121be9a8595218777335a955036dd71c7f8fce34984af63a81aa99 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b47949c1a5c11618a97fec77e17ce4dc0f3f45fa --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9a2ea8cecd087cad452a207655215f219fc6a82f286cac01d4180bac468f6ac +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a44972e5aa6a322e3f48316377d902a8c2061e3c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef7fe0d6a8d35775f1f95d3ad6dcb9022f6271a9d05b1ac60439680bde43a591 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d91b8cd29211c5ef6dc37bee22dd96c562f1d9fe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5091e2b6f875081687026fd816dd333892f5904e99fe44b67eb35cb68a3c30f +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1a77b94aadb3ece48e55173b1f362adefe988643 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:727c8f6e2e75da07c59bcbb72b27e70fed39fd23f8acac238b5c7ea4d36d3986 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..77ca41645ba679b8879266a0fd85cc166b64aead --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:298a59a76a8b5e3131d246ded031352e639ec9d5512edf42d8975ce4cc0ffd0c +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..661adcc088103b043dfd322616c8e4ccc6913005 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a051d8ec0613510996b92cd71d7228f8b2f70b86ff9730ea817f18fd19ca9a7b +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0bf301c5f004027ab72d4677ed148f563180e228 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd35ab0dd7504a1e2aab8b6e773dd782bdcae2ab3e53f430048c947e80a821bb +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0536c985e6c2240a77416df3fc4587f49859d090 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e03cb2f98eb0bb47bfbb0f48bfd9bb3798ee353c68b30441cac4c1916dbf334 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fbc09270f2495b80906cce06008aa607fb2a4691 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:50892064540fbf8c5e832ff114342ad8f7c2734567920f4ebcadeeef772534e9 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d79b65a392a633a2cf1b4cdd96f22bbffd110ffe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_24_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:38918351fdb9f9841df729e36e2952bb1d5874758089948fcb385e355a74653f +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7a43d649fc9656be021f48e1c0159dc48fa20aa6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e7e6f0ecf1d1de91f4e63b475d41b8071488a2f6f7001aeef66662b3e193e2b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..949699139f3131f73414e0bf76b10b9c77252971 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:baf490b513a221f17166925a06fbe29cb46ef20d9da4d27af9e69782b645d988 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7ce6e5601503715e8a0fab191cd95700ebee02fc --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1e0d22c6a86e0cffe127c0fe1c55377225f1008c37dae3884e3f822f3fafac0 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..705507b8093a96a29567eea3d9cb4b0ccac7dfff --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a91e410ed428d789ef5411568526630fa1378b3f4965345ddfd4cce9cfd611c +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..46c2de0188175662cfb9b2112ae1df7ccc64aebe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd52d28c3de9d0903dabcbee1e5445e2088c81534e89725704d7615d8644a37a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..32d4051c196ceb3e961bf7be77d3e7155d101ee1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ee14410687cbf9afc1d96a1b30afdaf4dfab380800790b221b238adfd8f2ffe9 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..14592160e61913101779a71bb69f29ad155eb191 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb433bd034fe269a64277d4d121c3f396687b5b02adad48b1d3896717c263dcb +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c8258e2bd3429014643a605a35e0ccb0e57887f2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:62155b0952dec0b23fb6b741e72c04b1cdaecaefe26bcd496b78b6a52a7b83f2 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7269dabf1cce0a0b7be1edccae5cdee717ec6b9b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:944ee09cb3a15d00fd8b10f0c853b540e150df82a790b4981f0d5b4e60bd36a5 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fb48e855dc02b4ea05365cd88a9d4a0d95725285 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a6c686b752ce1f37f7521f5c9cb624ab24bab1a10daf9f1f018b7375d03d445 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..eb0a30c4719f4ea272a31831c4714da93813512d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:04d3fe2f7dc317577d6968dc6ee42316d8e1bba7040601f3a32e1cf769acf156 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..634a709fb66222c6bf3d67a8671321b193f88f3e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_25_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b91a53d71e308b012ccb08ba613696e140fde7e9185e5ec1a1e989ea68d9b07c +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5a1e158d94851fb0b3c10eb77e2e05dd59b863bf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:741c91d1bd804124ff1d8e68ef3f56a90f6c27e23cb1ca22cd39fb124202fb00 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..77ffe91b9f76c176d7df5d609edc934ba8a86985 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35d4b3ec93fbf98e650d7fe8c8a4d52d5bc14b7cb61376b3c70206722282ef77 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..afc66f937cd3a30a54650d5a5c8a79308afc6a3c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f771cf7162325b73af6d7aa3d05643d71653237b78b8728135180ef02c76360c +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..90190f194a4ec5ffe3b2200828c668d9936b39f9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:419194b8ab6f5a90845a83f2187e03f6b2e47426762ce530f02925afb7470335 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2deb8a6d1f3aaf76ad96360621d65a9cc2278ac3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7459a0b89747318c36f9233e4c3987d093a53f8b7f7a1c930a85b39525ba1f51 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4080a5dad3a2a7e1b06899aeb3301a68424f2e6a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cbd004d20dcf143ce188b1bb47c9971a554e82eed8005fa791e72b2dd3de9f8b +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..faf623bf9bcf62caf56ce84e276752b6775f0968 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e852a245acd974ae0d8a764ed387fdef84adbc872cae019b7d1305afd69c0e4 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f2ce84ad5595ce9b26bc47b80e0be4db8d97f021 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0540f733275881394b617dcdea94cebff38cc05316a6fc05befc8a365f6de597 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7a20062af7c15fe7e52ea2b01c5656889f7925b2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43dfde99d61be05941cd5684ad48d6e268f3d1c39b6b98e8cf5ccfdcf67b481b +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6001570bd99d111c18f09490aa8602955ea96d03 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f6317f9f9f13459165bcddd72836b27ce2f40817b5c30cdf63671c3755b02b2 