Open4bits/DeepSeek-R1-mlx-2Bit
278
1{2 "metadata": {3 "total_size": 209877110784,4 "total_parameters": 6710264192005 },6 "weight_map": {7 "lm_head.biases": "model-00044-of-00044.safetensors",8 "lm_head.scales": "model-00044-of-00044.safetensors",9 "lm_head.weight": "model-00044-of-00044.safetensors",10 "model.embed_tokens.biases": "model-00001-of-00044.safetensors",11 "model.embed_tokens.scales": "model-00001-of-00044.safetensors",12 "model.embed_tokens.weight": "model-00001-of-00044.safetensors",13 "model.layers.0.input_layernorm.weight": "model-00001-of-00044.safetensors",14 "model.layers.0.mlp.down_proj.biases": "model-00001-of-00044.safetensors",15 "model.layers.0.mlp.down_proj.scales": "model-00001-of-00044.safetensors",16 "model.layers.0.mlp.down_proj.weight": "model-00001-of-00044.safetensors",17 "model.layers.0.mlp.gate_proj.biases": "model-00001-of-00044.safetensors",18 "model.layers.0.mlp.gate_proj.scales": "model-00001-of-00044.safetensors",19 "model.layers.0.mlp.gate_proj.weight": "model-00001-of-00044.safetensors",20 "model.layers.0.mlp.up_proj.biases": "model-00001-of-00044.safetensors",21 "model.layers.0.mlp.up_proj.scales": "model-00001-of-00044.safetensors",22 "model.layers.0.mlp.up_proj.weight": "model-00001-of-00044.safetensors",23 "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00044.safetensors",24 "model.layers.0.self_attn.kv_a_layernorm.weight": "model-00001-of-00044.safetensors",25 "model.layers.0.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00044.safetensors",26 "model.layers.0.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00044.safetensors",27 "model.layers.0.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00044.safetensors",28 "model.layers.0.self_attn.kv_b_proj.biases": "model-00001-of-00044.safetensors",29 "model.layers.0.self_attn.kv_b_proj.scales": "model-00001-of-00044.safetensors",30 "model.layers.0.self_attn.kv_b_proj.weight": "model-00001-of-00044.safetensors",31 "model.layers.0.self_attn.o_proj.biases": "model-00001-of-00044.safetensors",32 "model.layers.0.self_attn.o_proj.scales": "model-00001-of-00044.safetensors",33 "model.layers.0.self_attn.o_proj.weight": "model-00001-of-00044.safetensors",34 "model.layers.0.self_attn.q_a_layernorm.weight": "model-00001-of-00044.safetensors",35 "model.layers.0.self_attn.q_a_proj.biases": "model-00001-of-00044.safetensors",36 "model.layers.0.self_attn.q_a_proj.scales": "model-00001-of-00044.safetensors",37 "model.layers.0.self_attn.q_a_proj.weight": "model-00001-of-00044.safetensors",38 "model.layers.0.self_attn.q_b_proj.biases": "model-00001-of-00044.safetensors",39 "model.layers.0.self_attn.q_b_proj.scales": "model-00001-of-00044.safetensors",40 "model.layers.0.self_attn.q_b_proj.weight": "model-00001-of-00044.safetensors",41 "model.layers.1.input_layernorm.weight": "model-00001-of-00044.safetensors",42 "model.layers.1.mlp.down_proj.biases": "model-00001-of-00044.safetensors",43 "model.layers.1.mlp.down_proj.scales": "model-00001-of-00044.safetensors",44 "model.layers.1.mlp.down_proj.weight": "model-00001-of-00044.safetensors",45 "model.layers.1.mlp.gate_proj.biases": "model-00001-of-00044.safetensors",46 "model.layers.1.mlp.gate_proj.scales": "model-00001-of-00044.safetensors",47 "model.layers.1.mlp.gate_proj.weight": "model-00001-of-00044.safetensors",48 "model.layers.1.mlp.up_proj.biases": "model-00001-of-00044.safetensors",49 "model.layers.1.mlp.up_proj.scales": "model-00001-of-00044.safetensors",50 "model.layers.1.mlp.up_proj.weight": "model-00001-of-00044.safetensors",51 "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00044.safetensors",52 "model.layers.1.self_attn.kv_a_layernorm.weight": "model-00001-of-00044.safetensors",53 "model.layers.1.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00044.safetensors",54 "model.layers.1.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00044.safetensors",55 "model.layers.1.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00044.safetensors",56 "model.layers.1.self_attn.kv_b_proj.biases": "model-00001-of-00044.safetensors",57 "model.layers.1.self_attn.kv_b_proj.scales": "model-00001-of-00044.safetensors",58 "model.layers.1.self_attn.kv_b_proj.weight": "model-00001-of-00044.safetensors",59 "model.layers.1.self_attn.o_proj.biases": "model-00001-of-00044.safetensors",60 "model.layers.1.self_attn.o_proj.scales": "model-00001-of-00044.safetensors",61 "model.layers.1.self_attn.o_proj.weight": "model-00001-of-00044.safetensors",62 "model.layers.1.self_attn.q_a_layernorm.weight": "model-00001-of-00044.safetensors",63 "model.layers.1.self_attn.q_a_proj.biases": "model-00001-of-00044.safetensors",64 "model.layers.1.self_attn.q_a_proj.scales": "model-00001-of-00044.safetensors",65 "model.layers.1.self_attn.q_a_proj.weight": "model-00001-of-00044.safetensors",66 "model.layers.1.self_attn.q_b_proj.biases": "model-00001-of-00044.safetensors",67 "model.layers.1.self_attn.q_b_proj.scales": "model-00001-of-00044.safetensors",68 "model.layers.1.self_attn.q_b_proj.weight": "model-00001-of-00044.safetensors",69 "model.layers.10.input_layernorm.weight": "model-00007-of-00044.safetensors",70 "model.layers.10.mlp.gate.e_score_correction_bias": "model-00007-of-00044.safetensors",71 "model.layers.10.mlp.gate.weight": "model-00007-of-00044.safetensors",72 "model.layers.10.mlp.shared_experts.down_proj.biases": "model-00007-of-00044.safetensors",73 "model.layers.10.mlp.shared_experts.down_proj.scales": "model-00007-of-00044.safetensors",74 "model.layers.10.mlp.shared_experts.down_proj.weight": "model-00007-of-00044.safetensors",75 "model.layers.10.mlp.shared_experts.gate_proj.biases": "model-00007-of-00044.safetensors",76 "model.layers.10.mlp.shared_experts.gate_proj.scales": "model-00007-of-00044.safetensors",77 "model.layers.10.mlp.shared_experts.gate_proj.weight": "model-00007-of-00044.safetensors",78 "model.layers.10.mlp.shared_experts.up_proj.biases": "model-00007-of-00044.safetensors",79 "model.layers.10.mlp.shared_experts.up_proj.scales": "model-00007-of-00044.safetensors",80 "model.layers.10.mlp.shared_experts.up_proj.weight": "model-00007-of-00044.safetensors",81 "model.layers.10.mlp.switch_mlp.down_proj.biases": "model-00007-of-00044.safetensors",82 "model.layers.10.mlp.switch_mlp.down_proj.scales": "model-00007-of-00044.safetensors",83 "model.layers.10.mlp.switch_mlp.down_proj.weight": "model-00007-of-00044.safetensors",84 "model.layers.10.mlp.switch_mlp.gate_proj.biases": "model-00006-of-00044.safetensors",85 "model.layers.10.mlp.switch_mlp.gate_proj.scales": "model-00006-of-00044.safetensors",86 "model.layers.10.mlp.switch_mlp.gate_proj.weight": "model-00006-of-00044.safetensors",87 "model.layers.10.mlp.switch_mlp.up_proj.biases": "model-00006-of-00044.safetensors",88 "model.layers.10.mlp.switch_mlp.up_proj.scales": "model-00006-of-00044.safetensors",89 "model.layers.10.mlp.switch_mlp.up_proj.weight": "model-00006-of-00044.safetensors",90 "model.layers.10.post_attention_layernorm.weight": "model-00007-of-00044.safetensors",91 "model.layers.10.self_attn.kv_a_layernorm.weight": "model-00006-of-00044.safetensors",92 "model.layers.10.self_attn.kv_a_proj_with_mqa.biases": "model-00006-of-00044.safetensors",93 "model.layers.10.self_attn.kv_a_proj_with_mqa.scales": "model-00006-of-00044.safetensors",94 "model.layers.10.self_attn.kv_a_proj_with_mqa.weight": "model-00006-of-00044.safetensors",95 "model.layers.10.self_attn.kv_b_proj.biases": "model-00006-of-00044.safetensors",96 "model.layers.10.self_attn.kv_b_proj.scales": "model-00006-of-00044.safetensors",97 "model.layers.10.self_attn.kv_b_proj.weight": "model-00006-of-00044.safetensors",98 "model.layers.10.self_attn.o_proj.biases": "model-00006-of-00044.safetensors",99 "model.layers.10.self_attn.o_proj.scales": "model-00006-of-00044.safetensors",100 "model.layers.10.self_attn.o_proj.weight": "model-00006-of-00044.safetensors",101 "model.layers.10.self_attn.q_a_layernorm.weight": "model-00006-of-00044.safetensors",102 "model.layers.10.self_attn.q_a_proj.biases": "model-00006-of-00044.safetensors",103 "model.layers.10.self_attn.q_a_proj.scales": "model-00006-of-00044.safetensors",104 "model.layers.10.self_attn.q_a_proj.weight": "model-00006-of-00044.safetensors",105 "model.layers.10.self_attn.q_b_proj.biases": "model-00006-of-00044.safetensors",106 "model.layers.10.self_attn.q_b_proj.scales": "model-00006-of-00044.safetensors",107 "model.layers.10.self_attn.q_b_proj.weight": "model-00006-of-00044.safetensors",108 "model.layers.11.input_layernorm.weight": "model-00007-of-00044.safetensors",109 "model.layers.11.mlp.gate.e_score_correction_bias": "model-00007-of-00044.safetensors",110 "model.layers.11.mlp.gate.weight": "model-00007-of-00044.safetensors",111 "model.layers.11.mlp.shared_experts.down_proj.biases": "model-00007-of-00044.safetensors",112 "model.layers.11.mlp.shared_experts.down_proj.scales": "model-00007-of-00044.safetensors",113 "model.layers.11.mlp.shared_experts.down_proj.weight": "model-00007-of-00044.safetensors",114 "model.layers.11.mlp.shared_experts.gate_proj.biases": "model-00007-of-00044.safetensors",115 "model.layers.11.mlp.shared_experts.gate_proj.scales": "model-00007-of-00044.safetensors",116 "model.layers.11.mlp.shared_experts.gate_proj.weight": "model-00007-of-00044.safetensors",117 "model.layers.11.mlp.shared_experts.up_proj.biases": "model-00007-of-00044.safetensors",118 "model.layers.11.mlp.shared_experts.up_proj.scales": "model-00007-of-00044.safetensors",119 "model.layers.11.mlp.shared_experts.up_proj.weight": "model-00007-of-00044.safetensors",120 "model.layers.11.mlp.switch_mlp.down_proj.biases": "model-00007-of-00044.safetensors",121 "model.layers.11.mlp.switch_mlp.down_proj.scales": "model-00007-of-00044.safetensors",122 "model.layers.11.mlp.switch_mlp.down_proj.weight": "model-00007-of-00044.safetensors",123 "model.layers.11.mlp.switch_mlp.gate_proj.biases": "model-00007-of-00044.safetensors",124 "model.layers.11.mlp.switch_mlp.gate_proj.scales": "model-00007-of-00044.safetensors",125 "model.layers.11.mlp.switch_mlp.gate_proj.weight": "model-00007-of-00044.safetensors",126 "model.layers.11.mlp.switch_mlp.up_proj.biases": "model-00007-of-00044.safetensors",127 "model.layers.11.mlp.switch_mlp.up_proj.scales": "model-00007-of-00044.safetensors",128 "model.layers.11.mlp.switch_mlp.up_proj.weight": "model-00007-of-00044.safetensors",129 "model.layers.11.post_attention_layernorm.weight": "model-00007-of-00044.safetensors",130 "model.layers.11.self_attn.kv_a_layernorm.weight": "model-00007-of-00044.safetensors",131 "model.layers.11.self_attn.kv_a_proj_with_mqa.biases": "model-00007-of-00044.safetensors",132 "model.layers.11.self_attn.kv_a_proj_with_mqa.scales": "model-00007-of-00044.safetensors",133 "model.layers.11.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00044.safetensors",134 "model.layers.11.self_attn.kv_b_proj.biases": "model-00007-of-00044.safetensors",135 "model.layers.11.self_attn.kv_b_proj.scales": "model-00007-of-00044.safetensors",136 "model.layers.11.self_attn.kv_b_proj.weight": "model-00007-of-00044.safetensors",137 "model.layers.11.self_attn.o_proj.biases": "model-00007-of-00044.safetensors",138 "model.layers.11.self_attn.o_proj.scales": "model-00007-of-00044.safetensors",139 "model.layers.11.self_attn.o_proj.weight": "model-00007-of-00044.safetensors",140 "model.layers.11.self_attn.q_a_layernorm.weight": "model-00007-of-00044.safetensors",141 "model.layers.11.self_attn.q_a_proj.biases": "model-00007-of-00044.safetensors",142 "model.layers.11.self_attn.q_a_proj.scales": "model-00007-of-00044.safetensors",143 "model.layers.11.self_attn.q_a_proj.weight": "model-00007-of-00044.safetensors",144 "model.layers.11.self_attn.q_b_proj.biases": "model-00007-of-00044.safetensors",145 "model.layers.11.self_attn.q_b_proj.scales": "model-00007-of-00044.safetensors",146 "model.layers.11.self_attn.q_b_proj.weight": "model-00007-of-00044.safetensors",147 "model.layers.12.input_layernorm.weight": "model-00008-of-00044.safetensors",148 "model.layers.12.mlp.gate.e_score_correction_bias": "model-00008-of-00044.safetensors",149 "model.layers.12.mlp.gate.weight": "model-00008-of-00044.safetensors",150 "model.layers.12.mlp.shared_experts.down_proj.biases": "model-00008-of-00044.safetensors",151 "model.layers.12.mlp.shared_experts.down_proj.scales": "model-00008-of-00044.safetensors",152 "model.layers.12.mlp.shared_experts.down_proj.weight": "model-00008-of-00044.safetensors",153 "model.layers.12.mlp.shared_experts.gate_proj.biases": "model-00008-of-00044.safetensors",154 "model.layers.12.mlp.shared_experts.gate_proj.scales": "model-00008-of-00044.safetensors",155 "model.layers.12.mlp.shared_experts.gate_proj.weight": "model-00008-of-00044.safetensors",156 "model.layers.12.mlp.shared_experts.up_proj.biases": "model-00008-of-00044.safetensors",157 "model.layers.12.mlp.shared_experts.up_proj.scales": "model-00008-of-00044.safetensors",158 "model.layers.12.mlp.shared_experts.up_proj.weight": "model-00008-of-00044.safetensors",159 "model.layers.12.mlp.switch_mlp.down_proj.biases": "model-00008-of-00044.safetensors",160 "model.layers.12.mlp.switch_mlp.down_proj.scales": "model-00008-of-00044.safetensors",161 "model.layers.12.mlp.switch_mlp.down_proj.weight": "model-00008-of-00044.safetensors",162 "model.layers.12.