diff --git a/.gitattributes b/.gitattributes index 4a54df079dc9c7a2612b5cab5b88b99c52a856a0..b4de4042e416af4374d86af7d7580b3ff86826ba 100644 --- a/.gitattributes +++ b/.gitattributes @@ -387,3 +387,253 @@ deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.sign filter=lfs qwen3-4b-log-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text deepseek-r1-1.5b-unary31/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text +deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text diff --git a/deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 b/deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 new file mode 100644 index 0000000000000000000000000000000000000000..41dc9c1ab0695b778c586bb83ebd9fd020f49ed2 --- /dev/null +++ b/deepseek-r1-1.5b-packed/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-unary31/model_layers_0_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6eab56769470b216af57cc2f907f2a50cd6ba1fa --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e4398ac44e6d827abd4f5fb1dc689354f9f29bedff598be1c639fa56dcd51b7e +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c75e9f7883463882c7fed4e8c9b3f7d130cfe90e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_0_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cd51a5b883f1f916ccac2eac65a125b23b3dbf29 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f0f2bcb11c6fe3733574382a611d2f52a56645d46d6442c2cd65f217adacd9c +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..97c721e54a951aa8031e3d0665a92a9b47cba088 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2cf601ab6062858b266017e3ccc33f77bb1a6560510ddb28d0bddd9822adbd0b +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..437928a30d6e3ee7d71316ba9b2858cd8ef20e4a --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8b6994e4d41a48ae9764063df8498511c756d2de9be45716628a746e679883a2 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad057ec33226dd92818e0221690cfab99a2f7ce5 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_0_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..149d734bb75e42b7f5044a0d1712fee050c2dbde --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5e104c032c4c68245888a5ca8d0e472f195a8c5739111acb0bcf374d02b225db +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fa5c3f4361129e89d21fe2ecaff339213555bc39 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_0_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a5033087488d07a0da7cc597227c2ad9fba21fc8 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2f56946b5325dd1b5897fc27129a7301445ff2cd4ca4242299ff8bb72f8496 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e773326e4ea0d075505e655752ac141a0cbf12b5 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_0_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..79091999a779c761f087734ecacd99e1d8a64310 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c5e8ef8cffc0641ec01e4c91e292c3ce67d088ffef871aa98265002f8fcdefab +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1fe9a5f7c9fce4f9356dc1bda831cbe6b0d7643c --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93aaf4a9cbb3a8889e30662df570f4e51ed997c4714864898d6ea5fe3d6544ea +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fb674fd8ebd3eb94eb2f74b165e0e634583395c2 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3cf02c8c10afce88344a2b0aa0b4d6069547ec9bfceb51355481a53eb2143c2f +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1d50e783243a00834ff0fc7e7090d549545a7469 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c8d38e33a29916b3a384d78f3154474f9b47aa396ce1f0b4ab1c44518164ce8 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6aa577e910633bf3f4afd43468533521ff29f527 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6a7bc333a497612fb08e62ac8f382109a337cab927e09fc41c1fed906b50bf74 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4fdbf2d1500d88e97184bedfa89f8e16ba73441 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_10_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..78d2390ea46a4c2e5c7657300afb79f91854cf48 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1572f5b6dbd9936dae84bbd687c2db2b319601d94df7923d90b67ef60d235029 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d0fab48f55724a874b707a9213d3377e7c88a0f7 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:14a02754c82eed6f3e2a557f4e0560ed0b241998e36a924d38ab03ed508a7166 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6f7be89666c6a71b56ea9d3ab3eb9f366393a8c8 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:431585ec6292217d6b8d7f6c56e402c3a5067273ae6f01ff773f6b546c295222 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fe3b045e45fbf23aa53682fc73a0ddc9a21a90ac --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c68703a984d2d090b1cb0b157ddbf6a35984227a5576feef746a5f90bcaf1f94 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..56fc5db10d27ac481d30efd51f232d0da9992345 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_1_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1217b6855bab7e777287605ce4af40fe9768cbdc --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:49fdaf2a9b2a0b40052fa7df86f91d6cf6c4fa7171af371f089846c1604c2ef3 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e760140a86e30951ea0fa762d0e62e8dcc774115 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7a161d226b750496245767146f576d75554387c2831fabca60a236b62c0c1e68 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e0736ddff5d26116c3d2bcdcf88290b099a91e3a --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1028d183765318456b812c0444bb9fc73279aff341b0801f3a187b98cb0bc696 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..17ca7681f69c42604c206df7101c549518043210 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:55ab407c506a305f0d56787b3ebc6cf8bffe2a31ed0382393286587fce50cfcc +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e2008019eb8913e2c4b7b373d763df446a841ca5 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:264d743b356d1c334878111aa6d1c1fbd184503bb3bc5e09618c4659ef84c4d6 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a626a86fffa107c2a2802ba32636c7d9d750cf0d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_1_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2800fc7cd1934b6cebd4b5c8f9dc2f80e905ec10 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:084e761aa4eb0aaef88198bcde4e18ba8d418eccd6f996c06bd43991fcbf2de0 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8c552fa9ac56e9b7eb8ac5d9d27f8a6edd2edef6 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:03f920edb44554298432d0e677d40ad1b19aad7a0bffe57ff9d42e42728842be +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9d4c24212fb1458e2cb29fe61010d94d8e88de28 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4910406d2aff7bd205f58fcf484f9abd4b7efb7bb2a5740d5afc071e55cd2711 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a6076171f4b8706041fc52f01d9d91c6de955299 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:71595b0eae522ae9bd300dbdfc19d2c65f64ed108ac63af9c80a13cd5ecd2742 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6d18284006e739ef206049225cc91908ce5c340e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_2_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..60cf67161e472eabb76b9de3192148306ad96309 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3ef8b19b483e5c701cd841f100b08c04d092cec714b25a37697b3957213f7aac +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c5417a844321188a2cbf1efaa7e9af9620da0ba3 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2959ca73da13885c8bd2b97eba55955a11c54af86f4ded2216013ef7283830ac +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..36bde25fc00a15f9d84637cfe331d739dec1ce4e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dfcd69396e9bd01d0fab4f50cae4334ea575368c7da2251e78a5e09baf4b4a7b +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2d8e3330c9af2ac3b54295c1ebc7c7e9f2afac0b --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:48f2b14390e677da26d5109be28c56e2d54e3a7ef09cb127f4efaca6d937d000 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..501fff654801e463ad4005ee729286b4539d95af --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1cb36cc621fe9d22dde6257003f4843334fdd596bca99ae80a0c87753b04f1d2 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d10f37c35d5a1f5357cc4e447316c3e4ac8cabb2 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:816d513cdeac8dc0605a5808e97cfc152dddd76d3c3ac8451508ba3b140cbf6b +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fd912bd15da7f1259079786b1d64218c8966c07e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:78088541f39243b167a6fb3fa2eb1deb46f833b7e568ae4f16b28369d721936d +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e83c8277b20eb0de5fa7e404c6033c51b1abe5cf --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9d1f2ec7621ea4c2bfb6195d51c4c9f8f2d0b150d04f494f97871b61f726b603 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d82add41ab3145e77b2776f89a496bc68103076 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_3_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fd71ea5a2cc5e305d95f91cc47a2ae3da19e3ffb --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ffe57e12e4d95f84bab1eda718068006f9158132e70ab107f8381bfaf3ff2f +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a8a4a34f4627de28681a7ef6baf444341add0356 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_3_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..faf54d0a3ed0d43669847a33b184698a44208be8 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd5de36c17c78bbf66ea3a227130880be06ea939f4bfc6480e8f44df2793ce0e +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7ac8274054aee3e444fc610882d2910adc1a60d6 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fd3b8fb93a12a2e9411ec693f5e761da80b09734ca758f2ddd06cb83365677bb +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..35c2085e394e6ee32f2d5d5040714b3ecbd73d22 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d7a83b95bfb5bc107e9025d1d4bcda0b5f631e0e5263999bf1272080c7d46446 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..9475352a8785ef8db9cb776c99bb0b80fde1091d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:99e9229c23a396d0ab2850f7487af78390d7eb76faee82fc06f2293cab5e6318 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ee922a410d659781aae32a67b9082a0aa8980bf2 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1f794bbcdffd07b8719ce97780dab4eabc04d310bbe111dfba7f8205fb80b684 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..435f29a09d0bff2fe2aeba1bac3f967c5a54a104 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0214e01df969a57ea51694fdb696267019a8006d2b1d302fa94bd6e733286ab4 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..12a90022c8521c3b7ca0b9c273dc1a34fa7bfa9e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_3_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e4ceb27e39f9dbb7b9ff541a16f8d4f62c6afe4b --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_3_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89c41e8ae5038047ee6c3f1db2916b94f86a407e90c4c6ddf83869f6564b8a56 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e1ed8538109ff3087982ab05525d6cf33700ba5c --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:93e2afcbb365ecc438f018ce4ef45bc59b25aa07c8845424d30d2d1e06980377 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6add3d38b2d1d9a1e8a164f079cf0c1ef62ac239 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_4_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..17b77844d36ee9dfe2a6977d15c61e88cd55d014 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bdf8d3b508bc7f8b77a6124b177ccdd8b8b0099d1c85a3320ced693cc32bdc79 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..85f1804740d2fa63cb5919cfc7c5f201e6f71db6 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:74526432e6daa0d6f46fcb15e7a06a0dce50ab8453df5aade0383b27da9b1eaa +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ed6b6a92235567b0440e6b95be195fcbd46e2459 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a68f5701fef08f118ffb017010c9cd162dc1af902e3cc8028039d1a136fd8102 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5df012b5d24d77c14cd3ba580b1aa24c6346406e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5504f389d7257777f1fcc688c1626c90d960a9eb59612f3a6877ec2da722cb8 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..afce2ede035327e8cd4283a860277185faa776c8 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e3056bb8fbfd12b2ee16cd7d63c15814ee9e960e2a3c4b4b179e7f715fe3df5c +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0f5f196ae16ac9c712728fdb5228da585db0bf54 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:edf8d0e7fd4b659208097c9f50349f888d2842e187426a0410f0279a7dfde3b1 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..590ab442633f188dcd6d404689e77aa64d18d88a --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e19c6b8b0ae5aa69d9cb6b05db7a21daef7e6738961f1b34c2313f49606caa41 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..2e0e3ec59d18b2ce72919cc9669663da94e54d5d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:582926197217f7329522c01036fe2bfd2047e6a5a9c24404ec051750caaacd6a +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b6d315417c3d50166d4b2fb277f44adaaee4f719 