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..16a1fe674ae00b3014ee0ee12fc90d63a4cc453f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f7350f60bbc774b63dec0fc78c8b809ae051f288e1d75aad798d07a8036ab570 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..af56afd715c66ddb3e383f26a36106d8294795c0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5d9674a21586daa7e71197ddebc34420e5c627b2cab4cb8c19f30c26f8dd9890 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a7ab9a9557767af57b6b684698d0aa464b2d2a33 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:865854728dea50451288229380d73311ed0256aa5555cd8cc136f75cf73e71da +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a9f87232c9ce6be53798e3bdde5c15f739ea3e3a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_26_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37f7ce2c94254b89ad8a60026a4134d7ca37ab6c9fee7cde3bd05ffb62df818 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..aac5c27559deed9bb7d87f189df8d1e9952fd11b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f575142568737825b647050567e6da180367c1f56bc043420f2096f06f378b83 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fa6409fcc291564c368095876a6fa03c157ce851 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b9802c2703e26deb12a9b235ca74e82a89e4657095b4b2d67de78e4a898ce1e +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..414cbbd079045fcdb83cc9bb463a45db17748560 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3d4dba053861fbde903e9522df61c472b328c639be4aaed2bf3914c84b3d5fd9 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7f4274bf8372db7d73c4944d66234ceeac53d654 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f548c1b448e78772c85f4510ed0de5837d687228944d1e5a99c41ad239274de +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..17ad4b368f5769ac3248360af488871a1753a8de --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:169a042602946a21a2016436691e7d8e2e7019775dd493df1fd7d0e2f6bd6272 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4bd1949d588113ed8bcdd0ae564436d1df66d997 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72d545cd3871139f6303b96321c01e537ea811909405d47e93a607f1fa09f13a +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f549b5ef8ead45f9b2f27550466468be74ba82bb --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:860bdbbe2dee75f4d3d2f23d537913d425a25a53901bccb733d0c026624663d0 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4b9dc87ce12856ddb7cec445bae25445dae0f7d2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e8ac0eb4c1fb5faefb570f38f1bc9504ff14124ffdcc26ec4195aee3500257e +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..64f32f281252293c042d0d906c47adba2f6cdedc --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1aa1b296663733054730bd6e45c95c16319cf191638bd68661d6b0380230aa7f +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..74fe1eba8cd9850c2c73f16c5d2e48ab6857ae41 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4c2cd6e1df35a0c2b54416ca843841d9ad819c76a6e792b0b393acd563738cab +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..06720a59ab3474c840810b0a6397b2c60cf4e3f1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:657a1005355e61e36ac69fa36055f0917b6ab3d227dc4e69a7b7a1de83429116 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f58eeda1ecd0ad7f4c0511b87568a82438b79144 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c160b55cd50dca748973c98daae396002558f97ac11fb230604f44e87c25ca24 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..62ea10efa540ff6f78ed9a571fd9339c5377b323 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_27_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:212d4f293b6279f96bf2d171cba2bafd457d5270c9e69a63e5cf22814c2fcbec +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..54032c02c0a5b6c51b72881aeec494187ddaacdd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9b85daeec0aeed89aca0f34265567306b0b1ebf5ac2ada1f2e4a92a4515964d7 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b8a938069d58f49db6cfd40e385439d1d8141c1a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a18d0a4442d1f0752ef60dee2e73ba33a8cd768103b5e90933b18f26b9c11906 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..beee8243cb88e6ecf1e6c07a4b8ab97a45174216 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f5b92371efacfff4727b8a9f59fc14f468f9bcaeeeaeb3270318294a1d502a59 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..66ce3286b76bcf12f17489817dd9bb46812aa33d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a64a40b62de5b17fef33cd8a49b1a566712dfffed542e7a11336f05ac005ae1 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4e29f34a4065bedbc7335338f102e82e892f9e3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed93182d8d6ec30ba661854ccbf86961e02b20a122befb7bf97dd51016e4b51f +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5a24a4d8d4a3c6755d2d2b505c547c5f50c56833 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f87bc0c976ee4dd5972cffae396ed2c77a37ec879fa95a98386e796b9c02e241 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..30b61e279145e7c5c5f71c0e30c974df1d74afc8 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:07bc5589c2bbe0d89a77f4a9e748d411b3d8328a0558097bdcfe73caac798dd7 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4d0888211e9914c76688c3d98afb5438a2513e18 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:798135ead0ac5019307f0ce20ab71f4a4019902b249db0a97168d18348f14b85 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6eaf19fb376c589a99af2c720f735a414d8fad4a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:23c4248673d6011e055ffec707587b10ffbfd17f42cef37d13360861473d1039 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..889cd8d3f4374887edfae0f23a6e702fca37ce26 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c6b5c9ce54f83a78ef04a606bf0c3ac31b89fe332d34454380a4bb589c97642 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..36d3e1dfc7a72b8fdca01f0b07f4cb230eefb95e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f36185b038088e1837902ce02f60209c01e6c78bdad090482cb9e6159dd5d2e2 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..634977e4404ee044e6163093a172bc03a05ae114 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_28_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65a94ccbe0a3b0f5811e018b1566b6cffce5fc1a1d511f64b23c41817150cdad +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c0b1f0cbdc8bc28a58cc23dad1676ea7b292ccbe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:15267fca425147d85b1468eb2e1a6c32c1c45b9f8dfb9f950ada0269d36261c3 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..abb9c1b4b20dab063f6daf2a5ded604947090c79 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27e57eb37365d75ccc849c94153270799f6468a6720ad1a0dcb44c43aaf78fa4 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6379e09143770c6fc4f39cb95b7e17a6efd010fb --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9eb61b1b0e1f70f4dd04e03c80880e4702474bd131d3f26e7a678fc3c70162e4 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f5866378d28013690acb92d08908822dd239df26 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:86b52d5e88f08af7c4cbb4def0c15962702254df976f3fabba6b13de8322d5f9 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..979d4492b1e629a1bb3697a3c1ff2bfb5c391fb5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cf55f340609fb8b04f58dc5072f4143042980d3155c50cd169e5d775da852ab1 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cdd2bd67a25ab33596de5daf45423f03043415dd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2549cced54e0fd92911954594ecbc102027d67eced1cf449dd4c7c90bcc9bc85 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3068cdd2ef9322925050a00903b17b17fd561d20 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:508f51b5c0e11d493705111da81a1723874d36c75b7547062fc6dffa1bd69ff6 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6f494a4a1deb0af774bb0eac776681d875ae4f81 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02f5d442e6e841e30a40970815c1c60ee11f61fefdc1421edcd33ebe452d38f +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b0182fb88882cfb2a2b4aeb6d6933a391cde5be5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a1e489303b7d61e02a83d5ea2dc1f50d7939c464f39467725d38ce947d00372 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..03e33d27ddbc61c6018626e46a2f7e66c8a14195 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd7370698379e683ae80671026b20ebeae8af151ae76457cc22df13275e98d30 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..741cc7bff299594e36e101406b24991c901a8d55 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f95c38dd88ebd412928c36892eb74a3187109db01ad2f7d7ec845dabc6f31664 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..952ba450e7728a4a4a573bcd9a52039b02a1a394 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_29_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d77d0ee3f162a1e1fe0e8a47f65a7c572dca23c542290c097bfe0c9f3f198f88 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a107951512c7d8cdfe0fee9e1b41ead14d42298f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6f4c7fe138365b38466e2f99297569b8af8ace484700b510032152975b1bb936 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..812c578ac867336b8cd366f4a7b5ecde725639d9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3f0e32791553617754bbb25b2aa3d8bc630877af8a1282546326226653bc2f8b +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2d03e466f21db747a0ed3970f2955b18a4cc0a71 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2b38c128da639639b5570cb252b94901f32e58ae30c7d90416b187f2a657671d +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..03e018f6fed17611e59dfed0b65323d3e478c718 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e51452f908bb26332cdaff59df43a885a2a98c00c5519b29c2b8c99297a7c2a +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8a0b4b0cb700d932da82ecfb2c248957cd02399c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48a07993c4115b9f542a54991a4823ad12bd2c14af8b7c15a537b75bbe1ff4a2 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1e4a5330f898747fb7c5fcc81c408eac00a46f60 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6137d42c295e72a970f6f49b87320242c609ec5a51e6ed74d57e547c7d8e81fa +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3a470882d9cbbef5cf5df34121ed05f3f8f03c1d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8bb8ac3bf0d14921fc72221af0fb9f8faa2aa04ad99fead7fbef0781c15f561c +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe90e05856e39fac6a2441625f67d4324d319664 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b5741634d615481ae6c12fbb69dd9310e8859340af8c8869445b4bf0d00f4d00 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..63d2b774fcb0346e1fdeee70250c2bd3934255dd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e6532d4a63adaa85df24ac50d2236d89249d4568fb0107043ce52ad17273bb0b +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cf4bd9efed7afe83f5b7f218d7176af94e0db2e1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1df8b836467a5cb633322fe67eecbf50470ede6033f1a351241bb4e4b21e7356 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ebed3f4d1ef695d241562e10f4d20193ef630423 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffa1138c8fc5fb38b66c024f3cef301ee3feccdfeb7c57999694035f9b31a57e +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5e22b2b25323127e15114c9734e451949b3fa1e9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ddc493ff7cdbdfc248a40ae177b5fab8899a6debd74ef16bf090a300e299f15 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..19a7324c3f89748707a656c59ad5645d410fdc52 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_2_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:150e933ca56bec91f5aa5096b136f12af880c4335f51f22aa24ffec9999c9a7d +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a33c81441140ec6c439c005004911ec6fa1be57d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4112eed99c0538b70a560c34b7dbd7928eeff09eb3e77fb5fa21930172caedad +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b3e7bd0dfedab61846516b58ea5a049f19d049e0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0c8e2e3199662d49986b6fdbddd71ca5b32493d971ca1356dc17461dd101bf99 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5ef42df973e61f783a74b59f7688736274ce39e0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f659d42d063dfd4e053852f419c19e5bbcd2757c2e05e13527c1af2996036e31 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4991cbde403c9e0e90d80b54e569f1f8ad05ac05 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6c721482bcce0da35c2db31ee3a3a8282add068c600c6b6602d91a998ada242b +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4836f1d653ec92d6070ef70e3ce1d027a8137824 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:60b42072adbbf2a8a217ed00fa87f86b7a8009ff796d8aa488b3bb101bb01b54 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b67ea92d6ec16faa765b5f545efe8d431202263a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdf861da9743bb4cd1f057266448b5ddb40b628a1459f90673496b47a76b26c3 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dd5345bde3c5191de9ca1ba2aa18b4198598c84a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49820564586088491816415751df97b170701d15796ea55669adddfb55bd0e7a +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5b8c48302d7c913571a67856055b234bfdad1aca --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a102752404be2a33c72f3f7473e4a5f144829272c9214c2b1766804b9e5fadd5 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d9da877e7bf8051c5b04f1b8fd40520705a30b2c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e54b310b05bf8ea96aedb7a7c4462c9ff79b9fc649a4a234e254987960c848f +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7f377a58e40dd422cba79456cbc8150e3728e1be --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:20e9eec9c1ce3bd50395c7cc8975edcb4ff275d5c53c09a3c6fbbbf7df703f2c +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a24f576eb7ee786b5a6b43156df4128358e352b7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b423d324e7d25ace80a5e5f9e99e49dd2a800f4a607fc09624b9707454862d4 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..604bcb4c5e8110c1222d29f4b63b4c119aa046bb --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a1af0ace45e85b5d52c8b47b56f349c0f5b5d4f1c727a4cb044c951af527332b +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..331c16da3600b701b1f67643be89702398abf8a0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_30_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b3486efec8581b592e72142cc2bc3b39356fece78c8bfa9791fe396bd8f5af3 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..94d056286c8bfc9e51b14b4fdc5c6df48e2d09dd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:72c6d2f5a8a837d94e6593ec388334269eba570a8eee9c7df49de4fac3c96c38 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e38339467f50771764e05c10f433882214359eff --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1b6e6a6ef12d2fcfdeece4ed164030460b6dc71f3eaac63c56d25b59dce183a2 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2436ee7e22ec069e4fe031106796460ba0a3aee0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8fd8066403162577839f9d26b1c61e005a257a8d85283cd0f3281229798af8e7 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3d1660b562250689c36a8e227c4f18004175f4e5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3335d32ce01f270dba6f5fa759d0c1cfabc54cdc66d5801d48b958a07affe05b +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8a5f2355c73b8bd187d764e7a63f3e6a361bd7d6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:24bce0da5bd1817db29779b4dd838a80d2c1e3b21e3a4b9de8f16992615ed40b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c2a0ea0eb21071a2d915e4e6be2de7cc20b66ad2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e093905438c3ec8b60361e38a761c2c679427b57162abd3739034a2c53577dc +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2c30fcda2dccc8aeeac3840e5e2b1062e4f98431 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4ca0d1a4bfae3e8faef21c03326ac636b83a9a310803f4081087853586eb51e +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a0b6e5b6d3c1fe6554caad98a13473b55e9de6ff --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9fea1f82e6f1c15b30596107cc1a4820021843abeef83adae343e82c4e219a7e +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..77229e00db7956111b381913f96a1ca4849b4840 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7a53fd61085d2ba84d1926704b53ca13df38127680a18052075869373229a20 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9861e184b6981fb8b80b121d0fdb77e70e88a207 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:45df2c6cbc9459d1e396e0d035c5701788eb4d287d9788b0f035fdd39e1f411d +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..31198fdbd556e0189891fbce1398ab1822b88074 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ca42c46f501aaab24c5bc7780bb4e884c79000a6009cdc3001416c9ad49fc644 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d84be544dc1837a524f403763553bbc3daf8e555 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_31_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8335493072e2effcdecdf76210c26ebd91777de398c9bb32b4edbf6cdabcc264 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6d62c633cc78ab682697a3c3777a625124709a6d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:31d6ea32cac2ffe4273a7b382bbe01025d88ed8997e145b470f1d1e823191625 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2712ace0ef9d24a7ec5c0867777cfe39a0fe2c07 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b9825bfe350c32219006f68b394444e24a9b5b0cb79331fde9f8250770e696e2 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..540fb865b4e1c841d14648fa8d8ebc2a2e27fa71 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:649b64806d0df220082adbd3f4710b1c8e8d8a56291b1609b323c6bee818643a +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e59aeb3f09d022fafa14e0481a44d9e95a2a27d4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f8ab17825fd0c7481ad4d5b20fa554c764dbf237913812cd09895494ff358f8d +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e6e81a85293bab777a8b87a776ff936e3a5c9d51 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:895b64ae0cb40dfc6725bc2478efd3505ec59fdfc355f6582480bda41e971022 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7625fbb0de9a4b92d2783cc6e543940ec23ca482 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:63ed3bc375485704c07c833e9dcf66bf2d820d28145a2c6342fe7f5833321f08 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0700caed1ab664c808c4668df1972a6804d44bc9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29d43882aca8e28b888563b738cc9d7766b7c6a7ef319675c32d590d6a4ec38a +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1eb43fadd16c4cce31d6f537ce07b6e412dfa293 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cd4b006197cfb130862fa91467820b3a0b356dbcb0c8e0cfad78c65a7e842275 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2e30ee8c400e4b4a7bd3f1d6be8148f9d9f29f75 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:83a817a4a6fa0bf964e46478adfefc07ed31008830fc60dc0abc665706d03f54 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..468ba7b10627f313a6367277770111525e242aa0 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48cd7468e0a0c3527caf18bef9c455430cc8b839da8ca8e86e42513bb3fbcbda +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..32b6ef70c5baae225f27c316629e03e4fb629c91 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6384c3f78f00efd5e9fbe3d9af6c8dc0bfd8427c41acdf3ad2c2b6ece9244145 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ad5df35c1868bf951059320c46d71abff86702b1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cd1515cdf15a6839b2c6959168d484389e87db586744d2a29c12055ba68167c +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4c79c1abc557748556ca4f53583cf593c8d9c044 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_32_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ab1c47137c86fc121098d9269c6fc07973b216f48d98c3000b9df09f855c7f2 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e9c31dd8a045317e9ab0db8f08b2c8b5aa25c50d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:91301c0f93f4e2f4d5823319a4a075c9f003f074c0477795dff967e13a84bb00 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3a3b7c7c7f0a46f60c086dc6efa840b641d5de4e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ecaf8624d6da5b09ddf5fea8688b511dff8ec271a15fbbbc8911c211bc30c815 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..cc0c97a001822cb693b507bf401ba04385b39cb6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f54a28c1f02547833315f73dc6b4cc7d92ffe4d31555692682e797ee851f527 