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00044.safetensors",163 "model.layers.12.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00044.safetensors",164 "model.layers.12.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00044.safetensors",165 "model.layers.12.mlp.switch_mlp.up_proj.biases": "model-00008-of-00044.safetensors",166 "model.layers.12.mlp.switch_mlp.up_proj.scales": "model-00008-of-00044.safetensors",167 "model.layers.12.mlp.switch_mlp.up_proj.weight": "model-00008-of-00044.safetensors",168 "model.layers.12.post_attention_layernorm.weight": "model-00008-of-00044.safetensors",169 "model.layers.12.self_attn.kv_a_layernorm.weight": "model-00007-of-00044.safetensors",170 "model.layers.12.self_attn.kv_a_proj_with_mqa.biases": "model-00007-of-00044.safetensors",171 "model.layers.12.self_attn.kv_a_proj_with_mqa.scales": "model-00007-of-00044.safetensors",172 "model.layers.12.self_attn.kv_a_proj_with_mqa.weight": "model-00007-of-00044.safetensors",173 "model.layers.12.self_attn.kv_b_proj.biases": "model-00007-of-00044.safetensors",174 "model.layers.12.self_attn.kv_b_proj.scales": "model-00007-of-00044.safetensors",175 "model.layers.12.self_attn.kv_b_proj.weight": "model-00007-of-00044.safetensors",176 "model.layers.12.self_attn.o_proj.biases": "model-00007-of-00044.safetensors",177 "model.layers.12.self_attn.o_proj.scales": "model-00007-of-00044.safetensors",178 "model.layers.12.self_attn.o_proj.weight": "model-00007-of-00044.safetensors",179 "model.layers.12.self_attn.q_a_layernorm.weight": "model-00007-of-00044.safetensors",180 "model.layers.12.self_attn.q_a_proj.biases": "model-00007-of-00044.safetensors",181 "model.layers.12.self_attn.q_a_proj.scales": "model-00007-of-00044.safetensors",182 "model.layers.12.self_attn.q_a_proj.weight": "model-00007-of-00044.safetensors",183 "model.layers.12.self_attn.q_b_proj.biases": "model-00007-of-00044.safetensors",184 "model.layers.12.self_attn.q_b_proj.scales": "model-00007-of-00044.safetensors",185 "model.layers.12.self_attn.q_b_proj.weight": "model-00007-of-00044.safetensors",186 "model.layers.13.input_layernorm.weight": "model-00009-of-00044.safetensors",187 "model.layers.13.mlp.gate.e_score_correction_bias": "model-00009-of-00044.safetensors",188 "model.layers.13.mlp.gate.weight": "model-00009-of-00044.safetensors",189 "model.layers.13.mlp.shared_experts.down_proj.biases": "model-00009-of-00044.safetensors",190 "model.layers.13.mlp.shared_experts.down_proj.scales": "model-00009-of-00044.safetensors",191 "model.layers.13.mlp.shared_experts.down_proj.weight": "model-00009-of-00044.safetensors",192 "model.layers.13.mlp.shared_experts.gate_proj.biases": "model-00009-of-00044.safetensors",193 "model.layers.13.mlp.shared_experts.gate_proj.scales": "model-00009-of-00044.safetensors",194 "model.layers.13.mlp.shared_experts.gate_proj.weight": "model-00009-of-00044.safetensors",195 "model.layers.13.mlp.shared_experts.up_proj.biases": "model-00009-of-00044.safetensors",196 "model.layers.13.mlp.shared_experts.up_proj.scales": "model-00009-of-00044.safetensors",197 "model.layers.13.mlp.shared_experts.up_proj.weight": "model-00009-of-00044.safetensors",198 "model.layers.13.mlp.switch_mlp.down_proj.biases": "model-00009-of-00044.safetensors",199 "model.layers.13.mlp.switch_mlp.down_proj.scales": "model-00009-of-00044.safetensors",200 "model.layers.13.mlp.switch_mlp.down_proj.weight": "model-00009-of-00044.safetensors",201 "model.layers.13.mlp.switch_mlp.gate_proj.biases": "model-00008-of-00044.safetensors",202 "model.layers.13.mlp.switch_mlp.gate_proj.scales": "model-00008-of-00044.safetensors",203 "model.layers.13.mlp.switch_mlp.gate_proj.weight": "model-00008-of-00044.safetensors",204 "model.layers.13.mlp.switch_mlp.up_proj.biases": "model-00009-of-00044.safetensors",205 "model.layers.13.mlp.switch_mlp.up_proj.scales": "model-00009-of-00044.safetensors",206 "model.layers.13.mlp.switch_mlp.up_proj.weight": "model-00009-of-00044.safetensors",207 "model.layers.13.post_attention_layernorm.weight": "model-00009-of-00044.safetensors",208 "model.layers.13.self_attn.kv_a_layernorm.weight": "model-00008-of-00044.safetensors",209 "model.layers.13.self_attn.kv_a_proj_with_mqa.biases": "model-00008-of-00044.safetensors",210 "model.layers.13.self_attn.kv_a_proj_with_mqa.scales": "model-00008-of-00044.safetensors",211 "model.layers.13.self_attn.kv_a_proj_with_mqa.weight": "model-00008-of-00044.safetensors",212 "model.layers.13.self_attn.kv_b_proj.biases": "model-00008-of-00044.safetensors",213 "model.layers.13.self_attn.kv_b_proj.scales": "model-00008-of-00044.safetensors",214 "model.layers.13.self_attn.kv_b_proj.weight": "model-00008-of-00044.safetensors",215 "model.layers.13.self_attn.o_proj.biases": "model-00008-of-00044.safetensors",216 "model.layers.13.self_attn.o_proj.scales": "model-00008-of-00044.safetensors",217 "model.layers.13.self_attn.o_proj.weight": "model-00008-of-00044.safetensors",218 "model.layers.13.self_attn.q_a_layernorm.weight": "model-00008-of-00044.safetensors",219 "model.layers.13.self_attn.q_a_proj.biases": "model-00008-of-00044.safetensors",220 "model.layers.13.self_attn.q_a_proj.scales": "model-00008-of-00044.safetensors",221 "model.layers.13.self_attn.q_a_proj.weight": "model-00008-of-00044.safetensors",222 "model.layers.13.self_attn.q_b_proj.biases": "model-00008-of-00044.safetensors",223 "model.layers.13.self_attn.q_b_proj.scales": "model-00008-of-00044.safetensors",224 "model.layers.13.self_attn.q_b_proj.weight": "model-00008-of-00044.safetensors",225 "model.layers.14.input_layernorm.weight": "model-00010-of-00044.safetensors",226 "model.layers.14.mlp.gate.e_score_correction_bias": "model-00010-of-00044.safetensors",227 "model.layers.14.mlp.gate.weight": "model-00010-of-00044.safetensors",228 "model.layers.14.mlp.shared_experts.down_proj.biases": "model-00010-of-00044.safetensors",229 "model.layers.14.mlp.shared_experts.down_proj.scales": "model-00010-of-00044.safetensors",230 "model.layers.14.mlp.shared_experts.down_proj.weight": "model-00010-of-00044.safetensors",231 "model.layers.14.mlp.shared_experts.gate_proj.biases": "model-00010-of-00044.safetensors",232 "model.layers.14.mlp.shared_experts.gate_proj.scales": "model-00010-of-00044.safetensors",233 "model.layers.14.mlp.shared_experts.gate_proj.weight": "model-00010-of-00044.safetensors",234 "model.layers.14.mlp.shared_experts.up_proj.biases": "model-00010-of-00044.safetensors",235 "model.layers.14.mlp.shared_experts.up_proj.scales": "model-00010-of-00044.safetensors",236 "model.layers.14.mlp.shared_experts.up_proj.weight": "model-00010-of-00044.safetensors",237 "model.layers.14.mlp.switch_mlp.down_proj.biases": "model-00010-of-00044.safetensors",238 "model.layers.14.mlp.switch_mlp.down_proj.scales": "model-00010-of-00044.safetensors",239 "model.layers.14.mlp.switch_mlp.down_proj.weight": "model-00010-of-00044.safetensors",240 "model.layers.14.mlp.switch_mlp.gate_proj.biases": "model-00009-of-00044.safetensors",241 "model.layers.14.mlp.switch_mlp.gate_proj.scales": "model-00009-of-00044.safetensors",242 "model.layers.14.mlp.switch_mlp.gate_proj.weight": "model-00009-of-00044.safetensors",243 "model.layers.14.mlp.switch_mlp.up_proj.biases": "model-00009-of-00044.safetensors",244 "model.layers.14.mlp.switch_mlp.up_proj.scales": "model-00009-of-00044.safetensors",245 "model.layers.14.mlp.switch_mlp.up_proj.weight": "model-00009-of-00044.safetensors",246 "model.layers.14.post_attention_layernorm.weight": "model-00010-of-00044.safetensors",247 "model.layers.14.self_attn.kv_a_layernorm.weight": "model-00009-of-00044.safetensors",248 "model.layers.14.self_attn.kv_a_proj_with_mqa.biases": "model-00009-of-00044.safetensors",249 "model.layers.14.self_attn.kv_a_proj_with_mqa.scales": "model-00009-of-00044.safetensors",250 "model.layers.14.self_attn.kv_a_proj_with_mqa.weight": "model-00009-of-00044.safetensors",251 "model.layers.14.self_attn.kv_b_proj.biases": "model-00009-of-00044.safetensors",252 "model.layers.14.self_attn.kv_b_proj.scales": "model-00009-of-00044.safetensors",253 "model.layers.14.self_attn.kv_b_proj.weight": "model-00009-of-00044.safetensors",254 "model.layers.14.self_attn.o_proj.biases": "model-00009-of-00044.safetensors",255 "model.layers.14.self_attn.o_proj.scales": "model-00009-of-00044.safetensors",256 "model.layers.14.self_attn.o_proj.weight": "model-00009-of-00044.safetensors",257 "model.layers.14.self_attn.q_a_layernorm.weight": "model-00009-of-00044.safetensors",258 "model.layers.14.self_attn.q_a_proj.biases": "model-00009-of-00044.safetensors",259 "model.layers.14.self_attn.q_a_proj.scales": "model-00009-of-00044.safetensors",260 "model.layers.14.self_attn.q_a_proj.weight": "model-00009-of-00044.safetensors",261 "model.layers.14.self_attn.q_b_proj.biases": "model-00009-of-00044.safetensors",262 "model.layers.14.self_attn.q_b_proj.scales": "model-00009-of-00044.safetensors",263 "model.layers.14.self_attn.q_b_proj.weight": "model-00009-of-00044.safetensors",264 "model.layers.15.input_layernorm.weight": "model-00010-of-00044.safetensors",265 "model.layers.15.mlp.gate.e_score_correction_bias": "model-00010-of-00044.safetensors",266 "model.layers.15.mlp.gate.weight": "model-00010-of-00044.safetensors",267 "model.layers.15.mlp.shared_experts.down_proj.biases": "model-00010-of-00044.safetensors",268 "model.layers.15.mlp.shared_experts.down_proj.scales": "model-00010-of-00044.safetensors",269 "model.layers.15.mlp.shared_experts.down_proj.weight": "model-00010-of-00044.safetensors",270 "model.layers.15.mlp.shared_experts.gate_proj.biases": "model-00010-of-00044.safetensors",271 "model.layers.15.mlp.shared_experts.gate_proj.scales": "model-00010-of-00044.safetensors",272 "model.layers.15.mlp.shared_experts.gate_proj.weight": "model-00010-of-00044.safetensors",273 "model.layers.15.mlp.shared_experts.up_proj.biases": "model-00010-of-00044.safetensors",274 "model.layers.15.mlp.shared_experts.up_proj.scales": "model-00010-of-00044.safetensors",275 "model.layers.15.mlp.shared_experts.up_proj.weight": "model-00010-of-00044.safetensors",276 "model.layers.15.mlp.switch_mlp.down_proj.biases": "model-00010-of-00044.safetensors",277 "model.layers.15.mlp.switch_mlp.down_proj.scales": "model-00010-of-00044.safetensors",278 "model.layers.15.mlp.switch_mlp.down_proj.weight": "model-00010-of-00044.safetensors",279 "model.layers.15.mlp.switch_mlp.gate_proj.biases": "model-00010-of-00044.safetensors",280 "model.layers.15.mlp.switch_mlp.gate_proj.scales": "model-00010-of-00044.safetensors",281 "model.layers.15.mlp.switch_mlp.gate_proj.weight": "model-00010-of-00044.safetensors",282 "model.layers.15.mlp.switch_mlp.up_proj.biases": "model-00010-of-00044.safetensors",283 "model.layers.15.mlp.switch_mlp.up_proj.scales": "model-00010-of-00044.safetensors",284 "model.layers.15.mlp.switch_mlp.up_proj.weight": "model-00010-of-00044.safetensors",285 "model.layers.15.post_attention_layernorm.weight": "model-00010-of-00044.safetensors",286 "model.layers.15.self_attn.kv_a_layernorm.weight": "model-00010-of-00044.safetensors",287 "model.layers.15.self_attn.kv_a_proj_with_mqa.biases": "model-00010-of-00044.safetensors",288 "model.layers.15.self_attn.kv_a_proj_with_mqa.scales": "model-00010-of-00044.safetensors",289 "model.layers.15.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00044.safetensors",290 "model.layers.15.self_attn.kv_b_proj.biases": "model-00010-of-00044.safetensors",291 "model.layers.15.self_attn.kv_b_proj.scales": "model-00010-of-00044.safetensors",292 "model.layers.15.self_attn.kv_b_proj.weight": "model-00010-of-00044.safetensors",293 "model.layers.15.self_attn.o_proj.biases": "model-00010-of-00044.safetensors",294 "model.layers.15.self_attn.o_proj.scales": "model-00010-of-00044.safetensors",295 "model.layers.15.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",296 "model.layers.15.self_attn.q_a_layernorm.weight": "model-00010-of-00044.safetensors",297 "model.layers.15.self_attn.q_a_proj.biases": "model-00010-of-00044.safetensors",298 "model.layers.15.self_attn.q_a_proj.scales": "model-00010-of-00044.safetensors",299 "model.layers.15.self_attn.q_a_proj.weight": "model-00010-of-00044.safetensors",300 "model.layers.15.self_attn.q_b_proj.biases": "model-00010-of-00044.safetensors",301 "model.layers.15.self_attn.q_b_proj.scales": "model-00010-of-00044.safetensors",302 "model.layers.15.self_attn.q_b_proj.weight": "model-00010-of-00044.safetensors",303 "model.layers.16.input_layernorm.weight": "model-00011-of-00044.safetensors",304 "model.layers.16.mlp.gate.e_score_correction_bias": "model-00011-of-00044.safetensors",305 "model.layers.16.mlp.gate.weight": "model-00011-of-00044.safetensors",306 "model.layers.16.mlp.shared_experts.down_proj.biases": "model-00011-of-00044.safetensors",307 "model.layers.16.mlp.shared_experts.down_proj.scales": "model-00011-of-00044.safetensors",308 "model.layers.16.mlp.shared_experts.down_proj.weight": "model-00011-of-00044.safetensors",309 "model.layers.16.mlp.shared_experts.gate_proj.biases": "model-00011-of-00044.safetensors",310 "model.layers.16.mlp.shared_experts.gate_proj.scales": "model-00011-of-00044.safetensors",311 "model.layers.16.mlp.shared_experts.gate_proj.weight": "model-00011-of-00044.safetensors",312 "model.layers.16.mlp.shared_experts.up_proj.biases": "model-00011-of-00044.safetensors",313 "model.layers.16.mlp.shared_experts.up_proj.scales": "model-00011-of-00044.safetensors",314 "model.layers.16.mlp.shared_experts.up_proj.weight": "model-00011-of-00044.safetensors",315 "model.layers.16.mlp.switch_mlp.down_proj.biases": "model-00011-of-00044.safetensors",316 "model.layers.16.mlp.switch_mlp.down_proj.scales": "model-00011-of-00044.safetensors",317 "model.layers.16.mlp.switch_mlp.down_proj.weight": "model-00011-of-00044.safetensors",318 "model.layers.16.