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:480a23f93eb763fe243109aff55a64ab2e83432703a30608c4cc738f638604a2 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6fad70c474b66c4ab5dcd6fc2061803e9af51e42 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_4_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4ae0c762812dfaf7205437bed1438cb1cc56bbb8b0f27f1ad56b2be111a4a548 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f0325795b4140d9dc853c64ac6c49066a9eaacea --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:780a6aecf2b9c7e6760eb68353aad38c481fc257d23cc593cc407cc0eec735b1 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d4f11fd2cb034cd562044d6dfc4cd58339429c0c --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c45fbbe8647edf44b099797b2180f6358914ae23627fb690fcbb0d4e0073dc16 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..48a1523e74c49ad36c6c256eee7016ae761b8b97 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d0ddfdfedb759f4781b50ec2b01cef7de8395efcd56158aa141891ecddfb3c76 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5b737a8d28c18cbcc1b29da860cdea1929072482 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_5_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..082e597d2bc9d6af239cca6c494d79e979e6ee77 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:77d1e3ad16ef2135c95215a5069d3ea20ed8b5bc249b8d7b18943704938c24cc +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2b83049a6bcf2bef96c73f21549f241c75c5b80a --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_5_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8b97ca9dfcf4f96dac2df2cacd2ca89df957c65b --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2fe20511f44e01bea6801c6a88d270b32302e4a576bb2bfc362851be7ef67564 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a81b3280a91ceb1215c69c9ea8547f495ce8c3cd --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:65c172e63324f5453086c379accb7b9a71330ce948809a1fd08d23da2e1c28b7 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..25d138ac7ad161538ce403fcf1ec8d9b3c35463d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ea502782ca87f1068f0d34260206df8b18c106eee96ce075fe5eecc7e9382cf4 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c79ecba83a713182368bed08ce640b5e064960b4 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_5_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0154b1aff556e657e999fbbe99698e760023958f317c3ea35d162901c74e29d4 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..330e1f6a1d6d78db32b666b40a5af27b5b2aae9b --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dfdb0f8253063d0cda1b98f79833585956bb8fb82ff42d322975e2d1f4c7347 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7f6535489ceff0c44c943fe6782be067f31729ad --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:946ab4cebd19429bf274a62cfe4903c99103ffe90478a708f97c589a71e5b102 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ed41db6d1df6bf82c7bf3e98b67dfbb609719e72 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e32d5896358715e1cadecb99ce2409775220cfaef07b319a8b99bd8beb9c45ba +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9cdee53a2f1714ba63faf4d5d106c486b0b05943 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1940e1c5c0ec03694254094fffaa692ef5927a3f3e47872358d279dc42d539b9 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..22a8dfcf38213cbad82690bb4459eb1e656d84a1 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:df539562fdee3ddc463ce317c9619d9d4634a1263448efb0caa706d639f27521 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4efa1ba0a0818418d8100943433e79f8532e40ea --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_6_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1f8bbc47935ad38f817ec497d86df0ae0781c19e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:daef640cfd3475024aeae3bce85eab027e37332379d79bc8481f7abf22860f7b +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1354c1ac7247fbc0850fe2dc0fdc171ba8e66212 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9f1d6dd4292f85430e86a4533c34e95acdad35f3947e851ee4a1ec4c020527f9 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..72c05f28798691e9f47a84ce0ad076c4e1cd45a3 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_6_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8b6b0b017c796c2f571a538da2b2d2917eada60d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e5bd7f43542cddf301c65118897100bbc2428f053f5b7f5d21737be595b2c295 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dd0f784b73d04762f550a4cfee4abb8d767eb103 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:57d01e4ee171edbf32521fb4fb4600773ab6652c60971be5f497e97e41f7e911 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4776bc5f39ca813ed8314edf16cf9b5d6a7bf713 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_6_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6b667998491088897b7f0d7475d07423d783d5077ec45e9cc1baea417122afd9 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..00791b6df238e3c9598310888d30eaeefd921262 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:29bc0d44144e22825ff89ae59e7633d1eb06e38dbb550b399301c24454a2702d +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f2bc88d3ecc168172d9815944b90a249f1f3a15c --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_7_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8331ed94824344959c87e30b3dc4c6b6c97d557f --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:153b453442277c935b718c6103465ed6dcac7ecacd2079020d907fdff9495d16 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d18791cd1d7deff3a55b2a6f070d468dd27e44f9 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_7_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..40d1443c791edaf36fbccaf9fb675af4173f2baa --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c52e52377d78898fe295632974178175dcdc972f76419204541b4a986075c7db +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe5ba90dbc97bd5ce02bf72bcbc6cb1ab7d3acef --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_7_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f46110bc697670fb8234e4924ad8c0d2438cc8ea --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1c20c06a4744099c7b0d2768948d2e749639bae74e43c8776f9e800020f4bbac +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..738fb39f3b60e3af9825889d472414ae97aea294 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:22720ff4c9bee78463cd84c2bc11b29faaaf130083d5a7f494004f4e354e666c +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4d6433dbbb230ba3c9bb6fe2ad65ebe996566e12 