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..67dff1abfadcef5c8c74f963124e290e27c01b00 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b3ffaf9b26c290dea3baaf94847eb4784741f40b9fcde8b16499917579a00740 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..88d04a0366c2fa196b428de8c331502863767418 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f655cb4f0098004dbc17f4556ca15567b2a9d873fdeca5cdde18db8573cd11e1 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4b015f97c3ded32a8ca67ca0ff926c41415eaf11 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18f0bb6f02413ddb7b553fe327c94de0e852f6b6f315d84231149cbc1b37aff6 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..35eb5c5bcd8851640cc7c9e75df15e702fcc27dd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff63d4027a4d436e8e32d10dc589d6446087788be1e7d9916a616709fcab5a23 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..aa2a4b951e67e333419f3141189249f2c653c866 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0e5581b65a271d95626e6b434e8bedebba13c45a5eed9a65db12a266e28effad +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5e71e0580aff9b3e93d17d14abf39138eeda38de --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:562cb5deb9dbad73d775e6f3170d9ad3e99774c2d8c770427e9c5237a6c7b3d8 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..130271f4c84d411ad7c9037b7131f3d20ee86541 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa422771a46b0b4dc0ea6727594747ade1e76c9c661e3a60b7aecb5ee6c34d52 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..42dd80edbfbedd1fe94ba57f7cdb81c92003b2d3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec07a495d99d8f39165ddf9702758450439a0a42bb2ce59b7a0bb8011e6e5991 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2959331d3f6bb0ca19bf01534d2b1a8d7ad3dea9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_33_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:efc7abe3adc53580110b59204ee86b80516941397a417a372db2f14cd866066a +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..126f75d1dc972e758cbc55ce624d1b549ddbe008 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:39a5233b63b77ae41a3920230fc57c3af208d79aa2df49d5a47bd06ebe496a0a +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d0174dca86b5d646e1d8c9b0b058690d0c35ae6d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3a1c9b1328827e96bf3dd5ff2c813e0da0a62d3b138ca1f5a0b9fe495b08bcb3 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0a2417f0ccb76d2dad427c22f07129253fbdf123 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d112ef6df9f8eb4e7ddf213d5a8719f1aced3d008f28e58faa25ed1e42317d52 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..21c8b4ab349ab4ef318c068b18a3d5f3d5491811 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d2ff0d75704a0c204127e1bf9920987099730361914cbfd74aedb26cd0c7cf21 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..06e8e84ef88e4a120cd5657a0dfed3ba9b21b59e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b4b40cc4b7f5cc989a8c72544a8296c69cee8890f19e9af49b4cc57f2e32380 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cd47c81dd9215d03253946a3c17249ecc309b6bf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8ba3d873ae5016b8c37a0fe70428708369f3de88412bb051da45de56e644967c +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6dd4bf31528b84e2c9f55f2901c2d7aed7a2b8d2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5ba374ca49835e48c20606d83c6e23afea2b1d427bf289e0e25e74800917ea5 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c4058d81b2ca23eaffba2ba67afb8f56844201eb --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:36f5c25408ed56ae402ff2d9fb0e26300e72a658ec24e8f75195948b894abb01 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0de25c4b5bd91e8661cad9ab3845a51f30518f4b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bf089f13b33ba4a9d5887980fe41235f1154bc409b02ba225031ca32deb2de41 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b05085a374ded5f33a2bea8f4a91f249453948a1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8459c45a7c980cd297ff57076f120d0c5418c02b838d64ccd57d2448d65e9031 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5146b9e5a2091d5690fa3c827db4049be2a8d999 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_34_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:51a31c8901d35e9a647937f05d6733769a5abb69d35f0f550c06a1f7a0c6763b +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..383cee09ff7fde68cc91653cb0b1f7735e42b912 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7942192eeaa18254653f85492374fa344813f4de347c0aad907283b85ee771eb +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..92a8e7914c4ebfd4c15d9daed9086af5c114e27f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9120381da8f7093a14a374a492bab1ca20432ee320af8e99dc0922beca6ed864 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..40d6a414b4ca7c028a765fce00aad3db8e76c9b5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4aba3a74a141d9124c7c1ef13c90ea3cd4c0de18ac66d6ba10afe6f3bcb2aa79 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5413baf9b10f7395f79305966b5949cfcc6d27cb --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a91db08af421c39fdc9fa42d04ad7fb08939b2ecf9d8a0b31f890854020b67a +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cc806e3cd49909de4e5124c28bf432051cba358a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:739c4150389ab274173ddb64f2e1c846e87cde95481622c2c8f9ce8682823af5 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e1cc6f430f134b4b37fa34a9988b363c681bdfe8 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e27c2cf85c08569e1824fc7bedcace591056d7ca4c5e89c350a19080e1324594 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fbc41a51ba5e2f14903c40e6aa7ce9dd4924e24d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fe8c95a315804fa042512521a8a6fd491fd317eab819f1a456fc71671da584a6 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d343eed613951f7a8b618c54479025b49f1d4b27 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d56f8225496b4959a78ad0163c6ecb3671edde0660db7514b454d5dc05c65d29 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..70b01ab5457181f7ac145c720035014863258aaf --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c410f27312f376cf3b1d7aee7bcd630a8e1bf1fff96ef19a87d72a4a2b2bed9a +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5fc521b7d8f7e4d8b83907f9269ac439e8232279 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e55f84154bd8d21718fd3ac371ce337cdeabb831a3a084fa49ae56b077cf3c21 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7565d8926440bc095981c9d9e0c5571284b30373 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c87c162c4261b433807de81f483726176f516ff7ded3fb2bb2bebff5a78e58b4 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..160f223bf25642a1c215ba4c77e8e718f0f5c1c5 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a08f0f9c158205396d5911705ef45a37ab265981ba17f047b7acf746d06349 