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00044.safetensors",319 "model.layers.16.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00044.safetensors",320 "model.layers.16.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00044.safetensors",321 "model.layers.16.mlp.switch_mlp.up_proj.biases": "model-00011-of-00044.safetensors",322 "model.layers.16.mlp.switch_mlp.up_proj.scales": "model-00011-of-00044.safetensors",323 "model.layers.16.mlp.switch_mlp.up_proj.weight": "model-00011-of-00044.safetensors",324 "model.layers.16.post_attention_layernorm.weight": "model-00011-of-00044.safetensors",325 "model.layers.16.self_attn.kv_a_layernorm.weight": "model-00010-of-00044.safetensors",326 "model.layers.16.self_attn.kv_a_proj_with_mqa.biases": "model-00010-of-00044.safetensors",327 "model.layers.16.self_attn.kv_a_proj_with_mqa.scales": "model-00010-of-00044.safetensors",328 "model.layers.16.self_attn.kv_a_proj_with_mqa.weight": "model-00010-of-00044.safetensors",329 "model.layers.16.self_attn.kv_b_proj.biases": "model-00010-of-00044.safetensors",330 "model.layers.16.self_attn.kv_b_proj.scales": "model-00010-of-00044.safetensors",331 "model.layers.16.self_attn.kv_b_proj.weight": "model-00010-of-00044.safetensors",332 "model.layers.16.self_attn.o_proj.biases": "model-00010-of-00044.safetensors",333 "model.layers.16.self_attn.o_proj.scales": "model-00010-of-00044.safetensors",334 "model.layers.16.self_attn.o_proj.weight": "model-00010-of-00044.safetensors",335 "model.layers.16.self_attn.q_a_layernorm.weight": "model-00010-of-00044.safetensors",336 "model.layers.16.self_attn.q_a_proj.biases": "model-00010-of-00044.safetensors",337 "model.layers.16.self_attn.q_a_proj.scales": "model-00010-of-00044.safetensors",338 "model.layers.16.self_attn.q_a_proj.weight": "model-00010-of-00044.safetensors",339 "model.layers.16.self_attn.q_b_proj.biases": "model-00010-of-00044.safetensors",340 "model.layers.16.self_attn.q_b_proj.scales": "model-00010-of-00044.safetensors",341 "model.layers.16.self_attn.q_b_proj.weight": "model-00010-of-00044.safetensors",342 "model.layers.17.input_layernorm.weight": "model-00012-of-00044.safetensors",343 "model.layers.17.mlp.gate.e_score_correction_bias": "model-00012-of-00044.safetensors",344 "model.layers.17.mlp.gate.weight": "model-00012-of-00044.safetensors",345 "model.layers.17.mlp.shared_experts.down_proj.biases": "model-00012-of-00044.safetensors",346 "model.layers.17.mlp.shared_experts.down_proj.scales": "model-00012-of-00044.safetensors",347 "model.layers.17.mlp.shared_experts.down_proj.weight": "model-00012-of-00044.safetensors",348 "model.layers.17.mlp.shared_experts.gate_proj.biases": "model-00012-of-00044.safetensors",349 "model.layers.17.mlp.shared_experts.gate_proj.scales": "model-00012-of-00044.safetensors",350 "model.layers.17.mlp.shared_experts.gate_proj.weight": "model-00012-of-00044.safetensors",351 "model.layers.17.mlp.shared_experts.up_proj.biases": "model-00012-of-00044.safetensors",352 "model.layers.17.mlp.shared_experts.up_proj.scales": "model-00012-of-00044.safetensors",353 "model.layers.17.mlp.shared_experts.up_proj.weight": "model-00012-of-00044.safetensors",354 "model.layers.17.mlp.switch_mlp.down_proj.biases": "model-00012-of-00044.safetensors",355 "model.layers.17.mlp.switch_mlp.down_proj.scales": "model-00012-of-00044.safetensors",356 "model.layers.17.mlp.switch_mlp.down_proj.weight": "model-00012-of-00044.safetensors",357 "model.layers.17.mlp.switch_mlp.gate_proj.biases": "model-00011-of-00044.safetensors",358 "model.layers.17.mlp.switch_mlp.gate_proj.scales": "model-00011-of-00044.safetensors",359 "model.layers.17.mlp.switch_mlp.gate_proj.weight": "model-00011-of-00044.safetensors",360 "model.layers.17.mlp.switch_mlp.up_proj.biases": "model-00012-of-00044.safetensors",361 "model.layers.17.mlp.switch_mlp.up_proj.scales": "model-00012-of-00044.safetensors",362 "model.layers.17.mlp.switch_mlp.up_proj.weight": "model-00012-of-00044.safetensors",363 "model.layers.17.post_attention_layernorm.weight": "model-00012-of-00044.safetensors",364 "model.layers.17.self_attn.kv_a_layernorm.weight": "model-00011-of-00044.safetensors",365 "model.layers.17.self_attn.kv_a_proj_with_mqa.biases": "model-00011-of-00044.safetensors",366 "model.layers.17.self_attn.kv_a_proj_with_mqa.scales": "model-00011-of-00044.safetensors",367 "model.layers.17.self_attn.kv_a_proj_with_mqa.weight": "model-00011-of-00044.safetensors",368 "model.layers.17.self_attn.kv_b_proj.biases": "model-00011-of-00044.safetensors",369 "model.layers.17.self_attn.kv_b_proj.scales": "model-00011-of-00044.safetensors",370 "model.layers.17.self_attn.kv_b_proj.weight": "model-00011-of-00044.safetensors",371 "model.layers.17.self_attn.o_proj.biases": "model-00011-of-00044.safetensors",372 "model.layers.17.self_attn.o_proj.scales": "model-00011-of-00044.safetensors",373 "model.layers.17.self_attn.o_proj.weight": "model-00011-of-00044.safetensors",374 "model.layers.17.self_attn.q_a_layernorm.weight": "model-00011-of-00044.safetensors",375 "model.layers.17.self_attn.q_a_proj.biases": "model-00011-of-00044.safetensors",376 "model.layers.17.self_attn.q_a_proj.scales": "model-00011-of-00044.safetensors",377 "model.layers.17.self_attn.q_a_proj.weight": "model-00011-of-00044.safetensors",378 "model.layers.17.self_attn.q_b_proj.biases": "model-00011-of-00044.safetensors",379 "model.layers.17.self_attn.q_b_proj.scales": "model-00011-of-00044.safetensors",380 "model.layers.17.self_attn.q_b_proj.weight": "model-00011-of-00044.safetensors",381 "model.layers.18.input_layernorm.weight": "model-00013-of-00044.safetensors",382 "model.layers.18.mlp.gate.e_score_correction_bias": "model-00013-of-00044.safetensors",383 "model.layers.18.mlp.gate.weight": "model-00013-of-00044.safetensors",384 "model.layers.18.mlp.shared_experts.down_proj.biases": "model-00013-of-00044.safetensors",385 "model.layers.18.mlp.shared_experts.down_proj.scales": "model-00013-of-00044.safetensors",386 "model.layers.18.mlp.shared_experts.down_proj.weight": "model-00013-of-00044.safetensors",387 "model.layers.18.mlp.shared_experts.gate_proj.biases": "model-00013-of-00044.safetensors",388 "model.layers.18.mlp.shared_experts.gate_proj.scales": "model-00013-of-00044.safetensors",389 "model.layers.18.mlp.shared_experts.gate_proj.weight": "model-00013-of-00044.safetensors",390 "model.layers.18.mlp.shared_experts.up_proj.biases": "model-00013-of-00044.safetensors",391 "model.layers.18.mlp.shared_experts.up_proj.scales": "model-00013-of-00044.safetensors",392 "model.layers.18.mlp.shared_experts.up_proj.weight": "model-00013-of-00044.safetensors",393 "model.layers.18.mlp.switch_mlp.down_proj.biases": "model-00013-of-00044.safetensors",394 "model.layers.18.mlp.switch_mlp.down_proj.scales": "model-00013-of-00044.safetensors",395 "model.layers.18.mlp.switch_mlp.down_proj.weight": "model-00013-of-00044.safetensors",396 "model.layers.18.mlp.switch_mlp.gate_proj.biases": "model-00012-of-00044.safetensors",397 "model.layers.18.mlp.switch_mlp.gate_proj.scales": "model-00012-of-00044.safetensors",398 "model.layers.18.mlp.switch_mlp.gate_proj.weight": "model-00012-of-00044.safetensors",399 "model.layers.18.mlp.switch_mlp.up_proj.biases": "model-00012-of-00044.safetensors",400 "model.layers.18.mlp.switch_mlp.up_proj.scales": "model-00012-of-00044.safetensors",401 "model.layers.18.mlp.switch_mlp.up_proj.weight": "model-00012-of-00044.safetensors",402 "model.layers.18.post_attention_layernorm.weight": "model-00013-of-00044.safetensors",403 "model.layers.18.self_attn.kv_a_layernorm.weight": "model-00012-of-00044.safetensors",404 "model.layers.18.self_attn.kv_a_proj_with_mqa.biases": "model-00012-of-00044.safetensors",405 "model.layers.18.self_attn.kv_a_proj_with_mqa.scales": "model-00012-of-00044.safetensors",406 "model.layers.18.self_attn.kv_a_proj_with_mqa.weight": "model-00012-of-00044.safetensors",407 "model.layers.18.self_attn.kv_b_proj.biases": "model-00012-of-00044.safetensors",408 "model.layers.18.self_attn.kv_b_proj.scales": "model-00012-of-00044.safetensors",409 "model.layers.18.self_attn.kv_b_proj.weight": "model-00012-of-00044.safetensors",410 "model.layers.18.self_attn.o_proj.biases": "model-00012-of-00044.safetensors",411 "model.layers.18.self_attn.o_proj.scales": "model-00012-of-00044.safetensors",412 "model.layers.18.self_attn.o_proj.weight": "model-00012-of-00044.safetensors",413 "model.layers.18.self_attn.q_a_layernorm.weight": "model-00012-of-00044.safetensors",414 "model.layers.18.self_attn.q_a_proj.biases": "model-00012-of-00044.safetensors",415 "model.layers.18.self_attn.q_a_proj.scales": "model-00012-of-00044.safetensors",416 "model.layers.18.self_attn.q_a_proj.weight": "model-00012-of-00044.safetensors",417 "model.layers.18.self_attn.q_b_proj.biases": "model-00012-of-00044.safetensors",418 "model.layers.18.self_attn.q_b_proj.scales": "model-00012-of-00044.safetensors",419 "model.layers.18.self_attn.q_b_proj.weight": "model-00012-of-00044.safetensors",420 "model.layers.19.input_layernorm.weight": "model-00013-of-00044.safetensors",421 "model.layers.19.mlp.gate.e_score_correction_bias": "model-00013-of-00044.safetensors",422 "model.layers.19.mlp.gate.weight": "model-00013-of-00044.safetensors",423 "model.layers.19.mlp.shared_experts.down_proj.biases": "model-00013-of-00044.safetensors",424 "model.layers.19.mlp.shared_experts.down_proj.scales": "model-00013-of-00044.safetensors",425 "model.layers.19.mlp.shared_experts.down_proj.weight": "model-00013-of-00044.safetensors",426 "model.layers.19.mlp.shared_experts.gate_proj.biases": "model-00013-of-00044.safetensors",427 "model.layers.19.mlp.shared_experts.gate_proj.scales": "model-00013-of-00044.safetensors",428 "model.layers.19.mlp.shared_experts.gate_proj.weight": "model-00013-of-00044.safetensors",429 "model.layers.19.mlp.shared_experts.up_proj.biases": "model-00013-of-00044.safetensors",430 "model.layers.19.mlp.shared_experts.up_proj.scales": "model-00013-of-00044.safetensors",431 "model.layers.19.mlp.shared_experts.up_proj.weight": "model-00013-of-00044.safetensors",432 "model.layers.19.mlp.switch_mlp.down_proj.biases": "model-00013-of-00044.safetensors",433 "model.layers.19.mlp.switch_mlp.down_proj.scales": "model-00013-of-00044.safetensors",434 "model.layers.19.mlp.switch_mlp.down_proj.weight": "model-00013-of-00044.safetensors",435 "model.layers.19.mlp.switch_mlp.gate_proj.biases": "model-00013-of-00044.safetensors",436 "model.layers.19.mlp.switch_mlp.gate_proj.scales": "model-00013-of-00044.safetensors",437 "model.layers.19.mlp.switch_mlp.gate_proj.weight": "model-00013-of-00044.safetensors",438 "model.layers.19.mlp.switch_mlp.up_proj.biases": "model-00013-of-00044.safetensors",439 "model.layers.19.mlp.switch_mlp.up_proj.scales": "model-00013-of-00044.safetensors",440 "model.layers.19.mlp.switch_mlp.up_proj.weight": "model-00013-of-00044.safetensors",441 "model.layers.19.post_attention_layernorm.weight": "model-00013-of-00044.safetensors",442 "model.layers.19.self_attn.kv_a_layernorm.weight": "model-00013-of-00044.safetensors",443 "model.layers.19.self_attn.kv_a_proj_with_mqa.biases": "model-00013-of-00044.safetensors",444 "model.layers.19.self_attn.kv_a_proj_with_mqa.scales": "model-00013-of-00044.safetensors",445 "model.layers.19.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-00044.safetensors",446 "model.layers.19.self_attn.kv_b_proj.biases": "model-00013-of-00044.safetensors",447 "model.layers.19.self_attn.kv_b_proj.scales": "model-00013-of-00044.safetensors",448 "model.layers.19.self_attn.kv_b_proj.weight": "model-00013-of-00044.safetensors",449 "model.layers.19.self_attn.o_proj.biases": "model-00013-of-00044.safetensors",450 "model.layers.19.self_attn.o_proj.scales": "model-00013-of-00044.safetensors",451 "model.layers.19.self_attn.o_proj.weight": "model-00013-of-00044.safetensors",452 "model.layers.19.self_attn.q_a_layernorm.weight": "model-00013-of-00044.safetensors",453 "model.layers.19.self_attn.q_a_proj.biases": "model-00013-of-00044.safetensors",454 "model.layers.19.self_attn.q_a_proj.scales": "model-00013-of-00044.safetensors",455 "model.layers.19.self_attn.q_a_proj.weight": "model-00013-of-00044.safetensors",456 "model.layers.19.self_attn.q_b_proj.biases": "model-00013-of-00044.safetensors",457 "model.layers.19.self_attn.q_b_proj.scales": "model-00013-of-00044.safetensors",458 "model.layers.19.self_attn.q_b_proj.weight": "model-00013-of-00044.safetensors",459 "model.layers.2.input_layernorm.weight": "model-00001-of-00044.safetensors",460 "model.layers.2.mlp.down_proj.biases": "model-00001-of-00044.safetensors",461 "model.layers.2.mlp.down_proj.scales": "model-00001-of-00044.safetensors",462 "model.layers.2.mlp.down_proj.weight": "model-00001-of-00044.safetensors",463 "model.layers.2.mlp.gate_proj.biases": "model-00001-of-00044.safetensors",464 "model.layers.2.mlp.gate_proj.scales": "model-00001-of-00044.safetensors",465 "model.layers.2.mlp.gate_proj.weight": "model-00001-of-00044.safetensors",466 "model.layers.2.mlp.up_proj.biases": "model-00001-of-00044.safetensors",467 "model.layers.2.mlp.up_proj.scales": "model-00001-of-00044.safetensors",468 "model.layers.2.mlp.up_proj.weight": "model-00001-of-00044.safetensors",469 "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00044.safetensors",470 "model.layers.2.self_attn.kv_a_layernorm.weight": "model-00001-of-00044.safetensors",471 "model.layers.2.