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a4b8961d1cbe2020f8bae5485e7b78fbb1f950e54ae311abc242bc26fe868554 +size 294912 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ee702bd965da7429357e877e0bd90da9d940a970 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:632c9cc84d28d4de557788619051c59da754d9febdc6ef7589db3fad97d3e912 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4317211761b1e83b5112d19e59467e8a51bd1c3 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_7_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..86519bef96cc1ca405e48aff749074060a8ca8f2 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_7_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:44ae44e10790e3f312e09aef56b98de6843df1da71fa49d3d7f783cf39090363 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7a3104202483e8090a0dc723d67fdd46a915474d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7eb6650c7890e8ac0a0c148612eaefcd189815bb811c3a36d4795175d6fc3390 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d5022b9a01f5bcae7fe698e6ca2909f00650dbb --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0f6f24414e4afc9611a2f38800fa26723f5c774be244dac3330acefc141cba18 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..10e3722678bf56694d65754e29815345bc0fe2e9 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bc6213949fc817ca17d573e7a0ba39dbc6a4d02618de13690cc2897a4eff120e +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..1340a1447f132fca9c0a97810416590739d77829 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b147df9cdc62e23e654a6d42c51e2c49222a600a0e1755db94b087bd17c3f00a +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d941fe5b26ea517ff69cd10dfaa58fc9e893196a --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:484438c5b8a6fa3e3a4a19cebb6fa4e10482b27d33c04a52b192f5a6f2293c45 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6cd856e61b79e2b67a3acccacd108895063741c3 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d3f6aa79044e0dc8b68a383cbbe079719694dd1d5d0cdc3b5b41a12fb68288dc +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..59dd6dbeb6bd0ef96be38a87d50dff101311d64d --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae2101b2960c2076fd088e39c3d447d684076f1d06c3d408ce8ff32bbf3f8999 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..402ef2b02ca251f0c3a7fc8a3b7972c978146c69 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:eae419cc9ccc3c513d06945eb31bd05dceeb2092a7d2e10f01ba67a9eb7a01bf +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..23166f78fc7398891dc4b7a225fb238bf2c1a4c1 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_8_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b8a1704addc309335634ecfa7791ba152631aca5 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12ab6f37e20f819bac1f702c5835802a25aa131950ba810496363a9f9c1df89a +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a585069c982ec6830f80482e7004cbd25ee16f16 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_8_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..45b4228de1d0cffeb037e1cd67c0e3407b9487bb --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_8_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5b6a48c897ac3e7c15b60843ede79eb004fc4303d108dacef59530ed4c9c543b +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..060f3a077333c6386619cba42ecb5464e01f2d32 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:626901e84f6337016f03fb35d5e74e4cf76b604c65ee7ba13e1cfa7bedb7dd9f +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8ee4ee400036ceeb2424a22029a7b85384701bde --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:183f4dc7071f39c281ae75ebc315a3d78341fd143e2af80c38726e17df818d42 +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e0fe0c78efee41f984d96ad32487d3edc0ded26e --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:975c80ae164e8b092857a05df8b35c8c842e9bf8d409a0072d23a21cab886a24 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ed617cb33adfad64ba79a154492eb4216bc6010 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.sign @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18c32a9787b099b2afbd50f74d79759336805cffc85ec9ff2137042c5e98c88e +size 1720320 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3e5ef5f21528860c6245cbaa5cf04ab508df9780 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:439b811a9a3285908dd103a7659632a5a4d87c93b0633c85e8beb490a6cfb028 +size 53329920 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6b23d7902cb40d7d8ea83d221cd2894883a95d6a --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_9_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b246b19901f62b8a78c18098cda365eca3bfa62c --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:985cc35be35854a971ac39b511fed551b088546d21d6ec71b7e73834a4097021 +size 1523712 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ef360f933c2f5b449c3bb0c4b9ef8ecfb84c77d9 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:35e784e553722db67c21698c294bafe1909c4288b0868c6ac956692c26e389eb +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7779f95a229a2f7df437f13048d611beca13a501 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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-unary31/model_layers_9_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f646347cb2cf58f2f3d64affe6f5cb2917a39d13 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a0da7b9ff34248de3953fe93fd59d7ab38b5a5cc18f5ace3d42a0e6df4ea8cd2 +size 9142272 diff --git a/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..df93509d64067043b6f37b652ff5aae9ef8f6ca9 --- /dev/null +++ b/deepseek-r1-1.5b-unary31/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/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8a8d4df3f52e3f9d2f52f8c527598a6e4a894f0f --- /dev/null +++ b/deepseek-r1-1.5b-unary31/model_layers_9_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:165c4f0f312bbdb06fcb2b396fefce0e5f0dfb5f37dd774db5a229bb4a46e1f9 +size 1523712 diff --git a/deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a4def26db4c7244b68bcd4b5277f54fc8b917154 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:098e646653a7504851af225d2edee57dd4533cb961cb8626818dc36afdbdcc1b +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c75e9f7883463882c7fed4e8c9b3f7d130cfe90e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_0_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..700d9c00346f46101bc5973f24b7a78b6476f2d9 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:375d923a2a650928fa46fba8bf7798d76aadbc9e954bc3948d8f316c4ab7e422 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ad057ec33226dd92818e0221690cfab99a2f7ce5 