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9f62fc86fba55b0ef2a31bed999b1d8f5ef6073f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b4ca42b6ee14fd561d1cd5ba1c862c824e1de0425b4c19ebae4b1be37b8c4270 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1bbbcf0a9475e3cb3b35d1065bfc9de09169d37f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_35_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c39d0b2bd7fe0b3d8cf3e977ab8799f47119a95c1277cb9a0e07cc51b38545ff +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..08560893e1f92eb1a52c69c06bb80e27997c96b6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70d4edcb7e50226e559f7312c9ddada2ac06dad50a993e0dbd9344a162aca227 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..10b56561f35f56312340e339354a2c2974b64515 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d13b23f5b030332996c7ff69ca13ba527011317597b473c76c6786f427ccbbb +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b253ea4f3b260247b28bbb702bbd74da726495c1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f03c183e9c5ca01948309e4d7ef4656cd2ac5e4db9f5726a9fa4539a831c5a76 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c8c11265daa2a31721510f6058c317fa499c9207 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d4c459e4963458f07855ca68409659cb5282e42e1d2932bb30ae6d23544a23be +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a6532e75aa47eda85e6d6ff9f6409d8456c5ddb7 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:28864f3a28c1e8c310e36bb82713b368d4adab4e6a98bd1f31800a545fecd465 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1a27e2ad0fb92786aab29cd9d8a0c73068c7e27e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a81c5da55cc6b57aa6e1d1779571bacb52f09aa9ca5b531d84527b50d5a40c16 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8a75eddc8aae7df2fd33fd2a48376be49525878c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ed736658fd2dcda169113abfce76c7de33cd8b2f79d71578970c55184542b95d +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ac9d159b3270c73b4eab8b62dcdd8b1e6901b664 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fb7130de27fbe5fb7bbec666653235b9f22b0430707bf1f6ab56c4059e9a52df +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9eb01e0375d8493f97b99ef3769ed88946e2686c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9e16c97fb97f6e20e3956da84891b003b95207dd0e5ecce674bc981ee580a531 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..24d25f4f119e962bf97a9afdc907c43efae9aa1d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:538e66a6c8ac9ec0d51ad8baf8adb53fa30b1f1520eb216dce3eaae1f88b5f5b +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a28abee35c35973c1b394e34f8c33a2534f10bf1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cc77f2b3da9cd43c2126a55051fdb805f03d99d05130c61833524d4d46a9f089 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9c259fbbdaabc22a5d8b946e87ea6b3a8fa68bc6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:21fa0d83d23707c781518d1bc271254da44bda3209e692bb2d547b047a2e1998 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d0b204e40194c72e7d8e47dcf5b7b70fc9b778dd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_3_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9a2ca170c739021763e7920408848e978bee082d0e02d29f68c390b7d67c4d8 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..01d50ed33301e243a98b621a556c73f265df7041 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1afa4b583f5c780e7d44ca12675e91d16b9662b2c26a675d511d5da59e2a0085 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..34d3a6a41d410f68b3caa1dab6ed170e2f6a638c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7aac6b66f5bc3ae7320f66a5f68479391475590d4320a458e2ad0b6184f78315 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fd431d1d5e1db8dda0edc4783a9934a05db1f80b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0667a822f3a51d3bc0a63d0fd261cea1a4ade316dc09818b61d6e6ed8a3558fa +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..83c08c818c69c03c08fb2b1706d49a974ba53bb3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:47080bb29d3be3b6869889e790a78d411c39e26b5d6035e99fa2a5cc74644e4a +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5ba6efc4049f8c9f0a11489bf1ae5782df5dfe42 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a2281c6c090ab59898ed94d94926d2fdb41e6aeba6eeb28c540bc25a21b1dead +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..50a480d0b615ab303c0ed851b70f1d935e4a475f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2c131503cde8c92254de535856e0ffddec98c6cf1d51df1d17b34bd00faf7adb +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..07bd40824f346f2a7c8cfca93504c77614f00081 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ff84427c3c11247ef309794d3a490142edb9261b9a1d5eb4336560216c520a05 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..98ed1b352ca12c662e1778f323404f5c10ca1b43 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48caa8267c59107f568b20cf03588572f24b4281f67e1e68bedc334958768c3f +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..101ecb7df0eff03822102c3ed5eb575e599cddbe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d5e8ef70e11950579cfc21c2ff534296410196a25f13df1c228607a74f8347ab +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5811c60de5c9c766a740c1bfd6eb40e4258353a9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0e96e8c3819c8190ee2bf43676a591c5c5f3a323f0acb7a8b7fdbeb10dcba88 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..92b56a992cda6fb747162ccd16978b5d36586a5b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e794afa6156c9e4d947239aad71c1b7b1d9b32661955a3d07c086831880e2fd +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..603e06ee3607524fbb4958566cd13d6b4becc129 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_4_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa7df73eb8ac358777595048ad0c5de64c7057b4a275418bf9905bfb042c4da8 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ecbf6e9bbb5763c3cfcb26a6cb4adb2a0bc481e3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f01f43766274d62457faac351518a437b239a3368de2095be5d1550bc80be16 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dab775a35cdc7e7b769b993bad07f482a3bf8caa --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e12831adfc38588fe9515ffa85e8271d7f3b4e1661aa84090bb44eb299897357 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ebd48884b8f38340464559ce3e4bdcd35b5e741e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c289a15af132e79443cc0223930ec18bdb6d04444ea0668ae89ab3cc160d3e0b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..04b9cc7f1c70cb422f5748a587a48faa5cccfc25 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:79c12439786b1552f67c9fd21f64439d7f4bfb308eccdd3e2725eba05d32b8a8 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..98c977c6cd71d493492a620fbe7d7eeefd464777 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:592c9b67d4b4934ddefbb04e7896e27b298e9fc3f92dd7c267d47b7480323c72 