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00044.safetensors",472 "model.layers.2.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00044.safetensors",473 "model.layers.2.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00044.safetensors",474 "model.layers.2.self_attn.kv_b_proj.biases": "model-00001-of-00044.safetensors",475 "model.layers.2.self_attn.kv_b_proj.scales": "model-00001-of-00044.safetensors",476 "model.layers.2.self_attn.kv_b_proj.weight": "model-00001-of-00044.safetensors",477 "model.layers.2.self_attn.o_proj.biases": "model-00001-of-00044.safetensors",478 "model.layers.2.self_attn.o_proj.scales": "model-00001-of-00044.safetensors",479 "model.layers.2.self_attn.o_proj.weight": "model-00001-of-00044.safetensors",480 "model.layers.2.self_attn.q_a_layernorm.weight": "model-00001-of-00044.safetensors",481 "model.layers.2.self_attn.q_a_proj.biases": "model-00001-of-00044.safetensors",482 "model.layers.2.self_attn.q_a_proj.scales": "model-00001-of-00044.safetensors",483 "model.layers.2.self_attn.q_a_proj.weight": "model-00001-of-00044.safetensors",484 "model.layers.2.self_attn.q_b_proj.biases": "model-00001-of-00044.safetensors",485 "model.layers.2.self_attn.q_b_proj.scales": "model-00001-of-00044.safetensors",486 "model.layers.2.self_attn.q_b_proj.weight": "model-00001-of-00044.safetensors",487 "model.layers.20.input_layernorm.weight": "model-00014-of-00044.safetensors",488 "model.layers.20.mlp.gate.e_score_correction_bias": "model-00014-of-00044.safetensors",489 "model.layers.20.mlp.gate.weight": "model-00014-of-00044.safetensors",490 "model.layers.20.mlp.shared_experts.down_proj.biases": "model-00014-of-00044.safetensors",491 "model.layers.20.mlp.shared_experts.down_proj.scales": "model-00014-of-00044.safetensors",492 "model.layers.20.mlp.shared_experts.down_proj.weight": "model-00014-of-00044.safetensors",493 "model.layers.20.mlp.shared_experts.gate_proj.biases": "model-00014-of-00044.safetensors",494 "model.layers.20.mlp.shared_experts.gate_proj.scales": "model-00014-of-00044.safetensors",495 "model.layers.20.mlp.shared_experts.gate_proj.weight": "model-00014-of-00044.safetensors",496 "model.layers.20.mlp.shared_experts.up_proj.biases": "model-00014-of-00044.safetensors",497 "model.layers.20.mlp.shared_experts.up_proj.scales": "model-00014-of-00044.safetensors",498 "model.layers.20.mlp.shared_experts.up_proj.weight": "model-00014-of-00044.safetensors",499 "model.layers.20.mlp.switch_mlp.down_proj.biases": "model-00014-of-00044.safetensors",500 "model.layers.20.mlp.switch_mlp.down_proj.scales": "model-00014-of-00044.safetensors",501 "model.layers.20.mlp.switch_mlp.down_proj.weight": "model-00014-of-00044.safetensors",502 "model.layers.20.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00044.safetensors",503 "model.layers.20.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00044.safetensors",504 "model.layers.20.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00044.safetensors",505 "model.layers.20.mlp.switch_mlp.up_proj.biases": "model-00014-of-00044.safetensors",506 "model.layers.20.mlp.switch_mlp.up_proj.scales": "model-00014-of-00044.safetensors",507 "model.layers.20.mlp.switch_mlp.up_proj.weight": "model-00014-of-00044.safetensors",508 "model.layers.20.post_attention_layernorm.weight": "model-00014-of-00044.safetensors",509 "model.layers.20.self_attn.kv_a_layernorm.weight": "model-00013-of-00044.safetensors",510 "model.layers.20.self_attn.kv_a_proj_with_mqa.biases": "model-00013-of-00044.safetensors",511 "model.layers.20.self_attn.kv_a_proj_with_mqa.scales": "model-00013-of-00044.safetensors",512 "model.layers.20.self_attn.kv_a_proj_with_mqa.weight": "model-00013-of-00044.safetensors",513 "model.layers.20.self_attn.kv_b_proj.biases": "model-00013-of-00044.safetensors",514 "model.layers.20.self_attn.kv_b_proj.scales": "model-00013-of-00044.safetensors",515 "model.layers.20.self_attn.kv_b_proj.weight": "model-00013-of-00044.safetensors",516 "model.layers.20.self_attn.o_proj.biases": "model-00013-of-00044.safetensors",517 "model.layers.20.self_attn.o_proj.scales": "model-00013-of-00044.safetensors",518 "model.layers.20.self_attn.o_proj.weight": "model-00013-of-00044.safetensors",519 "model.layers.20.self_attn.q_a_layernorm.weight": "model-00013-of-00044.safetensors",520 "model.layers.20.self_attn.q_a_proj.biases": "model-00013-of-00044.safetensors",521 "model.layers.20.self_attn.q_a_proj.scales": "model-00013-of-00044.safetensors",522 "model.layers.20.self_attn.q_a_proj.weight": "model-00013-of-00044.safetensors",523 "model.layers.20.self_attn.q_b_proj.biases": "model-00013-of-00044.safetensors",524 "model.layers.20.self_attn.q_b_proj.scales": "model-00013-of-00044.safetensors",525 "model.layers.20.self_attn.q_b_proj.weight": "model-00013-of-00044.safetensors",526 "model.layers.21.input_layernorm.weight": "model-00015-of-00044.safetensors",527 "model.layers.21.mlp.gate.e_score_correction_bias": "model-00015-of-00044.safetensors",528 "model.layers.21.mlp.gate.weight": "model-00015-of-00044.safetensors",529 "model.layers.21.mlp.shared_experts.down_proj.biases": "model-00015-of-00044.safetensors",530 "model.layers.21.mlp.shared_experts.down_proj.scales": "model-00015-of-00044.safetensors",531 "model.layers.21.mlp.shared_experts.down_proj.weight": "model-00015-of-00044.safetensors",532 "model.layers.21.mlp.shared_experts.gate_proj.biases": "model-00015-of-00044.safetensors",533 "model.layers.21.mlp.shared_experts.gate_proj.scales": "model-00015-of-00044.safetensors",534 "model.layers.21.mlp.shared_experts.gate_proj.weight": "model-00015-of-00044.safetensors",535 "model.layers.21.mlp.shared_experts.up_proj.biases": "model-00015-of-00044.safetensors",536 "model.layers.21.mlp.shared_experts.up_proj.scales": "model-00015-of-00044.safetensors",537 "model.layers.21.mlp.shared_experts.up_proj.weight": "model-00015-of-00044.safetensors",538 "model.layers.21.mlp.switch_mlp.down_proj.biases": "model-00015-of-00044.safetensors",539 "model.layers.21.mlp.switch_mlp.down_proj.scales": "model-00015-of-00044.safetensors",540 "model.layers.21.mlp.switch_mlp.down_proj.weight": "model-00015-of-00044.safetensors",541 "model.layers.21.mlp.switch_mlp.gate_proj.biases": "model-00014-of-00044.safetensors",542 "model.layers.21.mlp.switch_mlp.gate_proj.scales": "model-00014-of-00044.safetensors",543 "model.layers.21.mlp.switch_mlp.gate_proj.weight": "model-00014-of-00044.safetensors",544 "model.layers.21.mlp.switch_mlp.up_proj.biases": "model-00015-of-00044.safetensors",545 "model.layers.21.mlp.switch_mlp.up_proj.scales": "model-00015-of-00044.safetensors",546 "model.layers.21.mlp.switch_mlp.up_proj.weight": "model-00015-of-00044.safetensors",547 "model.layers.21.post_attention_layernorm.weight": "model-00015-of-00044.safetensors",548 "model.layers.21.self_attn.kv_a_layernorm.weight": "model-00014-of-00044.safetensors",549 "model.layers.21.self_attn.kv_a_proj_with_mqa.biases": "model-00014-of-00044.safetensors",550 "model.layers.21.self_attn.kv_a_proj_with_mqa.scales": "model-00014-of-00044.safetensors",551 "model.layers.21.self_attn.kv_a_proj_with_mqa.weight": "model-00014-of-00044.safetensors",552 "model.layers.21.self_attn.kv_b_proj.biases": "model-00014-of-00044.safetensors",553 "model.layers.21.self_attn.kv_b_proj.scales": "model-00014-of-00044.safetensors",554 "model.layers.21.self_attn.kv_b_proj.weight": "model-00014-of-00044.safetensors",555 "model.layers.21.self_attn.o_proj.biases": "model-00014-of-00044.safetensors",556 "model.layers.21.self_attn.o_proj.scales": "model-00014-of-00044.safetensors",557 "model.layers.21.self_attn.o_proj.weight": "model-00014-of-00044.safetensors",558 "model.layers.21.self_attn.q_a_layernorm.weight": "model-00014-of-00044.safetensors",559 "model.layers.21.self_attn.q_a_proj.biases": "model-00014-of-00044.safetensors",560 "model.layers.21.self_attn.q_a_proj.scales": "model-00014-of-00044.safetensors",561 "model.layers.21.self_attn.q_a_proj.weight": "model-00014-of-00044.safetensors",562 "model.layers.21.self_attn.q_b_proj.biases": "model-00014-of-00044.safetensors",563 "model.layers.21.self_attn.q_b_proj.scales": "model-00014-of-00044.safetensors",564 "model.layers.21.self_attn.q_b_proj.weight": "model-00014-of-00044.safetensors",565 "model.layers.22.input_layernorm.weight": "model-00016-of-00044.safetensors",566 "model.layers.22.mlp.gate.e_score_correction_bias": "model-00016-of-00044.safetensors",567 "model.layers.22.mlp.gate.weight": "model-00016-of-00044.safetensors",568 "model.layers.22.mlp.shared_experts.down_proj.biases": "model-00016-of-00044.safetensors",569 "model.layers.22.mlp.shared_experts.down_proj.scales": "model-00016-of-00044.safetensors",570 "model.layers.22.mlp.shared_experts.down_proj.weight": "model-00016-of-00044.safetensors",571 "model.layers.22.mlp.shared_experts.gate_proj.biases": "model-00016-of-00044.safetensors",572 "model.layers.22.mlp.shared_experts.gate_proj.scales": "model-00016-of-00044.safetensors",573 "model.layers.22.mlp.shared_experts.gate_proj.weight": "model-00016-of-00044.safetensors",574 "model.layers.22.mlp.shared_experts.up_proj.biases": "model-00016-of-00044.safetensors",575 "model.layers.22.mlp.shared_experts.up_proj.scales": "model-00016-of-00044.safetensors",576 "model.layers.22.mlp.shared_experts.up_proj.weight": "model-00016-of-00044.safetensors",577 "model.layers.22.mlp.switch_mlp.down_proj.biases": "model-00016-of-00044.safetensors",578 "model.layers.22.mlp.switch_mlp.down_proj.scales": "model-00016-of-00044.safetensors",579 "model.layers.22.mlp.switch_mlp.down_proj.weight": "model-00016-of-00044.safetensors",580 "model.layers.22.mlp.switch_mlp.gate_proj.biases": "model-00015-of-00044.safetensors",581 "model.layers.22.mlp.switch_mlp.gate_proj.scales": "model-00015-of-00044.safetensors",582 "model.layers.22.mlp.switch_mlp.gate_proj.weight": "model-00015-of-00044.safetensors",583 "model.layers.22.mlp.switch_mlp.up_proj.biases": "model-00015-of-00044.safetensors",584 "model.layers.22.mlp.switch_mlp.up_proj.scales": "model-00015-of-00044.safetensors",585 "model.layers.22.mlp.switch_mlp.up_proj.weight": "model-00015-of-00044.safetensors",586 "model.layers.22.post_attention_layernorm.weight": "model-00016-of-00044.safetensors",587 "model.layers.22.self_attn.kv_a_layernorm.weight": "model-00015-of-00044.safetensors",588 "model.layers.22.self_attn.kv_a_proj_with_mqa.biases": "model-00015-of-00044.safetensors",589 "model.layers.22.self_attn.kv_a_proj_with_mqa.scales": "model-00015-of-00044.safetensors",590 "model.layers.22.self_attn.kv_a_proj_with_mqa.weight": "model-00015-of-00044.safetensors",591 "model.layers.22.self_attn.kv_b_proj.biases": "model-00015-of-00044.safetensors",592 "model.layers.22.self_attn.kv_b_proj.scales": "model-00015-of-00044.safetensors",593 "model.layers.22.self_attn.kv_b_proj.weight": "model-00015-of-00044.safetensors",594 "model.layers.22.self_attn.o_proj.biases": "model-00015-of-00044.safetensors",595 "model.layers.22.self_attn.o_proj.scales": "model-00015-of-00044.safetensors",596 "model.layers.22.self_attn.o_proj.weight": "model-00015-of-00044.safetensors",597 "model.layers.22.self_attn.q_a_layernorm.weight": "model-00015-of-00044.safetensors",598 "model.layers.22.self_attn.q_a_proj.biases": "model-00015-of-00044.safetensors",599 "model.layers.22.self_attn.q_a_proj.scales": "model-00015-of-00044.safetensors",600 "model.layers.22.self_attn.q_a_proj.weight": "model-00015-of-00044.safetensors",601 "model.layers.22.self_attn.q_b_proj.biases": "model-00015-of-00044.safetensors",602 "model.layers.22.self_attn.q_b_proj.scales": "model-00015-of-00044.safetensors",603 "model.layers.22.self_attn.q_b_proj.weight": "model-00015-of-00044.safetensors",604 "model.layers.23.input_layernorm.weight": "model-00016-of-00044.safetensors",605 "model.layers.23.mlp.gate.e_score_correction_bias": "model-00016-of-00044.safetensors",606 "model.layers.23.mlp.gate.weight": "model-00016-of-00044.safetensors",607 "model.layers.23.mlp.shared_experts.down_proj.biases": "model-00016-of-00044.safetensors",608 "model.layers.23.mlp.shared_experts.down_proj.scales": "model-00016-of-00044.safetensors",609 "model.layers.23.mlp.shared_experts.down_proj.weight": "model-00016-of-00044.safetensors",610 "model.layers.23.mlp.shared_experts.gate_proj.biases": "model-00016-of-00044.safetensors",611 "model.layers.23.mlp.shared_experts.gate_proj.scales": "model-00016-of-00044.safetensors",612 "model.layers.23.mlp.shared_experts.gate_proj.weight": "model-00016-of-00044.safetensors",613 "model.layers.23.mlp.shared_experts.up_proj.biases": "model-00016-of-00044.safetensors",614 "model.layers.23.mlp.shared_experts.up_proj.scales": "model-00016-of-00044.safetensors",615 "model.layers.23.mlp.shared_experts.up_proj.weight": "model-00016-of-00044.safetensors",616 "model.layers.23.mlp.switch_mlp.down_proj.biases": "model-00016-of-00044.safetensors",617 "model.layers.23.mlp.switch_mlp.down_proj.scales": "model-00016-of-00044.safetensors",618 "model.layers.23.mlp.switch_mlp.down_proj.weight": "model-00016-of-00044.safetensors",619 "model.layers.23.mlp.switch_mlp.gate_proj.biases": "model-00016-of-00044.safetensors",620 "model.layers.23.mlp.switch_mlp.gate_proj.scales": "model-00016-of-00044.safetensors",621 "model.layers.23.mlp.switch_mlp.gate_proj.weight": "model-00016-of-00044.safetensors",622 "model.layers.23.mlp.switch_mlp.up_proj.biases": "model-00016-of-00044.safetensors",623 "model.layers.23.mlp.switch_mlp.up_proj.scales": "model-00016-of-00044.safetensors",624 "model.layers.23.mlp.switch_mlp.up_proj.weight": "model-00016-of-00044.safetensors",625 "model.layers.23.post_attention_layernorm.weight": "model-00016-of-00044.safetensors",626 "model.layers.23.self_attn.kv_a_layernorm.weight": "model-00016-of-00044.safetensors",627 "model.layers.23.self_attn.kv_a_proj_with_mqa.biases": "model-00016-of-00044.safetensors",628 "model.layers.23.self_attn.kv_a_proj_with_mqa.scales": "model-00016-of-00044.safetensors",629 "model.layers.23.self_attn.kv_a_proj_with_mqa.weight": "model-00016-of-00044.safetensors",630 "model.layers.23.self_attn.kv_b_proj.biases": "model-00016-of-00044.safetensors",631 "model.layers.23.self_attn.kv_b_proj.scales": "model-00016-of-00044.safetensors",632 "model.layers.23.self_attn.kv_b_proj.weight": "model-00016-of-00044.safetensors",633 "model.layers.23.self_attn.o_proj.biases": "model-00016-of-00044.safetensors",634 "model.layers.23.self_attn.o_proj.scales": "model-00016-of-00044.safetensors",635 "model.layers.23.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",636 "model.layers.23.self_attn.q_a_layernorm.weight": "model-00016-of-00044.safetensors",637 "model.layers.23.self_attn.q_a_proj.biases": "model-00016-of-00044.safetensors",638 "model.layers.23.self_attn.q_a_proj.scales": "model-00016-of-00044.safetensors",639 "model.layers.23.self_attn.q_a_proj.weight": "model-00016-of-00044.safetensors",640 "model.layers.23.self_attn.q_b_proj.biases": "model-00016-of-00044.safetensors",641 "model.layers.23.self_attn.q_b_proj.scales": "model-00016-of-00044.safetensors",642 "model.layers.23.self_attn.q_b_proj.weight": "model-00016-of-00044.safetensors",643 "model.layers.24.input_layernorm.weight": "model-00017-of-00044.safetensors",644 "model.layers.24.mlp.gate.e_score_correction_bias": "model-00017-of-00044.safetensors",645 "model.layers.24.mlp.gate.weight": "model-00017-of-00044.safetensors",646 "model.layers.24.mlp.shared_experts.down_proj.biases": "model-00017-of-00044.safetensors",647 "model.layers.24.mlp.shared_experts.down_proj.scales": "model-00017-of-00044.safetensors",648 "model.layers.24.mlp.shared_experts.down_proj.weight": "model-00017-of-00044.safetensors",649 "model.layers.24.mlp.shared_experts.gate_proj.biases": "model-00017-of-00044.safetensors",650 "model.layers.24.mlp.shared_experts.gate_proj.scales": "model-00017-of-00044.safetensors",651 "model.layers.24.mlp.shared_experts.gate_proj.weight": "model-00017-of-00044.safetensors",652 "model.layers.24.mlp.shared_experts.up_proj.biases": "model-00017-of-00044.safetensors",653 "model.layers.24.mlp.shared_experts.up_proj.scales": "model-00017-of-00044.safetensors",654 "model.layers.24.mlp.shared_experts.up_proj.weight": "model-00017-of-00044.safetensors",655 "model.layers.24.mlp.switch_mlp.down_proj.biases": "model-00017-of-00044.safetensors",656 "model.layers.24.mlp.switch_mlp.down_proj.scales": "model-00017-of-00044.safetensors",657 "model.layers.24.mlp.switch_mlp.down_proj.weight": "model-00017-of-00044.safetensors",658 "model.layers.24.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00044.safetensors",659 "model.layers.24.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00044.safetensors",660 "model.layers.24.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00044.safetensors",661 "model.layers.24.mlp.switch_mlp.up_proj.biases": "model-00017-of-00044.safetensors",662 "model.layers.24.mlp.switch_mlp.up_proj.scales": "model-00017-of-00044.safetensors",663 "model.layers.24.mlp.switch_mlp.up_proj.weight": "model-00017-of-00044.safetensors",664 "model.layers.24.post_attention_layernorm.weight": "model-00017-of-00044.safetensors",665 "model.layers.24.self_attn.kv_a_layernorm.weight": "model-00016-of-00044.safetensors",666 "model.layers.24.self_attn.kv_a_proj_with_mqa.biases": "model-00016-of-00044.safetensors",667 "model.layers.24.self_attn.kv_a_proj_with_mqa.scales": "model-00016-of-00044.safetensors",668 "model.layers.24.self_attn.kv_a_proj_with_mqa.weight": "model-00016-of-00044.safetensors",669 "model.layers.24.self_attn.kv_b_proj.biases": "model-00016-of-00044.safetensors",670 "model.layers.24.self_attn.kv_b_proj.scales": "model-00016-of-00044.safetensors",671 "model.layers.24.self_attn.kv_b_proj.weight": "model-00016-of-00044.safetensors",672 "model.layers.24.self_attn.o_proj.biases": "model-00016-of-00044.safetensors",673 "model.layers.24.self_attn.o_proj.scales": "model-00016-of-00044.safetensors",674 "model.layers.24.self_attn.o_proj.weight": "model-00016-of-00044.safetensors",675 "model.layers.24.self_attn.q_a_layernorm.weight": "model-00016-of-00044.safetensors",676 "model.layers.24.self_attn.q_a_proj.biases": "model-00016-of-00044.safetensors",677 "model.layers.24.self_attn.q_a_proj.scales": "model-00016-of-00044.safetensors",678 "model.layers.24.self_attn.q_a_proj.weight": "model-00016-of-00044.safetensors",679 "model.layers.24.self_attn.q_b_proj.biases": "model-00016-of-00044.safetensors",680 "model.layers.24.self_attn.q_b_proj.scales": "model-00016-of-00044.safetensors",681 "model.layers.24.self_attn.q_b_proj.weight": "model-00016-of-00044.safetensors",682 "model.layers.25.input_layernorm.weight": "model-00018-of-00044.safetensors",683 "model.layers.25.mlp.gate.e_score_correction_bias": "model-00018-of-00044.safetensors",684 "model.layers.25.mlp.gate.weight": "model-00018-of-00044.safetensors",685 "model.layers.25.mlp.shared_experts.down_proj.biases": "model-00018-of-00044.safetensors",686 "model.layers.25.mlp.shared_experts.down_proj.scales": "model-00018-of-00044.safetensors",687 "model.layers.25.mlp.shared_experts.down_proj.weight": "model-00018-of-00044.safetensors",688 "model.layers.25.mlp.shared_experts.gate_proj.biases": "model-00018-of-00044.safetensors",689 "model.layers.25.mlp.shared_experts.gate_proj.scales": "model-00018-of-00044.safetensors",690 "model.layers.25.mlp.shared_experts.gate_proj.weight": "model-00018-of-00044.safetensors",691 "model.layers.25.mlp.shared_experts.up_proj.biases": "model-00018-of-00044.safetensors",692 "model.layers.25.mlp.shared_experts.up_proj.scales": "model-00018-of-00044.safetensors",693 "model.layers.25.mlp.shared_experts.up_proj.weight": "model-00018-of-00044.safetensors",694 "model.layers.25.mlp.switch_mlp.down_proj.biases": "model-00018-of-00044.safetensors",695 "model.layers.25.mlp.switch_mlp.down_proj.scales": "model-00018-of-00044.safetensors",696 "model.layers.25.mlp.switch_mlp.down_proj.weight": "model-00018-of-00044.safetensors",697 "model.layers.25.mlp.switch_mlp.gate_proj.biases": "model-00017-of-00044.safetensors",698 "model.layers.25.mlp.switch_mlp.gate_proj.scales": "model-00017-of-00044.safetensors",699 "model.layers.25.mlp.switch_mlp.gate_proj.weight": "model-00017-of-00044.safetensors",700 "model.layers.25.mlp.switch_mlp.up_proj.biases": "model-00018-of-00044.safetensors",701 "model.layers.25.mlp.switch_mlp.up_proj.scales": "model-00018-of-00044.safetensors",702 "model.layers.25.mlp.switch_mlp.up_proj.weight": "model-00018-of-00044.safetensors",703 "model.layers.25.post_attention_layernorm.weight": "model-00018-of-00044.safetensors",704 "model.layers.25.self_attn.kv_a_layernorm.weight": "model-00017-of-00044.safetensors",705 "model.layers.25.self_attn.kv_a_proj_with_mqa.biases": "model-00017-of-00044.safetensors",706 "model.layers.25.self_attn.kv_a_proj_with_mqa.scales": "model-00017-of-00044.safetensors",707 "model.layers.25.self_attn.kv_a_proj_with_mqa.weight": "model-00017-of-00044.safetensors",708 "model.layers.25.self_attn.kv_b_proj.biases": "model-00017-of-00044.safetensors",709 "model.layers.25.self_attn.kv_b_proj.scales": "model-00017-of-00044.safetensors",710 "model.layers.25.self_attn.kv_b_proj.weight": "model-00017-of-00044.safetensors",711 "model.layers.25.self_attn.o_proj.biases": "model-00017-of-00044.safetensors",712 "model.layers.25.self_attn.o_proj.scales": "model-00017-of-00044.safetensors",713 "model.layers.25.self_attn.o_proj.weight": "model-00017-of-00044.safetensors",714 "model.layers.25.self_attn.q_a_layernorm.weight": "model-00017-of-00044.safetensors",715 "model.layers.25.self_attn.q_a_proj.biases": "model-00017-of-00044.safetensors",716 "model.layers.25.self_attn.q_a_proj.scales": "model-00017-of-00044.safetensors",717 "model.layers.25.self_attn.q_a_proj.weight": "model-00017-of-00044.safetensors",718 "model.layers.25.self_attn.q_b_proj.biases": "model-00017-of-00044.safetensors",719 "model.layers.25.self_attn.q_b_proj.scales": "model-00017-of-00044.safetensors",720 "model.layers.25.self_attn.q_b_proj.weight": "model-00017-of-00044.safetensors",721 "model.layers.26.input_layernorm.weight": "model-00019-of-00044.safetensors",722 "model.layers.26.mlp.gate.e_score_correction_bias": "model-00019-of-00044.safetensors",723 "model.layers.26.mlp.gate.weight": "model-00019-of-00044.safetensors",724 "model.layers.26.mlp.shared_experts.down_proj.biases": "model-00019-of-00044.safetensors",725 "model.layers.26.mlp.shared_experts.down_proj.scales": "model-00019-of-00044.safetensors",726 "model.layers.26.mlp.shared_experts.down_proj.weight": "model-00019-of-00044.safetensors",727 "model.layers.26.mlp.shared_experts.gate_proj.biases": "model-00019-of-00044.safetensors",728 "model.layers.26.mlp.shared_experts.gate_proj.scales": "model-00019-of-00044.safetensors",729 "model.layers.26.mlp.shared_experts.gate_proj.weight": "model-00019-of-00044.safetensors",730 "model.layers.26.mlp.shared_experts.up_proj.biases": "model-00019-of-00044.safetensors",731 "model.layers.26.mlp.shared_experts.up_proj.scales": "model-00019-of-00044.safetensors",732 "model.layers.26.mlp.shared_experts.up_proj.weight": "model-00019-of-00044.safetensors",733 "model.layers.26.mlp.switch_mlp.down_proj.biases": "model-00019-of-00044.safetensors",734 "model.layers.26.mlp.switch_mlp.down_proj.scales": "model-00019-of-00044.safetensors",735 "model.layers.26.mlp.switch_mlp.down_proj.weight": "model-00019-of-00044.safetensors",736 "model.layers.26.mlp.switch_mlp.gate_proj.biases": "model-00018-of-00044.safetensors",737 "model.layers.26.mlp.switch_mlp.gate_proj.scales": "model-00018-of-00044.safetensors",738 "model.layers.26.mlp.switch_mlp.gate_proj.weight": "model-00018-of-00044.safetensors",739 "model.layers.26.mlp.switch_mlp.up_proj.biases": "model-00018-of-00044.safetensors",740 "model.layers.26.mlp.switch_mlp.up_proj.scales": "model-00018-of-00044.safetensors",741 "model.layers.26.mlp.switch_mlp.up_proj.weight": "model-00018-of-00044.safetensors",742 "model.layers.26.post_attention_layernorm.weight": "model-00019-of-00044.safetensors",743 "model.layers.26.self_attn.kv_a_layernorm.weight": "model-00018-of-00044.safetensors",744 "model.layers.26.self_attn.kv_a_proj_with_mqa.biases": "model-00018-of-00044.safetensors",745 "model.layers.26.self_attn.kv_a_proj_with_mqa.scales": "model-00018-of-00044.safetensors",746 "model.layers.26.self_attn.kv_a_proj_with_mqa.weight": "model-00018-of-00044.safetensors",747 "model.layers.26.self_attn.kv_b_proj.biases": "model-00018-of-00044.safetensors",748 "model.layers.26.self_attn.kv_b_proj.scales": "model-00018-of-00044.safetensors",749 "model.layers.26.self_attn.kv_b_proj.weight": "model-00018-of-00044.safetensors",750 "model.layers.26.self_attn.o_proj.biases": "model-00018-of-00044.safetensors",751 "model.layers.26.self_attn.o_proj.scales": "model-00018-of-00044.safetensors",752 "model.layers.26.self_attn.o_proj.weight": "model-00018-of-00044.safetensors",753 "model.layers.26.self_attn.q_a_layernorm.weight": "model-00018-of-00044.safetensors",754 "model.layers.26.self_attn.q_a_proj.biases": "model-00018-of-00044.safetensors",755 "model.layers.26.self_attn.q_a_proj.scales": "model-00018-of-00044.safetensors",756 "model.layers.26.self_attn.q_a_proj.weight": "model-00018-of-00044.safetensors",757 "model.layers.26.self_attn.q_b_proj.biases": "model-00018-of-00044.safetensors",758 "model.layers.26.self_attn.q_b_proj.scales": "model-00018-of-00044.safetensors",759 "model.layers.26.self_attn.q_b_proj.weight": "model-00018-of-00044.safetensors",760 "model.layers.27.input_layernorm.weight": "model-00019-of-00044.safetensors",761 "model.layers.27.mlp.gate.e_score_correction_bias": "model-00019-of-00044.safetensors",762 "model.layers.27.mlp.gate.weight": "model-00019-of-00044.safetensors",763 "model.layers.27.mlp.shared_experts.down_proj.biases": "model-00019-of-00044.safetensors",764 "model.layers.27.mlp.shared_experts.down_proj.scales": "model-00019-of-00044.safetensors",765 "model.layers.27.mlp.shared_experts.down_proj.weight": "model-00019-of-00044.safetensors",766 "model.layers.27.mlp.shared_experts.gate_proj.biases": "model-00019-of-00044.safetensors",767 "model.layers.27.mlp.shared_experts.gate_proj.scales": "model-00019-of-00044.safetensors",768 "model.layers.27.mlp.shared_experts.gate_proj.weight": "model-00019-of-00044.safetensors",769 "model.layers.27.mlp.shared_experts.up_proj.biases": "model-00019-of-00044.safetensors",770 "model.layers.27.mlp.shared_experts.up_proj.scales": "model-00019-of-00044.safetensors",771 "model.layers.27.mlp.shared_experts.up_proj.weight": "model-00019-of-00044.safetensors",772 "model.layers.27.mlp.switch_mlp.down_proj.biases": "model-00019-of-00044.safetensors",773 "model.layers.27.mlp.switch_mlp.down_proj.scales": "model-00019-of-00044.safetensors",774 "model.layers.27.mlp.switch_mlp.down_proj.weight": "model-00019-of-00044.safetensors",775 "model.layers.27.mlp.switch_mlp.gate_proj.biases": "model-00019-of-00044.safetensors",776 "model.layers.27.mlp.switch_mlp.gate_proj.scales": "model-00019-of-00044.safetensors",777 "model.layers.27.mlp.switch_mlp.gate_proj.weight": "model-00019-of-00044.safetensors",778 "model.layers.27.mlp.switch_mlp.up_proj.biases": "model-00019-of-00044.safetensors",779 "model.layers.27.mlp.switch_mlp.up_proj.scales": "model-00019-of-00044.safetensors",780 "model.layers.27.mlp.switch_mlp.up_proj.weight": "model-00019-of-00044.safetensors",781 "model.layers.27.post_attention_layernorm.weight": "model-00019-of-00044.safetensors",782 "model.layers.27.self_attn.kv_a_layernorm.weight": "model-00019-of-00044.safetensors",783 "model.layers.27.self_attn.kv_a_proj_with_mqa.biases": "model-00019-of-00044.safetensors",784 "model.layers.27.self_attn.kv_a_proj_with_mqa.scales": "model-00019-of-00044.safetensors",785 "model.layers.27.self_attn.kv_a_proj_with_mqa.weight": "model-00019-of-00044.safetensors",786 "model.layers.27.self_attn.kv_b_proj.biases": "model-00019-of-00044.safetensors",787 "model.layers.27.self_attn.kv_b_proj.scales": "model-00019-of-00044.safetensors",788 "model.layers.27.self_attn.kv_b_proj.weight": "model-00019-of-00044.safetensors",789 "model.layers.27.self_attn.o_proj.biases": "model-00019-of-00044.safetensors",790 "model.layers.27.self_attn.o_proj.scales": "model-00019-of-00044.safetensors",791 "model.layers.27.self_attn.o_proj.weight": "model-00019-of-00044.safetensors",792 "model.layers.27.self_attn.q_a_layernorm.weight": "model-00019-of-00044.safetensors",793 "model.layers.27.self_attn.q_a_proj.biases": "model-00019-of-00044.safetensors",794 "model.layers.27.self_attn.q_a_proj.scales": "model-00019-of-00044.safetensors",795 "model.layers.27.self_attn.q_a_proj.weight": "model-00019-of-00044.safetensors",796 "model.layers.27.self_attn.q_b_proj.biases": "model-00019-of-00044.safetensors",797 "model.layers.27.self_attn.q_b_proj.scales": "model-00019-of-00044.safetensors",798 "model.layers.27.self_attn.q_b_proj.weight": "model-00019-of-00044.safetensors",799 "model.layers.28.input_layernorm.weight": "model-00020-of-00044.safetensors",800 "model.layers.28.mlp.gate.e_score_correction_bias": "model-00020-of-00044.safetensors",801 "model.layers.28.mlp.gate.weight": "model-00020-of-00044.safetensors",802 "model.layers.28.mlp.shared_experts.down_proj.biases": "model-00020-of-00044.safetensors",803 "model.layers.28.mlp.shared_experts.down_proj.scales": "model-00020-of-00044.safetensors",804 "model.layers.28.mlp.shared_experts.down_proj.weight": "model-00020-of-00044.safetensors",805 "model.layers.28.mlp.shared_experts.gate_proj.biases": "model-00020-of-00044.safetensors",806 "model.layers.28.mlp.shared_experts.gate_proj.scales": "model-00020-of-00044.safetensors",807 "model.layers.28.mlp.shared_experts.gate_proj.weight": "model-00020-of-00044.safetensors",808 "model.layers.28.mlp.shared_experts.up_proj.biases": "model-00020-of-00044.safetensors",809 "model.layers.28.mlp.shared_experts.up_proj.scales": "model-00020-of-00044.safetensors",810 "model.layers.28.mlp.shared_experts.up_proj.weight": "model-00020-of-00044.safetensors",811 "model.layers.28.mlp.switch_mlp.down_proj.biases": "model-00020-of-00044.safetensors",812 "model.layers.28.mlp.switch_mlp.down_proj.scales": "model-00020-of-00044.safetensors",813 "model.layers.28.mlp.switch_mlp.down_proj.weight": "model-00020-of-00044.safetensors",814 "model.layers.28.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00044.safetensors",815 "model.layers.28.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00044.safetensors",816 "model.layers.28.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00044.safetensors",817 "model.layers.28.mlp.switch_mlp.up_proj.biases": "model-00020-of-00044.safetensors",818 "model.layers.28.mlp.switch_mlp.up_proj.scales": "model-00020-of-00044.safetensors",819 "model.layers.28.mlp.switch_mlp.up_proj.weight": "model-00020-of-00044.safetensors",820 "model.layers.28.post_attention_layernorm.weight": "model-00020-of-00044.safetensors",821 "model.layers.28.self_attn.kv_a_layernorm.weight": "model-00019-of-00044.safetensors",822 "model.layers.28.self_attn.kv_a_proj_with_mqa.biases": "model-00019-of-00044.safetensors",823 "model.layers.28.self_attn.kv_a_proj_with_mqa.scales": "model-00019-of-00044.safetensors",824 "model.layers.28.self_attn.kv_a_proj_with_mqa.weight": "model-00019-of-00044.safetensors",825 "model.layers.28.self_attn.kv_b_proj.biases": "model-00019-of-00044.safetensors",826 "model.layers.28.self_attn.kv_b_proj.scales": "model-00019-of-00044.safetensors",827 "model.layers.28.self_attn.kv_b_proj.weight": "model-00019-of-00044.safetensors",828 "model.layers.28.self_attn.o_proj.biases": "model-00019-of-00044.safetensors",829 "model.layers.28.self_attn.o_proj.scales": "model-00019-of-00044.safetensors",830 "model.layers.28.self_attn.o_proj.weight": "model-00019-of-00044.safetensors",831 "model.layers.28.self_attn.q_a_layernorm.weight": "model-00019-of-00044.safetensors",832 "model.layers.28.self_attn.q_a_proj.biases": "model-00019-of-00044.safetensors",833 "model.layers.28.self_attn.q_a_proj.scales": "model-00019-of-00044.safetensors",834 "model.layers.28.self_attn.q_a_proj.weight": "model-00019-of-00044.safetensors",835 "model.layers.28.self_attn.q_b_proj.biases": "model-00019-of-00044.safetensors",836 "model.layers.28.self_attn.q_b_proj.scales": "model-00019-of-00044.safetensors",837 "model.layers.28.self_attn.q_b_proj.weight": "model-00019-of-00044.safetensors",838 "model.layers.29.input_layernorm.weight": "model-00021-of-00044.safetensors",839 "model.layers.29.mlp.gate.e_score_correction_bias": "model-00021-of-00044.safetensors",840 "model.layers.29.mlp.gate.weight": "model-00021-of-00044.safetensors",841 "model.layers.29.mlp.shared_experts.down_proj.biases": "model-00021-of-00044.safetensors",842 "model.layers.29.mlp.shared_experts.down_proj.scales": "model-00021-of-00044.safetensors",843 "model.layers.29.mlp.shared_experts.down_proj.weight": "model-00021-of-00044.safetensors",844 "model.layers.29.mlp.shared_experts.gate_proj.biases": "model-00021-of-00044.safetensors",845 "model.layers.29.mlp.shared_experts.gate_proj.scales": "model-00021-of-00044.safetensors",846 "model.layers.29.mlp.shared_experts.gate_proj.weight": "model-00021-of-00044.safetensors",847 "model.layers.29.mlp.shared_experts.up_proj.biases": "model-00021-of-00044.safetensors",848 "model.layers.29.mlp.shared_experts.up_proj.scales": "model-00021-of-00044.safetensors",849 "model.layers.29.mlp.shared_experts.up_proj.weight": "model-00021-of-00044.safetensors",850 "model.layers.29.mlp.switch_mlp.down_proj.biases": "model-00021-of-00044.safetensors",851 "model.layers.29.mlp.switch_mlp.down_proj.scales": "model-00021-of-00044.safetensors",852 "model.layers.29.mlp.switch_mlp.down_proj.weight": "model-00021-of-00044.safetensors",853 "model.layers.29.mlp.switch_mlp.gate_proj.biases": "model-00020-of-00044.safetensors",854 "model.layers.29.mlp.switch_mlp.gate_proj.scales": "model-00020-of-00044.safetensors",855 "model.layers.29.mlp.switch_mlp.gate_proj.weight": "model-00020-of-00044.safetensors",856 "model.layers.29.mlp.switch_mlp.up_proj.biases": "model-00021-of-00044.safetensors",857 "model.layers.29.mlp.switch_mlp.up_proj.scales": "model-00021-of-00044.safetensors",858 "model.layers.29.mlp.switch_mlp.up_proj.weight": "model-00021-of-00044.safetensors",859 "model.layers.29.post_attention_layernorm.weight": "model-00021-of-00044.safetensors",860 "model.layers.29.self_attn.kv_a_layernorm.weight": "model-00020-of-00044.safetensors",861 "model.layers.29.self_attn.kv_a_proj_with_mqa.biases": "model-00020-of-00044.safetensors",862 "model.layers.29.self_attn.kv_a_proj_with_mqa.scales": "model-00020-of-00044.safetensors",863 "model.layers.29.self_attn.kv_a_proj_with_mqa.weight": "model-00020-of-00044.safetensors",864 "model.layers.29.self_attn.kv_b_proj.biases": "model-00020-of-00044.safetensors",865 "model.layers.29.self_attn.kv_b_proj.scales": "model-00020-of-00044.safetensors",866 "model.layers.29.self_attn.kv_b_proj.weight": "model-00020-of-00044.safetensors",867 "model.layers.29.self_attn.o_proj.biases": "model-00020-of-00044.safetensors",868 "model.layers.29.self_attn.o_proj.scales": "model-00020-of-00044.safetensors",869 "model.layers.29.self_attn.o_proj.weight": "model-00020-of-00044.safetensors",870 "model.layers.29.self_attn.q_a_layernorm.weight": "model-00020-of-00044.safetensors",871 "model.layers.29.self_attn.q_a_proj.biases": "model-00020-of-00044.safetensors",872 "model.layers.29.self_attn.q_a_proj.scales": "model-00020-of-00044.safetensors",873 "model.layers.29.self_attn.q_a_proj.weight": "model-00020-of-00044.safetensors",874 "model.layers.29.self_attn.q_b_proj.biases": "model-00020-of-00044.safetensors",875 "model.layers.29.self_attn.q_b_proj.scales": "model-00020-of-00044.safetensors",876 "model.layers.29.self_attn.q_b_proj.weight": "model-00020-of-00044.safetensors",877 "model.layers.3.input_layernorm.weight": "model-00001-of-00044.safetensors",878 "model.layers.3.mlp.gate.e_score_correction_bias": "model-00001-of-00044.safetensors",879 "model.layers.3.mlp.gate.weight": "model-00001-of-00044.safetensors",880 "model.layers.3.mlp.shared_experts.down_proj.biases": "model-00001-of-00044.safetensors",881 "model.layers.3.mlp.shared_experts.down_proj.scales": "model-00001-of-00044.safetensors",882 "model.layers.3.mlp.shared_experts.down_proj.weight": "model-00001-of-00044.safetensors",883 "model.layers.3.mlp.shared_experts.gate_proj.biases": "model-00001-of-00044.safetensors",884 "model.layers.3.mlp.shared_experts.gate_proj.scales": "model-00001-of-00044.safetensors",885 "model.layers.3.mlp.shared_experts.gate_proj.weight": "model-00001-of-00044.safetensors",886 "model.layers.3.mlp.shared_experts.up_proj.biases": "model-00001-of-00044.safetensors",887 "model.layers.3.mlp.shared_experts.up_proj.scales": "model-00001-of-00044.safetensors",888 "model.layers.3.mlp.shared_experts.up_proj.weight": "model-00001-of-00044.safetensors",889 "model.layers.3.mlp.switch_mlp.down_proj.biases": "model-00001-of-00044.safetensors",890 "model.layers.3.mlp.switch_mlp.down_proj.scales": "model-00001-of-00044.safetensors",891 "model.layers.3.mlp.switch_mlp.down_proj.weight": "model-00001-of-00044.safetensors",892 "model.layers.3.mlp.switch_mlp.gate_proj.biases": "model-00001-of-00044.safetensors",893 "model.layers.3.mlp.switch_mlp.gate_proj.scales": "model-00001-of-00044.safetensors",894 "model.layers.3.mlp.switch_mlp.gate_proj.weight": "model-00001-of-00044.safetensors",895 "model.layers.3.mlp.switch_mlp.up_proj.biases": "model-00001-of-00044.safetensors",896 "model.layers.3.mlp.switch_mlp.up_proj.scales": "model-00001-of-00044.safetensors",897 "model.layers.3.mlp.switch_mlp.up_proj.weight": "model-00001-of-00044.safetensors",898 "model.layers.3.post_attention_layernorm.weight": "model-00001-of-00044.safetensors",899 "model.layers.3.self_attn.kv_a_layernorm.weight": "model-00001-of-00044.safetensors",900 "model.layers.3.self_attn.kv_a_proj_with_mqa.biases": "model-00001-of-00044.safetensors",901 "model.layers.3.self_attn.kv_a_proj_with_mqa.scales": "model-00001-of-00044.safetensors",902 "model.layers.3.self_attn.kv_a_proj_with_mqa.weight": "model-00001-of-00044.safetensors",903 "model.layers.3.self_attn.kv_b_proj.biases": "model-00001-of-00044.safetensors",904 "model.layers.3.self_attn.kv_b_proj.scales": "model-00001-of-00044.safetensors",905 "model.layers.3.self_attn.kv_b_proj.weight": "model-00001-of-00044.safetensors",906 "model.layers.3.self_attn.o_proj.biases": "model-00001-of-00044.safetensors",907 "model.layers.3.self_attn.o_proj.scales": "model-00001-of-00044.safetensors",908 "model.layers.3.self_attn.o_proj.weight": "model-00001-of-00044.safetensors",909 "model.layers.3.self_attn.q_a_layernorm.weight": "model-00001-of-00044.safetensors",910 "model.layers.3.self_attn.q_a_proj.biases": "model-00001-of-00044.safetensors",911 "model.layers.3.self_attn.q_a_proj.scales": "model-00001-of-00044.safetensors",912 "model.layers.3.self_attn.q_a_proj.weight": "model-00001-of-00044.safetensors",913 "model.layers.3.self_attn.q_b_proj.biases": "model-00001-of-00044.safetensors",914 "model.layers.3.self_attn.q_b_proj.scales": "model-00001-of-00044.safetensors",915 "model.layers.3.self_attn.q_b_proj.weight": "model-00001-of-00044.safetensors",916 "model.layers.30.input_layernorm.weight": "model-00022-of-00044.safetensors",917 "model.layers.30.mlp.gate.e_score_correction_bias": "model-00022-of-00044.safetensors",918 "model.layers.30.mlp.gate.weight": "model-00022-of-00044.safetensors",919 "model.layers.30.mlp.shared_experts.down_proj.biases": "model-00022-of-00044.safetensors",920 "model.layers.30.mlp.shared_experts.down_proj.scales": "model-00022-of-00044.safetensors",921 "model.layers.30.mlp.shared_experts.down_proj.weight": "model-00022-of-00044.safetensors",922 "model.layers.30.mlp.shared_experts.gate_proj.biases": "model-00022-of-00044.safetensors",923 "model.layers.30.mlp.shared_experts.gate_proj.scales": "model-00022-of-00044.safetensors",924 "model.layers.30.mlp.shared_experts.gate_proj.weight": "model-00022-of-00044.safetensors",925 "model.layers.30.mlp.shared_experts.up_proj.biases": "model-00022-of-00044.safetensors",926 "model.layers.30.mlp.shared_experts.up_proj.scales": "model-00022-of-00044.safetensors",927 "model.layers.30.mlp.shared_experts.up_proj.weight": "model-00022-of-00044.safetensors",928 "model.layers.30.mlp.switch_mlp.down_proj.biases": "model-00022-of-00044.safetensors",929 "model.layers.30.mlp.switch_mlp.down_proj.scales": "model-00022-of-00044.safetensors",930 "model.layers.30.mlp.switch_mlp.down_proj.weight": "model-00022-of-00044.safetensors",931 "model.layers.30.mlp.switch_mlp.gate_proj.biases": "model-00021-of-00044.safetensors",932 "model.layers.30.mlp.switch_mlp.gate_proj.scales": "model-00021-of-00044.safetensors",933 "model.layers.30.mlp.switch_mlp.gate_proj.weight": "model-00021-of-00044.safetensors",934 "model.layers.30.mlp.switch_mlp.up_proj.biases": "model-00021-of-00044.safetensors",935 "model.layers.30.mlp.switch_mlp.up_proj.scales": "model-00021-of-00044.safetensors",936 "model.layers.30.mlp.switch_mlp.up_proj.weight": "model-00021-of-00044.safetensors",937 "model.layers.30.post_attention_layernorm.weight": "model-00022-of-00044.safetensors",938 "model.layers.30.self_attn.kv_a_layernorm.weight": "model-00021-of-00044.safetensors",939 "model.layers.30.self_attn.kv_a_proj_with_mqa.biases": "model-00021-of-00044.safetensors",940 "model.layers.30.self_attn.kv_a_proj_with_mqa.scales": "model-00021-of-00044.safetensors",941 "model.layers.30.self_attn.kv_a_proj_with_mqa.weight": "model-00021-of-00044.safetensors",942 "model.layers.30.self_attn.kv_b_proj.biases": "model-00021-of-00044.safetensors",943 "model.layers.30.self_attn.kv_b_proj.scales": "model-00021-of-00044.safetensors",944 "model.layers.30.self_attn.kv_b_proj.weight": "model-00021-of-00044.safetensors",945 "model.layers.30.self_attn.o_proj.biases": "model-00021-of-00044.safetensors",946 "model.layers.30.self_attn.o_proj.scales": "model-00021-of-00044.safetensors",947 "model.layers.30.self_attn.o_proj.weight": "model-00021-of-00044.safetensors",948 "model.layers.30.self_attn.q_a_layernorm.weight": "model-00021-of-00044.safetensors",949 "model.layers.30.self_attn.q_a_proj.biases": "model-00021-of-00044.safetensors",950 "model.layers.30.self_attn.q_a_proj.scales": "model-00021-of-00044.safetensors",951 "model.layers.30.self_attn.q_a_proj.weight": "model-00021-of-00044.safetensors",952 "model.layers.30.self_attn.q_b_proj.biases": "model-00021-of-00044.safetensors",953 "model.layers.30.self_attn.q_b_proj.scales": "model-00021-of-00044.safetensors",954 "model.layers.30.self_attn.q_b_proj.weight": "model-00021-of-00044.safetensors",955 "model.layers.31.input_layernorm.weight": "model-00022-of-00044.safetensors",956 "model.layers.31.mlp.gate.e_score_correction_bias": "model-00022-of-00044.safetensors",957 "model.layers.31.mlp.gate.weight": "model-00022-of-00044.safetensors",958 "model.layers.31.mlp.shared_experts.down_proj.biases": "model-00022-of-00044.safetensors",959 "model.layers.31.mlp.shared_experts.down_proj.scales": "model-00022-of-00044.safetensors",960 "model.layers.31.mlp.shared_experts.down_proj.weight": "model-00022-of-00044.safetensors",961 "model.layers.31.mlp.shared_experts.gate_proj.biases": "model-00022-of-00044.safetensors",962 "model.layers.31.mlp.shared_experts.gate_proj.scales": "model-00022-of-00044.safetensors",963 "model.layers.31.mlp.shared_experts.gate_proj.weight": "model-00022-of-00044.safetensors",964 "model.layers.31.mlp.shared_experts.up_proj.biases": "model-00022-of-00044.safetensors",965 "model.layers.31.mlp.shared_experts.up_proj.scales": "model-00022-of-00044.safetensors",966 "model.layers.31.mlp.shared_experts.up_proj.weight": "model-00022-of-00044.safetensors",967 "model.layers.31.mlp.switch_mlp.down_proj.biases": "model-00022-of-00044.safetensors",968 "model.layers.31.mlp.switch_mlp.down_proj.scales": "model-00022-of-00044.safetensors",969 "model.layers.31.mlp.switch_mlp.down_proj.weight": "model-00022-of-00044.safetensors",970 "model.layers.31.mlp.switch_mlp.gate_proj.biases": "model-00022-of-00044.safetensors",971 "model.layers.31.mlp.switch_mlp.gate_proj.scales": "model-00022-of-00044.safetensors",972 "model.layers.31.mlp.switch_mlp.gate_proj.weight": "model-00022-of-00044.safetensors",973 "model.layers.31.mlp.switch_mlp.up_proj.biases": "model-00022-of-00044.safetensors",974 "model.layers.31.mlp.switch_mlp.up_proj.scales": "model-00022-of-00044.safetensors",975 "model.layers.31.mlp.switch_mlp.up_proj.weight": "model-00022-of-00044.safetensors",976 "model.layers.31.post_attention_layernorm.weight": "model-00022-of-00044.safetensors",977 "model.layers.31.self_attn.kv_a_layernorm.weight": "model-00022-of-00044.safetensors",978 "model.layers.31.self_attn.kv_a_proj_with_mqa.biases": "model-00022-of-00044.safetensors",979 "model.layers.31.self_attn.kv_a_proj_with_mqa.scales": "model-00022-of-00044.safetensors",980 "model.layers.31.self_attn.kv_a_proj_with_mqa.weight": "model-00022-of-00044.safetensors",981 "model.layers.31.self_attn.kv_b_proj.biases": "model-00022-of-00044.safetensors",982 "model.layers.31.self_attn.kv_b_proj.scales": "model-00022-of-00044.safetensors",983 "model.layers.31.self_attn.kv_b_proj.weight": "model-00022-of-00044.safetensors",984 "model.layers.31.self_attn.o_proj.biases": "model-00022-of-00044.safetensors",985 "model.layers.31.self_attn.o_proj.scales": "model-00022-of-00044.safetensors",986 "model.layers.31.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",987 "model.layers.31.self_attn.q_a_layernorm.weight": "model-00022-of-00044.safetensors",988 "model.layers.31.self_attn.q_a_proj.biases": "model-00022-of-00044.safetensors",989 "model.layers.31.self_attn.q_a_proj.scales": "model-00022-of-00044.safetensors",990 "model.layers.31.self_attn.q_a_proj.weight": "model-00022-of-00044.safetensors",991 "model.layers.31.self_attn.q_b_proj.biases": "model-00022-of-00044.safetensors",992 "model.layers.31.self_attn.q_b_proj.scales": "model-00022-of-00044.safetensors",993 "model.layers.31.self_attn.q_b_proj.weight": "model-00022-of-00044.safetensors",994 "model.layers.32.input_layernorm.weight": "model-00023-of-00044.safetensors",995 "model.layers.32.mlp.gate.e_score_correction_bias": "model-00023-of-00044.safetensors",996 "model.layers.32.mlp.gate.weight": "model-00023-of-00044.safetensors",997 "model.layers.32.mlp.shared_experts.down_proj.biases": "model-00023-of-00044.safetensors",998 "model.layers.32.mlp.shared_experts.down_proj.scales": "model-00023-of-00044.safetensors",999 "model.layers.32.mlp.shared_experts.down_proj.weight": "model-00023-of-00044.safetensors",1000 "model.layers.32.mlp.shared_experts.gate_proj.biases": "model-00023-of-00044.safetensors",1001 "model.layers.32.mlp.shared_experts.gate_proj.scales": "model-00023-of-00044.safetensors",1002 "model.layers.32.mlp.shared_experts.gate_proj.weight": "model-00023-of-00044.safetensors",1003 "model.layers.32.mlp.shared_experts.up_proj.biases": "model-00023-of-00044.safetensors",1004 "model.layers.32.mlp.shared_experts.up_proj.scales": "model-00023-of-00044.safetensors",1005 "model.layers.32.mlp.shared_experts.up_proj.weight": "model-00023-of-00044.safetensors",1006 "model.layers.32.mlp.switch_mlp.down_proj.biases": "model-00023-of-00044.safetensors",1007 "model.layers.32.mlp.switch_mlp.down_proj.scales": "model-00023-of-00044.safetensors",1008 "model.layers.32.mlp.switch_mlp.down_proj.weight": "model-00023-of-00044.safetensors",1009 "model.layers.32.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00044.safetensors",1010 "model.layers.32.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00044.safetensors",1011 "model.layers.32.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00044.safetensors",1012 "model.layers.32.mlp.switch_mlp.up_proj.biases": "model-00023-of-00044.safetensors",1013 "model.layers.32.mlp.switch_mlp.up_proj.scales": "model-00023-of-00044.safetensors",1014 "model.layers.32.mlp.switch_mlp.up_proj.weight": "model-00023-of-00044.safetensors",1015 "model.layers.32.post_attention_layernorm.weight": "model-00023-of-00044.safetensors",1016 "model.layers.32.self_attn.kv_a_layernorm.weight": "model-00022-of-00044.safetensors",1017 "model.layers.32.self_attn.kv_a_proj_with_mqa.biases": "model-00022-of-00044.safetensors",1018 "model.layers.32.self_attn.kv_a_proj_with_mqa.scales": "model-00022-of-00044.safetensors",1019 "model.layers.32.self_attn.kv_a_proj_with_mqa.weight": "model-00022-of-00044.safetensors",1020 "model.layers.32.self_attn.kv_b_proj.biases": "model-00022-of-00044.safetensors",1021 "model.layers.32.self_attn.kv_b_proj.scales": "model-00022-of-00044.safetensors",1022 "model.layers.32.self_attn.kv_b_proj.weight": "model-00022-of-00044.safetensors",1023 "model.layers.32.self_attn.o_proj.biases": "model-00022-of-00044.safetensors",1024 "model.layers.32.self_attn.o_proj.scales": "model-00022-of-00044.safetensors",1025 "model.layers.32.self_attn.o_proj.weight": "model-00022-of-00044.safetensors",1026 "model.layers.32.self_attn.q_a_layernorm.weight": "model-00022-of-00044.safetensors",1027 "model.layers.32.self_attn.q_a_proj.biases": "model-00022-of-00044.safetensors",1028 "model.layers.32.self_attn.q_a_proj.scales": "model-00022-of-00044.safetensors",1029 "model.layers.32.self_attn.q_a_proj.weight": "model-00022-of-00044.safetensors",1030 "model.layers.32.self_attn.q_b_proj.biases": "model-00022-of-00044.safetensors",1031 "model.layers.32.self_attn.q_b_proj.scales": "model-00022-of-00044.safetensors",1032 "model.layers.32.self_attn.q_b_proj.weight": "model-00022-of-00044.safetensors",1033 "model.layers.33.input_layernorm.weight": "model-00024-of-00044.safetensors",1034 "model.layers.33.mlp.gate.e_score_correction_bias": "model-00024-of-00044.safetensors",1035 "model.layers.33.mlp.gate.weight": "model-00024-of-00044.safetensors",1036 "model.layers.33.mlp.shared_experts.down_proj.biases": "model-00024-of-00044.safetensors",1037 "model.layers.33.mlp.shared_experts.down_proj.scales": "model-00024-of-00044.safetensors",1038 "model.layers.33.mlp.shared_experts.down_proj.weight": "model-00024-of-00044.safetensors",1039 "model.layers.33.mlp.shared_experts.gate_proj.biases": "model-00024-of-00044.safetensors",1040 "model.layers.33.mlp.shared_experts.gate_proj.scales": "model-00024-of-00044.safetensors",1041 "model.layers.33.mlp.shared_experts.gate_proj.weight": "model-00024-of-00044.safetensors",1042 "model.layers.33.mlp.shared_experts.up_proj.biases": "model-00024-of-00044.safetensors",1043 "model.layers.33.mlp.shared_experts.up_proj.scales": "model-00024-of-00044.safetensors",1044 "model.layers.33.mlp.shared_experts.up_proj.weight": "model-00024-of-00044.safetensors",1045 "model.layers.33.mlp.switch_mlp.down_proj.biases": "model-00024-of-00044.safetensors",1046 "model.layers.33.mlp.switch_mlp.down_proj.scales": "model-00024-of-00044.safetensors",1047 "model.layers.33.mlp.switch_mlp.down_proj.weight": "model-00024-of-00044.safetensors",1048 "model.layers.33.mlp.switch_mlp.gate_proj.biases": "model-00023-of-00044.safetensors",1049 "model.layers.33.mlp.switch_mlp.gate_proj.scales": "model-00023-of-00044.safetensors",1050 "model.layers.33.mlp.switch_mlp.gate_proj.weight": "model-00023-of-00044.safetensors",1051 "model.layers.33.mlp.switch_mlp.up_proj.biases": "model-00024-of-00044.safetensors",1052 "model.layers.33.mlp.switch_mlp.up_proj.scales": "model-00024-of-00044.safetensors",1053 "model.layers.33.mlp.switch_mlp.up_proj.weight": "model-00024-of-00044.safetensors",1054 "model.layers.33.post_attention_layernorm.weight": "model-00024-of-00044.safetensors",1055 "model.layers.33.self_attn.kv_a_layernorm.weight": "model-00023-of-00044.safetensors",1056 "model.layers.33.self_attn.kv_a_proj_with_mqa.biases": "model-00023-of-00044.safetensors",1057 "model.layers.33.self_attn.kv_a_proj_with_mqa.scales": "model-00023-of-00044.safetensors",1058 "model.layers.33.self_attn.kv_a_proj_with_mqa.weight": "model-00023-of-00044.safetensors",1059 "model.layers.33.self_attn.kv_b_proj.biases": "model-00023-of-00044.safetensors",1060 "model.layers.33.self_attn.kv_b_proj.scales": "model-00023-of-00044.safetensors",1061 "model.layers.33.self_attn.kv_b_proj.weight": "model-00023-of-00044.safetensors",1062 "model.layers.33.self_attn.o_proj.biases": "model-00023-of-00044.safetensors",1063 "model.layers.33.self_attn.o_proj.scales": "model-00023-of-00044.safetensors",1064 "model.layers.33.self_attn.o_proj.weight": "model-00023-of-00044.safetensors",1065 "model.layers.33.self_attn.q_a_layernorm.weight": "model-00023-of-00044.safetensors",1066 "model.layers.33.self_attn.q_a_proj.biases": "model-00023-of-00044.safetensors",1067 "model.layers.33.self_attn.q_a_proj.scales": "model-00023-of-00044.safetensors",1068 "model.layers.33.self_attn.q_a_proj.weight": "model-00023-of-00044.safetensors",1069 "model.layers.33.self_attn.q_b_proj.biases": "model-00023-of-00044.safetensors",1070 "model.layers.33.self_attn.q_b_proj.scales": "model-00023-of-00044.safetensors",1071 "model.layers.33.self_attn.q_b_proj.weight": "model-00023-of-00044.safetensors",1072 "model.layers.34.input_layernorm.weight": "model-00025-of-00044.safetensors",1073 "model.layers.34.mlp.gate.e_score_correction_bias": "model-00025-of-00044.safetensors",1074 "model.layers.34.mlp.gate.weight": "model-00025-of-00044.safetensors",1075 "model.layers.34.mlp.shared_experts.down_proj.biases": "model-00025-of-00044.safetensors",1076 "model.layers.34.mlp.shared_experts.down_proj.scales": "model-00025-of-00044.safetensors",1077 "model.layers.34.mlp.shared_experts.down_proj.weight": "model-00025-of-00044.safetensors",1078 "model.layers.34.mlp.shared_experts.gate_proj.biases": "model-00025-of-00044.safetensors",1079 "model.layers.34.mlp.shared_experts.gate_proj.scales": "model-00025-of-00044.safetensors",1080 "model.layers.34.mlp.shared_experts.gate_proj.weight": "model-00025-of-00044.safetensors",1081 "model.layers.34.mlp.shared_experts.up_proj.biases": "model-00025-of-00044.safetensors",1082 "model.layers.34.mlp.shared_experts.up_proj.scales": "model-00025-of-00044.safetensors",1083 "model.layers.34.mlp.shared_experts.up_proj.weight": "model-00025-of-00044.safetensors",1084 "model.layers.34.mlp.switch_mlp.down_proj.biases": "model-00025-of-00044.safetensors",1085 "model.layers.34.mlp.switch_mlp.down_proj.scales": "model-00025-of-00044.safetensors",1086 "model.layers.34.mlp.switch_mlp.down_proj.weight": "model-00025-of-00044.safetensors",1087 "model.layers.34.mlp.switch_mlp.gate_proj.biases": "model-00024-of-00044.safetensors",1088 "model.layers.34.mlp.switch_mlp.gate_proj.scales": "model-00024-of-00044.safetensors",1089 "model.layers.34.mlp.switch_mlp.gate_proj.weight": "model-00024-of-00044.safetensors",1090 "model.layers.34.mlp.switch_mlp.up_proj.biases": "model-00024-of-00044.safetensors",1091 "model.layers.34.mlp.switch_mlp.up_proj.scales": "model-00024-of-00044.safetensors",1092 "model.layers.34.mlp.switch_mlp.up_proj.weight": "model-00024-of-00044.safetensors",1093 "model.layers.34.post_attention_layernorm.weight": "model-00025-of-00044.safetensors",1094 "model.layers.34.self_attn.kv_a_layernorm.weight": "model-00024-of-00044.safetensors",1095 "model.layers.34.self_attn.kv_a_proj_with_mqa.biases": "model-00024-of-00044.safetensors",1096 "model.layers.34.self_attn.kv_a_proj_with_mqa.scales": "model-00024-of-00044.safetensors",1097 "model.layers.34.self_attn.kv_a_proj_with_mqa.weight": "model-00024-of-00044.safetensors",1098 "model.layers.34.self_attn.kv_b_proj.biases": "model-00024-of-00044.safetensors",1099 "model.layers.34.self_attn.kv_b_proj.scales": "model-00024-of-00044.safetensors",1100 "model.layers.34.self_attn.kv_b_proj.weight": "model-00024-of-00044.safetensors",1101 "model.layers.34.self_attn.o_proj.biases": "model-00024-of-00044.safetensors",1102 "model.layers.34.self_attn.o_proj.scales": "model-00024-of-00044.safetensors",1103 "model.layers.34.self_attn.o_proj.weight": "model-00024-of-00044.safetensors",1104 "model.layers.34.self_attn.q_a_layernorm.weight": "model-00024-of-00044.safetensors",1105 "model.layers.34.self_attn.q_a_proj.biases": "model-00024-of-00044.safetensors",1106 "model.layers.34.self_attn.q_a_proj.scales": "model-00024-of-00044.safetensors",1107 "model.layers.34.self_attn.q_a_proj.weight": "model-00024-of-00044.safetensors",1108 "model.layers.34.self_attn.q_b_proj.biases": "model-00024-of-00044.safetensors",1109 "model.layers.34.self_attn.q_b_proj.scales": "model-00024-of-00044.safetensors",1110 "model.layers.34.self_attn.q_b_proj.weight": "model-00024-of-00044.safetensors",1111 "model.layers.35.input_layernorm.weight": "model-00025-of-00044.safetensors",1112 "model.layers.35.mlp.gate.e_score_correction_bias": "model-00025-of-00044.safetensors",1113 "model.layers.35.mlp.gate.weight": "model-00025-of-00044.safetensors",1114 "model.layers.35.mlp.shared_experts.down_proj.biases": "model-00025-of-00044.safetensors",1115 "model.layers.35.mlp.shared_experts.down_proj.scales": "model-00025-of-00044.safetensors",1116 "model.layers.35.mlp.shared_experts.down_proj.weight": "model-00025-of-00044.safetensors",1117 "model.layers.35.mlp.shared_experts.gate_proj.biases": "model-00025-of-00044.safetensors",1118 "model.layers.35.mlp.shared_experts.gate_proj.scales": "model-00025-of-00044.safetensors",1119 "model.layers.35.mlp.shared_experts.gate_proj.weight": "model-00025-of-00044.safetensors",1120 "model.layers.35.mlp.shared_experts.up_proj.biases": "model-00025-of-00044.safetensors",1121 "model.layers.35.mlp.shared_experts.up_proj.scales": "model-00025-of-00044.safetensors",1122 "model.layers.35.mlp.shared_experts.up_proj.weight": "model-00025-of-00044.safetensors",1123 "model.layers.35.mlp.switch_mlp.down_proj.biases": "model-00025-of-00044.safetensors",1124 "model.layers.35.mlp.switch_mlp.down_proj.scales": "model-00025-of-00044.safetensors",1125 "model.layers.35.mlp.switch_mlp.down_proj.weight": "model-00025-of-00044.safetensors",1126 "model.layers.35.mlp.switch_mlp.gate_proj.biases": "model-00025-of-00044.safetensors",1127 "model.layers.35.mlp.switch_mlp.gate_proj.scales": "model-00025-of-00044.safetensors",1128 "model.layers.35.mlp.switch_mlp.gate_proj.weight": "model-00025-of-00044.safetensors",1129 "model.layers.35.mlp.switch_mlp.up_proj.biases": "model-00025-of-00044.safetensors",1130 "model.layers.35.mlp.switch_mlp.up_proj.scales": "model-00025-of-00044.safetensors",1131 "model.layers.35.mlp.switch_mlp.up_proj.weight": "model-00025-of-00044.safetensors",1132 "model.layers.35.post_attention_layernorm.weight": "model-00025-of-00044.safetensors",1133 "model.layers.35.self_attn.kv_a_layernorm.weight": "model-00025-of-00044.safetensors",1134 "model.layers.35.self_attn.kv_a_proj_with_mqa.biases": "model-00025-of-00044.safetensors",1135 "model.layers.35.self_attn.kv_a_proj_with_mqa.scales": "model-00025-of-00044.safetensors",1136 "model.layers.35.self_attn.kv_a_proj_with_mqa.weight": "model-00025-of-00044.safetensors",1137 "model.layers.35.self_attn.kv_b_proj.biases": "model-00025-of-00044.safetensors",1138 "model.layers.35.self_attn.kv_b_proj.scales": "model-00025-of-00044.safetensors",1139 "model.layers.35.self_attn.kv_b_proj.weight": "model-00025-of-00044.safetensors",1140 "model.layers.35.self_attn.o_proj.biases": "model-00025-of-00044.safetensors",1141 "model.layers.35.self_attn.o_proj.scales": "model-00025-of-00044.safetensors",1142 "model.layers.35.self_attn.o_proj.weight": "model-00025-of-00044.safetensors",1143 "model.layers.35.self_attn.q_a_layernorm.weight": "model-00025-of-00044.safetensors",1144 "model.layers.35.self_attn.q_a_proj.biases": "model-00025-of-00044.safetensors",1145 "model.layers.35.self_attn.q_a_proj.scales": "model-00025-of-00044.safetensors",1146 "model.layers.35.self_attn.q_a_proj.weight": "model-00025-of-00044.safetensors",1147 "model.layers.35.self_attn.q_b_proj.biases": "model-00025-of-00044.safetensors",1148 "model.layers.35.self_attn.q_b_proj.scales": "model-00025-of-00044.safetensors",1149 "model.layers.35.self_attn.q_b_proj.weight": "model-00025-of-00044.safetensors",1150 "model.layers.36.input_layernorm.weight": "model-00026-of-00044.safetensors",1151 "model.layers.36.mlp.gate.e_score_correction_bias": "model-00026-of-00044.safetensors",1152 "model.layers.36.mlp.gate.weight": "model-00026-of-00044.safetensors",1153 "model.layers.36.mlp.shared_experts.down_proj.biases": "model-00026-of-00044.safetensors",1154 "model.layers.36.mlp.shared_experts.down_proj.scales": "model-00026-of-00044.safetensors",1155 "model.layers.36.mlp.shared_experts.down_proj.weight": "model-00026-of-00044.safetensors",1156 "model.layers.36.mlp.shared_experts.gate_proj.biases": "model-00026-of-00044.safetensors",1157 "model.layers.36.mlp.shared_experts.gate_proj.scales": "model-00026-of-00044.safetensors",1158 "model.layers.36.mlp.shared_experts.gate_proj.weight": "model-00026-of-00044.safetensors",1159 "model.layers.36.mlp.shared_experts.up_proj.biases": "model-00026-of-00044.safetensors",1160 "model.layers.36.mlp.shared_experts.up_proj.scales": "model-00026-of-00044.safetensors",1161 "model.layers.36.mlp.shared_experts.up_proj.weight": "model-00026-of-00044.safetensors",1162 "model.layers.36.mlp.switch_mlp.down_proj.biases": "model-00026-of-00044.safetensors",1163 "model.layers.36.mlp.switch_mlp.down_proj.scales": "model-00026-of-00044.safetensors",1164 "model.layers.36.mlp.switch_mlp.down_proj.weight": "model-00026-of-00044.safetensors",1165 "model.layers.36.mlp.switch_mlp.gate_proj.biases": "model-00026-of-00044.safetensors",1166 "model.layers.36.mlp.switch_mlp.gate_proj.scales": "model-00026-of-00044.safetensors",1167 "model.layers.36.mlp.switch_mlp.gate_proj.weight": "model-00026-of-00044.safetensors",1168 "model.layers.36.mlp.switch_mlp.up_proj.biases": "model-00026-of-00044.safetensors",1169 "model.layers.36.mlp.switch_mlp.up_proj.scales": "model-00026-of-00044.safetensors",1170 "model.layers.36.mlp.switch_mlp.up_proj.weight": "model-00026-of-00044.safetensors",1171 "model.layers.36.post_attention_layernorm.weight": "model-00026-of-00044.safetensors",1172 "model.layers.36.self_attn.kv_a_layernorm.weight": "model-00025-of-00044.safetensors",1173 "model.layers.36.self_attn.kv_a_proj_with_mqa.biases": "model-00025-of-00044.safetensors",1174 "model.layers.36.self_attn.kv_a_proj_with_mqa.scales": "model-00025-of-00044.safetensors",1175 "model.layers.36.self_attn.kv_a_proj_with_mqa.weight": "model-00025-of-00044.safetensors",1176 "model.layers.36.self_attn.kv_b_proj.biases": "model-00025-of-00044.safetensors",1177 "model.layers.36.self_attn.kv_b_proj.scales": "model-00025-of-00044.safetensors",1178 "model.layers.36.self_attn.kv_b_proj.weight": "model-00025-of-00044.safetensors",1179 "model.layers.36.self_attn.o_proj.biases": "model-00025-of-00044.safetensors",1180 "model.layers.36.self_attn.o_proj.scales": "model-00025-of-00044.safetensors",1181 "model.layers.36.self_attn.o_proj.weight": "model-00025-of-00044.safetensors",1182 "model.layers.36.self_attn.q_a_layernorm.weight": "model-00025-of-00044.safetensors",1183 "model.layers.36.self_attn.q_a_proj.biases": "model-00025-of-00044.safetensors",1184 "model.layers.36.self_attn.q_a_proj.scales": "model-00025-of-00044.safetensors",1185 "model.layers.36.self_attn.q_a_proj.weight": "model-00025-of-00044.safetensors",1186 "model.layers.36.self_attn.q_b_proj.biases": "model-00025-of-00044.safetensors",1187 "model.layers.36.self_attn.q_b_proj.scales": "model-00025-of-00044.safetensors",1188 "model.layers.36.self_attn.q_b_proj.weight": "model-00025-of-00044.safetensors",1189 "model.layers.37.input_layernorm.weight": "model-00027-of-00044.safetensors",1190 "model.layers.37.mlp.gate.e_score_correction_bias": "model-00027-of-00044.safetensors",1191 "model.layers.37.mlp.gate.weight": "model-00027-of-00044.safetensors",1192 "model.layers.37.mlp.shared_experts.down_proj.biases": "model-00027-of-00044.safetensors",1193 "model.layers.37.mlp.shared_experts.down_proj.scales": "model-00027-of-00044.safetensors",1194 "model.layers.37.mlp.shared_experts.down_proj.weight": "model-00027-of-00044.safetensors",1195 "model.layers.37.mlp.shared_experts.gate_proj.biases": "model-00027-of-00044.safetensors",1196 "model.layers.37.mlp.shared_experts.gate_proj.scales": "model-00027-of-00044.safetensors",1197 "model.layers.37.mlp.shared_experts.gate_proj.weight": "model-00027-of-00044.safetensors",1198 "model.layers.37.mlp.shared_experts.up_proj.biases": "model-00027-of-00044.safetensors",1199 "model.layers.37.mlp.shared_experts.up_proj.scales": "model-00027-of-00044.safetensors",1200 "model.layers.37.mlp.shared_experts.up_proj.weight": "model-00027-of-00044.safetensors",