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_0_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e773326e4ea0d075505e655752ac141a0cbf12b5 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_10_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..9a8f223f9fe8fc9869aed75a9dfd41594096bf16 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_10_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..531f05ed13bc6039ef40b9a6687fa10cfb56d9dd --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:db558f6fd2098270a15f1ea029d8fb93fbd239db60757a9a65d5bb0ed7ff9652 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..26f42192e9881c5c406f722bf63a924c45a416ee --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_10_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7a3d6d723eeb942b989ac7678a2cf2c6c1367bcb --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:c9579f964fcb3df2696abddda48e759a5d8c1f2bc487b0f063ec0695b5ab4b15 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4fdbf2d1500d88e97184bedfa89f8e16ba73441 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_11_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_11_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..88967b115589851b4ceae504665f361cdd3b7231 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_11_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4d3de0929279cf32f0daf7b66668c0010af2c35be8705c39f0bd38df32bfaf87 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c714e2f18dd61e45681040cdfed32a0473761dfa --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:12a84683fe00606eb7cf8806a17f580158e57cf7d7528a8f968c511e7d209933 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8c6f5a5e5f0fe4b2761fa2db0008d1ea0d41b191 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b53fd1602f017e71cb16894dc7b50dc5afd1926ed9cde72767207cd0f0dcfed5 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e72796c970ce0f95ea8e386b39da4f3e70d024bc --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5f78b362fac20ba1a16a6fca50637cfec65b10bde052298df0e9991fc66515e9 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cc729c54afc3f0c2c1c88a0dfca4fa11397abe44 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e9630c66d58e38b5b9b2810e4ad323c067f5808b1175fbea25ab68e0865760b2 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2b9b21163fe6fb7c4c9dcfab243b6cdfd1802024 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_12_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_12_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e7387c3abe3ddcbc733447931c042762072b17cf --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_12_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:52b100fd3247ca393310298d393539cc8ba37a22fda2d5977f669ed67cd385dd +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4b71edcc9ed1aec8d8a1e2002637e6950f74203e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b94fd67a23609af016e14b95b967d5ff948feeeffffad7a50970e7caf97a9b63 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4cf4dc1719e76f1237ec67ccfd21e5a99b8cb818 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8a79693505c9da3e0aad1b04728b870c72e49370da7d40888062732fb391ba88 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..68521e8c93bf651fd7a829721cbb52c9e02530d2 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_14_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..3a7cacd7a38ce74c10d60eaf6975fb7fb997ab23 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c6b3ef9ac202a5eda9c12904543b4397dc9df0de48f9d6fe7ef5f9843cb77b1 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f7e78ab91a6cd2f45495134c0d7698aa49f1b9c4 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4dd535d6c498f54b3cddbfcfa80da0a78e9e43a6deb0798d6bca600f83be329a +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..2354d5c4b7a0209bd3ffb708cdb037c4274eb380 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_14_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..98f603c35ed1ff48df53fa179f3f2c7d03dd7956 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f9596642b9e13fdb69c4af5c872a9b442cf99412eb0028a7106d12859f311d59 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fd6f2e7c532aa5f7ef590882bf23f97b9e76e091 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_14_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d2edc68208f7bb6d85e2a690fe9d465de7032c47 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_14_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:822626fac1588751eb47ce6139fc2ca8ef65739b985580207e5a6363846fbbb3 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4a204bf08c49122a190d0ecf100ef2ae4391f1b6 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_16_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c2300fd08b3af80996bdcf8d3c9db1dc434c8d8f --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3818f25308dde22cda8225b921ca7271e36d068afd7c339b4d769dc3d2fc1a2a +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fc4aa63868a73a31d9dc086929886ad8666564ff --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9731f2011ae0f4b45652c84dacbc5301e25ed9212516e32fa8b60508c7726ccf +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..68db0f64d31e402df933296b9f0b756032552aa9 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_16_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..484dac0e955f15ac4b3222ec401cb3b588aa2b90 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:81be6d1fc622410812b9d7895856d0ebe503796e843dfbbba7acd4a916b8f36a +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a85476ad468c989ce30f852ab42aaa8ea8a0dbc8 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_17_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..36b9ba937c3a2304b9d505187b96c9506e9e64cf --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3b1146909c6382a4c90df7528fd4fb2d97c8608eb6cf6580e33201f64e4d2b09 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..445b38859aa91dfee64aa73b4e2e49cba18fef7f --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_17_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_17_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..c8412571cdf7c7d7a235d8e4e1e77ac4c5277398 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_17_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0b9dd4c784039c9c20c5d7e916c02a0fcadaa976 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5c5354d66122352c5c9ca48f3475831c2e86adf81e39171ceab2c368c20d4851 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..1d3dec39ff297f544ae5b3e2cea79ef9a5a767c6 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e76316b20833b268c7331c8c965529629cc0dbe88c8af205fef2a82175e86640 