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4047853cbee2770aa2dbd81f6123dafef19c94c6 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:be1aab68448e037c7638d9aa0cf48285281fa448495c026018c4b7a1a564b72e +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d7181b0a06872487dbd2dd2df088938fb54b801e --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c8e622c3f4b13908e19b334d217943a6224b81fe4acb6bf90f7ed46a89b8a4cc +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1695458f6088dc3ff6bb11a8c5ffb72bf53948d4 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:806509d53c4f1821972f14f5d7ec751c878ab76c8764595e12cf02fd01efe0ee +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5f06ff31ea539b102a08452d57078b45ee4c6686 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c29a6d637bc6312464d21b2aa4807ab595c92cc480a486dde8c7e8daa8065b4d +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b53596f6c07e2e2f0bf5b9897acc146a14746f81 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:88fc111ae93eac8030a2905615f16df555ea6e876b590f55b8108fc5be1949c0 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1982c4be634f58d05c778f3e19c285895f9e0720 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5363869f2ee61a82667df2b77b85fe5d829b1aed07812254b66dbc8ca0fa08cd +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..eebc7a3e2c826a0dd4d18cf52a2b872e84a9d34a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_5_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59ac7e11732d5884562202b5eb685b33eeef127f997ccb555cc29eb28a739399 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..37d84b3b15265fcb40cb4b563b11e821a06a92d3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b652a55e2b4caed9f8e91b915790d9e3011ce87328a5ddbb691a3902fa15fef2 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6ae6dcf0fbdb3d36fb922b2078398879fb35cd27 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:840d1d04b8b722340c637cdfe916ec3f1e5903fa85f507551023823f032d5363 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d9b02ba2fa33340fbcfb5f4b81b9a4366309cff9 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:64a54a45a8106099fb4713bcdf85d2fd0d004ecbf350d39c44b8d5c5a42dd4ba +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f448a26bdce504bcf5804e696718ab7ae8c05eff --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:320d89e400c6adf1d2812a36c3f18a6d0acb78bad4ba9ba0db9e396a81d34ff3 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..346916fbc4cd2ef06a7c2bae495ff9f0b0d93309 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:06be69b331558f97a6ee48045c961043af032ad3fc42ddf743cf4d6074b260ed +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8831f8ecdb4c16f08f00d71910819961dd8229e8 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:961b24a4efebffeb32a8441ee83e35366b939cb8bf8b14df71296b1ab32b5a21 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c9617e31fec46ae9bda8ef361510653bcaeface3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89d3d1151ecbf67f73986df9f83ac02ef8180f957840908891ade599d5e9dcc5 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..34306d6cee6449cb769164dda7d72cef0c08a73c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9cc60bf12c26718dbb341b4ba1e712f8bdb767634b59d75e1602f32e7258121c +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..177b3d0d809fe630269d9335eb116dcee43d9e94 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:956620bf0f9ec9e46c45634e35347d11d825d6c5614cda890ac277d9e6b6a7d6 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c82d4f5f015184e1d59c57f922c2c3aca7ebaf48 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:01495223e7eccc785a2f98bc17ebc5a448c183f3d2994acd5de0adf2e4699c21 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..091391aa8aba7876b88d2557489a291d6029fc66 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:005599c4253023e63917e8ca76de575fc14b54e9784c5fee8a90e2158820f5ef +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9be1b862890b3a5c1cb0ce0d93359f45546d1bca --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_6_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ef23a6d654d21c4067557311961a0272cad2c02feba01f29e692dda19ba556b3 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b462088edfc1f38ac04614a4d1b2daac27272184 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b82b9e964ee8f8deeea759857b37fa129749e6e77255649f18d46393be63919 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..304ae342dc253fa289587c3ddbf0c2931cfd0414 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:177cf0133eae56c3d9f5dbc69ab998a7a80a30db5d69a44db707f771f913b3c7 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..db23dfc715630669aa8d96c83b87878a56228bcd --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9eaccb3c2ab1aa94ed424cb5b9ea21c4474c9d3c375204775acbd6134604297 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3cfdd96c3951acf205f383ef95c5b073d49be234 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:46ee00f615ee9224b5618a7145c131bdc3dd268c3266f8a474b14f50bf862c90 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ea4da613007f61f14ad7aac54bb3c325acd6840f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:61465cb7206925763c0cad4452e8ffd9d5f30fab79e74e1de6df9f64b8f3da6c +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..55e1580ace2a42385d1a801f86b2f06eae2f217b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0a7fde9a24f8f1ec4e6baa9bccfa12c052e1b7d40611accd21b0311a5c723abd +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..dce1778d861c1015faf09be9eec4cd8334f46ebb --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:98c20bf14d0f3d38264c3036303dc54a33b5a3d6da667952990b6dc8a868dea9 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d011f4adc9d9277b58f9d93295fef0c2ef44189d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c278083a9087a0fb94ff6ca052aa34fe5f9aa265e2020902c281ef635bca969f +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7002fdf0b271908db98333b6e890973b06cf6c4b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd400bac059ca9a3401506276da79d27de0876052972128aef5f762ab3efa4b3 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d0759ef9b4fb3875b3c12962455f0a0f4885807c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e0c4fdc7278b59d1c25d29e10f7452e1b71bdd600593afa829d7bcb91c2d55df +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..37940ad6c5fd59158ab9d58a3f0d13d443ac02a1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a7656b2ef0705a90de97f84a65430bc1594314078e82ddb84afd139f481eb05 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9ff18ef071ce24b8c491621a4c93ba042e76edbc --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a7fc8e386d8739a47aa82eedbac900194f407d459ac9aacc2120e4249fe32afd +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fea324b4b0aa79d2469331f66e51b71e623eee2a --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aa27ea3bd658a48d24f7491bd55914121d380ecc58993079b5627046fb737147 