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7bc648b61480d4d8efee98ca25d05cbc8161e131 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_18_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..99821fa8e7335187b2b6fa658b6fbfe73c1ccdb1 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:034e6da56f3122c85e3c67a1e096b577215311e26f586e9f90d369b9b05af14c +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..3a7e4174524872129dd9b1f87493b0021bec5ccf --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_18_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..b0f9725b406834a08492d7d164664fa27841b26a --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_18_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_18_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..43e4136285e9dafa6169eddc6ed7768707425efb --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_18_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:694fd723545a04150e46b21c93059c4caff0ff410aaec1816f6d820005d6d463 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fbfe939e7908673df0285bca06522eee6c8caacb --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:18ca353ed88b0ac2eba2cc2f253baf0cddd99fdf140ec7cddc9a0405bd7d9dc6 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d4884e4bf1d1530a73e6a8dea00b0d13fd65cc0d --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ae02f0a9c0eb7a93eee1fcc59edce4b23a5d9138d25b44e0e42cd14f998f59db +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fb2aa4a7fe173630db0b43c2931abcce7c3464fb --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:08424e49d21ccc66d3b0c591dc9f8a79d393b6f6c0a1b6177be5fa27130582f5 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe59371560baa115b55a7b935e80a4de8d985360 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_1_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..23c1e7925f9e7a67561d815bcc8a43cad34763c9 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:923748b8150865b6fa0eff5fbb2a4bdffb33759357c3e9f356f6e715220e9cdf +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..cc5c1cf2d1e4f4be860c6dfb5d3ae7cfbc662e2c --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8645313cde43d5c566be3b202b241ba4caa3887591ead18d7ac14388d8d9fc0a +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..56fc5db10d27ac481d30efd51f232d0da9992345 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_1_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..05a1a06741b19f02f72586b03b70b9b9e4151924 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:59eeabc50a6c38eef129a1792bdf3f35851f5a4c28acf8a9b6955fd6c6050297 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a626a86fffa107c2a2802ba32636c7d9d750cf0d --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_1_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_1_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..de16329ced2714d70ba5372f7cb362dbf023f395 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_1_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1d61731bef42a37fbce75bbdf080764a4d9dee351d283893228f3ac868ebbcea +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f8dd8a9d132ec8d2e1002dcad13ad9b4067432dc --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:70cc309e7990860ebcc405f50aea6b1edb3ab94b9a0a933bb5f07795a062e5dd +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4cd99d3feb54c5dc8adbaa8f062bf3159f34f925 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_20_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..fe1ea4c644e2e3eb04a5b24385212b3642110559 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dad4d286d838ba5f6ec5e6158fe4da2211226cff83ac2de2b9944c055b283b27 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..20edd82168699c22462b094aa7e35bb7b9cb737b --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ec96c69686afe7685bde1cef964dfa13eaa58ef248ce4bf51bdc3b22240ae612 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f00efb51c0274828ebb2f4edcfc0f44f2a57f10e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_21_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..89e1d2c8b372b909596dc6fa880b499df8ebc37d --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:27bd017985209042acd498a7a0666b7dfbe9f444706fda95916de83664888c97 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..97bd86bf817807baf8c8d049cb656e19d17207a8 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:bd0ef281d1095407152d57e0fe090257cbac64739161102265df2aa4c2ade9a1 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..76a6dffe65dd11314ec5764d82aecad61358cf41 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_21_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..18b37efa2c8f65f149df1550b7cbc8ac3f2853cf --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_21_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:af417b0930e6a08a43d4fa39ef4073d8137894119870625779cb3d325b3c4b8c +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..45f27f83cf9a152965c39de2379d87f077f208ac --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:e57eaea8ed6a8c7856e5875639e86577f0cc673d33d112e4658879f692f504fe +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4cbb5ad6e5f6417217bfa1af6ca7c523183bee89 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_22_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_22_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..0e7f57dec545e4927e414dde4716b45b76c5d6c7 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_22_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3102ad733bfa162c14f6de5442f2fda223de45069f3122dd98eeb41319096841 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..8f89222fdbe4450d13e09d53c996f539f7b7e4cb --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_22_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_22_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..ea066da65251182b79b153b5a9bf3c599a1161fe --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_22_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d6b0030aca31849627578413fa00b158443178aeb29f43c07629c841fa3ed231 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e774425e7acd5a3296dc36aa3d6fa3c5c915c365 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fdb4f579794a1da4bbe64e28165b21f74c32e9b2272309af254896cf6cf5ab41 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..5a3cce1fc8391388ce73e2ab0cc6d9e9e9a766d4 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:a84bfa01fb9da09db3183e8891c3de79ce3fbb044edc2f0fe4fd0d6e0ad7edda +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a0c0f48e833fb69ecaaef1b1ce5255d8c3e986e9 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:0141cb8ea92a588e77092c05bd16d7d60ba8c067e686a90a77ab5f10af90b51b +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..06ca5014339d1d681c7d77318182d1dc3411b689 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:9bffaa828a94eb1f667e5adf8967d0bacc5007bff2101bc6abeeddb36db74fb5 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..55a527bb3c1ecbbd996713b8b7b663867ebe5474 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_23_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..0ebcbc6a03a0b38051e288c48351634986f0a34a --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_23_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..da7a8550e4874ab7c5d134d4dfbc0216cd8480b3 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_23_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:b84ebcfc73188bd0d422fe9dc66fba0162be7fec858db249199caba417f78361 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..ff17124f9d467c54aa4ed5a4ef9b19ac812661c4 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_24_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_24_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..08e7b9ab0826f74243f5c2e603ca4375e9dec3d2 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_24_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_24_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a08ab5cc8dc08690389002eeaec14fa28c01d57a --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_24_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_24_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..a23b6f8b90c41fedec93ecff7f17e0a5423b127c --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_24_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6e134bd68d2bcd5a52bd64fdd6437f7f21b3c1370edd8b190185fdd12259f35f +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..835618fbaeb454c02cd19e4db4e1b5b90a754cf6 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:ffcd705d3d42d1ab5a1ee06c2891ef09e20271875e975f2689c1771ec595f06e +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8d530e76f2ffad35756e862e0939bd38b4a1337d --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:7b58951a493101eeca9e658f0284645a5d4e1ddbfea1827b19340c936ed9d1ef +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..acda4dd42aab98a628095119c03a61c703d49b7f --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:d498ab519060f68ada97338f53121970dfeb43385fe8893d8a2d3032e38fc8d1 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..00981cc6002c15e0706ad076d0290e6971602f73 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_25_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..92a2ab2176374a60bf7ec9f4baf2625e540d5298 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:89573ad24dd3441212a9bc71ac416cb7933a8380c8fe95a793bd26120517803d +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..cc8cfa4971b31665280221619e0f4ecaf610fadd --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_26_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..21ce500e87639076da235fcacd4ff71c137058c3 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2d2a54145fa10845da172a175309fe5517279f9bcd2f4d2f93a783390d0f4563 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..34cb9c5845fcca93bbfda851426bf39a45655e63 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_26_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..703a2c0d3c286b3c0b1366505f7f89d0b763686c --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2013586c28728e30af6893083fbe2edd62e78101e78994a1059271d8950a20d9 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..430186ee5ff4f73855cda1acc4c17021160e351d --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f7a2b419b3a715df58d819735f21c7acdadad4449fbd69a81464da7fca17184 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..efa6edd3a260dfde31f724e0b24f794570a0edcf --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_2_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..42035771d625bd0cc27ef6bc3e5cc37003781943 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f4a52d815a57ce406a834ea776712d9bad17f10c7f3bc6f0c23662fa2bfeddf0 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..831d5ac9e56a4a3669eced6887fb24b4a9051d4e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:f06a6d79752ef1fd84c0369883a18376a0962a54995b2539d0067b91f985f593 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..dedc1ef084d019c2871fabc2d811b83990c74081 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_3_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_3_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..5d82add41ab3145e77b2776f89a496bc68103076 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_3_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_3_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a8a4a34f4627de28681a7ef6baf444341add0356 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_3_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..831a0d35ad601f61dd2ee8c7e7286aba20dcfeb0 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:5db537d0d2cbe560232c96439503e2864cc0074a0267235168dd65125b429353 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..bfc656f39666afadb6f56e80ba4b2be0e33c9bb3 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:1835160987ada5c7cfa5a8005381acfb70dfa1760f1192a9ed8b05895d721f06 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..12a90022c8521c3b7ca0b9c273dc1a34fa7bfa9e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_3_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..60f663fd87b94df31fb4a1137b65c50e5f086c4e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_3_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:4f9e1317d4eecddbf00cfb8c5f2514ec11c98ba5f47f8797045bc41a72a5ad8d +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6778191f3d69bf956ab447b7c96aba57c8a6ddf1 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:789abaaf65194d903a703e27fc3f587814fa91a44d88badadcfde84877c4b753 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b41d8a2296975324a3ca9d945c39e14dbe91b802 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:30da63b8137b635374c8492f307db48c16f7acc178445c1464d404f20fc37651 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_4_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_4_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..29924eb3a070f23a4061a5b4936972a70d173159 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_4_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:cb1aaefbf77fa0a135b5c612aeffa63732c08b6ecc0b072126ba41329f07d806 