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..10ba4b843eecf5f65548ec6b899a3f91039adb0f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_7_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a08b6cf6a97b3bd9935d23106f17ce080d6193af5e9931190fcc99aae38d466b +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..98e1e13feb255f8426bd2d8ffb09fb4f1b72bc0b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a3ba4f19483eb507e671bce9609e23224d7810db10eeeb2cad8606a3d0abda9 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..91127ad4c67a74bfe4658361d2d86586cae6e176 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3edfb9e5481759a301116adeaf3cb09c37ea87b9cd3433531b3dae6e2c49c243 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..392b83bbd996728da0d38e758af4b542f23f4f0d --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9a0a6500007f4cbf14bfbf9420eab033e9e7966c82efdfb91e9861ecc47eca1b +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f733423574ccdd0e13d2080d25e9e9920e9da677 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7b21d12920e4ef75c15cb7550481c772deb1ac76fecf15e9262adf7d6214c6d +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ef628fa0cdb4ae7859f45393d9c8e54828dee2fe --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3e78ebcd312b41aa3a3a1e2dbddf6eb55fed8c125819318dcc02ebe641e8da0f +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f747e3abbceff6f213e8c7bfc4c122ec6048d217 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c37620f0bc874e40b732dbbc7ff1a4bd95bc47b9063ae82965aa06b18c2422ee +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7034885557d616168162739fd45f1b55e171bd29 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ac5bc3e707438bdabf997911e0163bd4292f2dff255cded2ab57faced530522b +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..742684f7bdf5a1bbc87b90eec57060d585101c36 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:321d1c8e7dfaeb493ca4b1cc7ec2eb0c27d1b674a08b5b32346369c51abc8aa1 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..485e07e8b9ec8e30e8bf3590845d0fccd6937e36 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c57874faf7a16244e587e565ffc6a96e2a42adace70cb6c6b8f33ce75d9279c0 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..98ad34259eae083dc4775d726b1ea3e8dfb21b27 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6979905b41408ac2b5100e121f7d0ab89426d5c52354144b1288aa4d79f02a27 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a5ff53566ba9ac743d17fc6b05191a2df08c5426 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e7840b4756b38bb7a8fb31715d08429ab4a75f3aa74e253167af130269b49b7 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5c59f8bc4bb72ef3ab8f7abaf6e9343d4d8238d1 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c6f501d198d1df65f6a5a47944ddeb7e0129c19f97910befb365d4246310317f +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c99e72bb20edda1b09e22a9bc04292e52cee8fba --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_8_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5a6e72fd652db48f95c949731475118d6458582d4919b70f8fe82d97c47df1f5 +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9c8c11711aea30d7f8c133723870dc1f450a2c76 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9362a70ffed5fd761706c36ef3a637423b93e5c84358ee44296ad11f5ab64dff +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..18ab6bc1e3f1168dbc53cc6ba3971de5188f9c2c --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d9c2d4c601af3fb6bbef4ae2a853c989a55a9d12ac61464cfcc47d453f665b1d +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..99d07ab342b93b91fc90d79b04502a3a7a5e7438 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:43b6f5ad02583c5104c1402ed09ff22f34da5eaf984b999f24bbec3d67a2a37c +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..98343c5256d9c9cb990a3f802101407f0e6e988f --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae1864c0b2f2887ae5cea42f82c57a9ac43707c0c1412c83b69bba0a9cbebcb7 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fef76d454fcdfe42e9b02ad971b57359aa55337b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:077d22d90f7f4cb021c6739490ccd1fe52b4f0b346e453ace4f0e44990e70283 +size 21790720 diff --git a/qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6f3c5f11406698432cbcb1352a1fc2b9fb9e6b57 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:037b40ca1264f8e121780e0290c5f3968e4e959f30d1c4d77e2898c3cbf899b5 +size 3112960 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e3e4ca9f822f0ba3c0a6071d526a72d6a7fd8a66 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08a346bae658cc1fc84f93a44d1ad60ccf9eb2f937ccb6016842257e10854168 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5c37170e6485d7334ea383258d3b4f3840cf9814 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_k_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7048ad4303aea1faa575bea41f11ca048dfa05936612a7eedece08f3a3b5ca7d +size 327680 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b884325a606e979895cf50ada6f7f366e507eed3 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f02d757b8b4f2ed7c5b23889da7fd2fed0f223649d0ca027d0923409c2c3952b +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..21bdcebac20909d840edc5a16221eec1d9dc78b2 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:570901be1e1070a244c5da4ecf84a256f5191c137f6f9ae87180eaf6edb3c9e0 +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..463da88813ef2dd8cec34779d865e336d65cca4b --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1ba624434605fb14b03808947888deac88dbdfa0b694c62f45c95f5ef4f38bd2 +size 9175040 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7f0bba28934643bd193f21b1696a17c293c26095 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8f0e8fe57e99468a7861e96eb6ed576a6b1c302d51408ff0f30fd861264345ef +size 1310720 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.planes b/qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c684a59b95ac7bcbe8e0d63b415f3b1b61c73475 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78272b47a5598f3c8edba80cacf52ac0b259b013e2d9c8935e27893c6766e144 +size 2293760 diff --git a/qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.sign b/qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..29f644c0d963b60969f74ba4963f34090f78dc10 --- /dev/null +++ b/qwen3-4b-thinking-unary/model_layers_9_self_attn_v_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cf844581fc1efda79de8027968886955bb4dd1538a2d293f6a01861e7a9f39e +size 327680 diff --git a/qwen3-4b-thinking-unary/tokenizer.json b/qwen3-4b-thinking-unary/tokenizer.json new file mode 100644 index 0000000000000000000000000000000000000000..cd71f61a15a522601badb3dc960d800d9cb3766c --- /dev/null +++ b/qwen3-4b-thinking-unary/tokenizer.json @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:aeb13307a71acd8fe81861d94ad54ab689df773318809eed3cbe794b4492dae4 +size 11422654