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..e55b1ce5f34d272087edea1d72aaa7fd0698f79f --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:580bd40e8c9a7411c484b81a00d42e5a906cd4ce5b912dde60dc4738b4e8a621 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_5_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_5_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8beb30a5655eecfadd1a28aaf44e6510100d27d3 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_5_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:dd1eb88f8f2d4a6bdf0c3ff49f8d1d20ff8862234f7c25a52a7925122910015b +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4713697103e199d6d1764fedd842080e3feecd59 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_6_mlp_gate_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f9164b42a217d35f1f9b2817041cfdd46e3b48fa --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:94784b57b3f318aa6cd0df844d0bc8c79eaf30921ced759ffca39b9be28cf204 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..74506f27e4dd1c745a60823f193584215445e39b --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:da5dc297392f79c9d8d0f205dc88a22350d3db360b16d1ef21d6706c458bc8de +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..4efa1ba0a0818418d8100943433e79f8532e40ea --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_6_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_6_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..7cb3243b2812ceda899fb1a58c169af787c12533 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_6_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:97fe1516009f4ea6f36ab12b2ae53993151d03b565ce49e2eecf4dff09d16f60 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..72c05f28798691e9f47a84ce0ad076c4e1cd45a3 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_6_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_6_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..b31577875ebe23f338952e6e6d318d1be1a2044e --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_6_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:8d7d61ca3b072a618e4f08d22476bc2ccb6909f5b3cd7545f2634f8f844b27f9 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..f2bc88d3ecc168172d9815944b90a249f1f3a15c --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_7_mlp_gate_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_7_mlp_gate_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..d18791cd1d7deff3a55b2a6f070d468dd27e44f9 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_7_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..8346cf07e10919ca45dab2670d219046da711b2f --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:569f641655e1b4bb194c5272e6575ac3d4b574115d351b41fb7c9189034e8a2b +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..fe5ba90dbc97bd5ce02bf72bcbc6cb1ab7d3acef --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_7_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_7_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..4f443dcdea496654f59256217b1ab09731eba948 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_7_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:3c19697df152bc76e8d02c4059a03ea17d0021085e0a7ed0933fb162febbe71d +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..e4317211761b1e83b5112d19e59467e8a51bd1c3 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_7_self_attn_v_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_7_self_attn_v_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..f4e27b9913f6b41f4984c55cfc70c7f3b030ce64 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_7_self_attn_v_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6520b7fe6f7595ae4ad8583c799fdefcca198209ef52661290f485f22a398c13 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..993ea624b1893abd15291f1e07dd18153f4a91fd --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:6cf84b8a3a59ea28eb2fc122e1965eb300737ccd66e26ad63ae4fbdd8338b0dd +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..61185887dcc9b25b674d61ffbf8a9f077e8d2a4b --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fce484de6fe36304b663c52456f80ca56081064d48a13a3c9dfca4d3e4b88f9f +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..23166f78fc7398891dc4b7a225fb238bf2c1a4c1 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_8_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..82ade7b6ab4ddf9ad00a5fc768efdfb43e80fdcd --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:34daa06621baf96638c1d76c7ed2cbf09af38e98312e691a307aba0f5592c8c7 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..a585069c982ec6830f80482e7004cbd25ee16f16 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_9_mlp_down_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..22fe8983de5183faf8c1f790304924262d3b56fe --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:2be8e812ded5f57adcbe0949b826216d0c04390763edbdf48809369892c38752 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..d79891c14d065808b829f919e1d13de979991a95 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:854e8235e72aab9e3a28fbf8043766be5ead914ca655bc58b79c129dd2d72ca2 +size 6881280 diff --git a/deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..6b23d7902cb40d7d8ea83d221cd2894883a95d6a --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_9_self_attn_k_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_k_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..6b457cdad7fd1a7281b483199dd637c2d025ef35 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_k_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:13d789d1643ed100a12617ced7f9baa55cab0f257d276efdcecac7e1dec609a7 +size 196608 diff --git a/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..7779f95a229a2f7df437f13048d611beca13a501 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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-unary4/model_layers_9_self_attn_q_proj_weight.planes b/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.planes new file mode 100644 index 0000000000000000000000000000000000000000..c2cf27dc574acd5f32e1954915d925ca1bed92b8 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.planes @@ -0,0 +1,3 @@ +version https://git-lfs.github.com/spec/v1 +oid sha256:fa2b89c6d4c8de32ff18c0cd36acee4e9a07177d6734098d58998d678040f7c6 +size 1179648 diff --git a/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.sign b/deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.sign new file mode 100644 index 0000000000000000000000000000000000000000..df93509d64067043b6f37b652ff5aae9ef8f6ca9 --- /dev/null +++ b/deepseek-r1-1.5b-unary4/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