TransWithAI/Step-Audio-R1.1-NVFP4
112
1{2 "metadata": {3 "total_parameters": 19834574976,4 "total_size": 221159895045 },6 "weight_map": {7 "adapter.conv.bias": "model-00005-of-00005.safetensors",8 "adapter.conv.weight": "model-00005-of-00005.safetensors",9 "adapter.linear1.bias": "model-00005-of-00005.safetensors",10 "adapter.linear1.weight": "model-00005-of-00005.safetensors",11 "adapter.linear2.bias": "model-00005-of-00005.safetensors",12 "adapter.linear2.weight": "model-00005-of-00005.safetensors",13 "encoder.after_norm.bias": "model-00005-of-00005.safetensors",14 "encoder.after_norm.weight": "model-00005-of-00005.safetensors",15 "encoder.blocks.0.attn.key.weight": "model-00004-of-00005.safetensors",16 "encoder.blocks.0.attn.out.bias": "model-00004-of-00005.safetensors",17 "encoder.blocks.0.attn.out.weight": "model-00004-of-00005.safetensors",18 "encoder.blocks.0.attn.query.bias": "model-00004-of-00005.safetensors",19 "encoder.blocks.0.attn.query.weight": "model-00004-of-00005.safetensors",20 "encoder.blocks.0.attn.value.bias": "model-00004-of-00005.safetensors",21 "encoder.blocks.0.attn.value.weight": "model-00004-of-00005.safetensors",22 "encoder.blocks.0.attn_ln.bias": "model-00004-of-00005.safetensors",23 "encoder.blocks.0.attn_ln.weight": "model-00004-of-00005.safetensors",24 "encoder.blocks.0.mlp.0.bias": "model-00004-of-00005.safetensors",25 "encoder.blocks.0.mlp.0.weight": "model-00004-of-00005.safetensors",26 "encoder.blocks.0.mlp.2.bias": "model-00004-of-00005.safetensors",27 "encoder.blocks.0.mlp.2.weight": "model-00004-of-00005.safetensors",28 "encoder.blocks.0.mlp_ln.bias": "model-00004-of-00005.safetensors",29 "encoder.blocks.0.mlp_ln.weight": "model-00004-of-00005.safetensors",30 "encoder.blocks.1.attn.key.weight": "model-00004-of-00005.safetensors",31 "encoder.blocks.1.attn.out.bias": "model-00004-of-00005.safetensors",32 "encoder.blocks.1.attn.out.weight": "model-00004-of-00005.safetensors",33 "encoder.blocks.1.attn.query.bias": "model-00004-of-00005.safetensors",34 "encoder.blocks.1.attn.query.weight": "model-00004-of-00005.safetensors",35 "encoder.blocks.1.attn.value.bias": "model-00004-of-00005.safetensors",36 "encoder.blocks.1.attn.value.weight": "model-00004-of-00005.safetensors",37 "encoder.blocks.1.attn_ln.bias": "model-00004-of-00005.safetensors",38 "encoder.blocks.1.attn_ln.weight": "model-00004-of-00005.safetensors",39 "encoder.blocks.1.mlp.0.bias": "model-00004-of-00005.safetensors",40 "encoder.blocks.1.mlp.0.weight": "model-00004-of-00005.safetensors",41 "encoder.blocks.1.mlp.2.bias": "model-00004-of-00005.safetensors",42 "encoder.blocks.1.mlp.2.weight": "model-00004-of-00005.safetensors",43 "encoder.blocks.1.mlp_ln.bias": "model-00004-of-00005.safetensors",44 "encoder.blocks.1.mlp_ln.weight": "model-00004-of-00005.safetensors",45 "encoder.blocks.10.attn.key.weight": "model-00004-of-00005.safetensors",46 "encoder.blocks.10.attn.out.bias": "model-00004-of-00005.safetensors",47 "encoder.blocks.10.attn.out.weight": "model-00004-of-00005.safetensors",48 "encoder.blocks.10.attn.query.bias": "model-00004-of-00005.safetensors",49 "encoder.blocks.10.attn.query.weight": "model-00004-of-00005.safetensors",50 "encoder.blocks.10.attn.value.bias": "model-00004-of-00005.safetensors",51 "encoder.blocks.10.attn.value.weight": "model-00004-of-00005.safetensors",52 "encoder.blocks.10.attn_ln.bias": "model-00004-of-00005.safetensors",53 "encoder.blocks.10.attn_ln.weight": "model-00004-of-00005.safetensors",54 "encoder.blocks.10.mlp.0.bias": "model-00004-of-00005.safetensors",55 "encoder.blocks.10.mlp.0.weight": "model-00004-of-00005.safetensors",56 "encoder.blocks.10.mlp.2.bias": "model-00004-of-00005.safetensors",57 "encoder.blocks.10.mlp.2.weight": "model-00004-of-00005.safetensors",58 "encoder.blocks.10.mlp_ln.bias": "model-00004-of-00005.safetensors",59 "encoder.blocks.10.mlp_ln.weight": "model-00004-of-00005.safetensors",60 "encoder.blocks.11.attn.key.weight": "model-00004-of-00005.safetensors",61 "encoder.blocks.11.attn.out.bias": "model-00004-of-00005.safetensors",62 "encoder.blocks.11.attn.out.weight": "model-00004-of-00005.safetensors",63 "encoder.blocks.11.attn.query.bias": "model-00004-of-00005.safetensors",64 "encoder.blocks.11.attn.query.weight": "model-00004-of-00005.safetensors",65 "encoder.blocks.11.attn.value.bias": "model-00004-of-00005.safetensors",66 "encoder.blocks.11.attn.value.weight": "model-00004-of-00005.safetensors",67 "encoder.blocks.11.attn_ln.bias": "model-00004-of-00005.safetensors",68 "encoder.blocks.11.attn_ln.weight": "model-00004-of-00005.safetensors",69 "encoder.blocks.11.mlp.0.bias": "model-00004-of-00005.safetensors",70 "encoder.blocks.11.mlp.0.weight": "model-00004-of-00005.safetensors",71 "encoder.blocks.11.mlp.2.bias": "model-00004-of-00005.safetensors",72 "encoder.blocks.11.mlp.2.weight": "model-00004-of-00005.safetensors",73 "encoder.blocks.11.mlp_ln.bias": "model-00004-of-00005.safetensors",74 "encoder.blocks.11.mlp_ln.weight": "model-00004-of-00005.safetensors",75 "encoder.blocks.12.attn.key.weight": "model-00004-of-00005.safetensors",76 "encoder.blocks.12.attn.out.bias": "model-00004-of-00005.safetensors",77 "encoder.blocks.12.attn.out.weight": "model-00004-of-00005.safetensors",78 "encoder.blocks.12.attn.query.bias": "model-00004-of-00005.safetensors",79 "encoder.blocks.12.attn.query.weight": "model-00004-of-00005.safetensors",80 "encoder.blocks.12.attn.value.bias": "model-00004-of-00005.safetensors",81 "encoder.blocks.12.attn.value.weight": "model-00004-of-00005.safetensors",82 "encoder.blocks.12.attn_ln.bias": "model-00004-of-00005.safetensors",83 "encoder.blocks.12.attn_ln.weight": "model-00004-of-00005.safetensors",84 "encoder.blocks.12.mlp.0.bias": "model-00004-of-00005.safetensors",85 "encoder.blocks.12.mlp.0.weight": "model-00004-of-00005.safetensors",86 "encoder.blocks.12.mlp.2.bias": "model-00004-of-00005.safetensors",87 "encoder.blocks.12.mlp.2.weight": "model-00004-of-00005.safetensors",88 "encoder.blocks.12.mlp_ln.bias": "model-00004-of-00005.safetensors",89 "encoder.blocks.12.mlp_ln.weight": "model-00004-of-00005.safetensors",90 "encoder.blocks.13.attn.key.weight": "model-00004-of-00005.safetensors",91 "encoder.blocks.13.attn.out.bias": "model-00004-of-00005.safetensors",92 "encoder.blocks.13.attn.out.weight": "model-00004-of-00005.safetensors",93 "encoder.blocks.13.attn.query.bias": "model-00004-of-00005.safetensors",94 "encoder.blocks.13.attn.query.weight": "model-00004-of-00005.safetensors",95 "encoder.blocks.13.attn.value.bias": "model-00004-of-00005.safetensors",96 "encoder.blocks.13.attn.value.weight": "model-00004-of-00005.safetensors",97 "encoder.blocks.13.attn_ln.bias": "model-00004-of-00005.safetensors",98 "encoder.blocks.13.attn_ln.weight": "model-00004-of-00005.safetensors",99 "encoder.blocks.13.mlp.0.bias": "model-00004-of-00005.safetensors",100 "encoder.blocks.13.mlp.0.weight": "model-00004-of-00005.safetensors",101 "encoder.blocks.13.mlp.2.bias": "model-00004-of-00005.safetensors",102 "encoder.blocks.13.mlp.2.weight": "model-00004-of-00005.safetensors",103 "encoder.blocks.13.mlp_ln.bias": "model-00004-of-00005.safetensors",104 "encoder.blocks.13.mlp_ln.weight": "model-00004-of-00005.safetensors",105 "encoder.blocks.14.attn.key.weight": "model-00004-of-00005.safetensors",106 "encoder.blocks.14.attn.out.bias": "model-00004-of-00005.safetensors",107 "encoder.blocks.14.attn.out.weight": "model-00004-of-00005.safetensors",108 "encoder.blocks.14.attn.query.bias": "model-00004-of-00005.safetensors",109 "encoder.blocks.14.attn.query.weight": "model-00004-of-00005.safetensors",110 "encoder.blocks.14.attn.value.bias": "model-00004-of-00005.safetensors",111 "encoder.blocks.14.attn.value.weight": "model-00004-of-00005.safetensors",112 "encoder.blocks.14.attn_ln.bias": "model-00004-of-00005.safetensors",113 "encoder.blocks.14.attn_ln.weight": "model-00004-of-00005.safetensors",114 "encoder.blocks.14.mlp.0.bias": "model-00004-of-00005.safetensors",115 "encoder.blocks.14.mlp.0.weight": "model-00004-of-00005.safetensors",116 "encoder.blocks.14.mlp.2.bias": "model-00004-of-00005.safetensors",117 "encoder.blocks.14.mlp.2.weight": "model-00004-of-00005.safetensors",118 "encoder.blocks.14.mlp_ln.bias": "model-00004-of-00005.safetensors",119 "encoder.blocks.14.mlp_ln.weight": "model-00004-of-00005.safetensors",120 "encoder.blocks.15.attn.key.weight": "model-00004-of-00005.safetensors",121 "encoder.blocks.15.attn.out.bias": "model-00004-of-00005.safetensors",122 "encoder.blocks.15.attn.out.weight": "model-00004-of-00005.safetensors",123 "encoder.blocks.15.attn.query.bias": "model-00004-of-00005.safetensors",124 "encoder.blocks.15.attn.query.weight": "model-00004-of-00005.safetensors",125 "encoder.blocks.15.attn.value.bias": "model-00004-of-00005.safetensors",126 "encoder.blocks.15.attn.value.weight": "model-00004-of-00005.safetensors",127 "encoder.blocks.15.attn_ln.bias": "model-00004-of-00005.safetensors",128 "encoder.blocks.15.attn_ln.weight": "model-00004-of-00005.safetensors",129 "encoder.blocks.15.mlp.0.bias": "model-00004-of-00005.safetensors",130 "encoder.blocks.15.mlp.0.weight": "model-00004-of-00005.safetensors",131 "encoder.blocks.15.mlp.2.bias": "model-00004-of-00005.safetensors",132 "encoder.blocks.15.mlp.2.weight": "model-00004-of-00005.safetensors",133 "encoder.blocks.15.mlp_ln.bias": "model-00004-of-00005.safetensors",134 "encoder.blocks.15.mlp_ln.weight": "model-00004-of-00005.safetensors",135 "encoder.blocks.16.attn.key.weight": "model-00005-of-00005.safetensors",136 "encoder.blocks.16.attn.out.bias": "model-00005-of-00005.safetensors",137 "encoder.blocks.16.attn.out.weight": "model-00005-of-00005.safetensors",138 "encoder.blocks.16.attn.query.bias": "model-00005-of-00005.safetensors",139 "encoder.blocks.16.attn.query.weight": "model-00005-of-00005.safetensors",140 "encoder.blocks.16.attn.value.bias": "model-00005-of-00005.safetensors",141 "encoder.blocks.16.attn.value.weight": "model-00005-of-00005.safetensors",142 "encoder.blocks.16.attn_ln.bias": "model-00005-of-00005.safetensors",143 "encoder.blocks.16.attn_ln.weight": "model-00005-of-00005.safetensors",144 "encoder.blocks.16.mlp.0.bias": "model-00005-of-00005.safetensors",145 "encoder.blocks.16.mlp.0.weight": "model-00005-of-00005.safetensors",146 "encoder.blocks.16.mlp.2.bias": "model-00005-of-00005.safetensors",147 "encoder.blocks.16.mlp.2.weight": "model-00005-of-00005.safetensors",148 "encoder.blocks.16.mlp_ln.bias": "model-00005-of-00005.safetensors",149 "encoder.blocks.16.mlp_ln.weight": "model-00005-of-00005.safetensors",150 "encoder.blocks.17.attn.key.weight": "model-00005-of-00005.safetensors",151 "encoder.blocks.17.attn.out.bias": "model-00005-of-00005.safetensors",152 "encoder.blocks.17.attn.out.weight": "model-00005-of-00005.safetensors",153 "encoder.blocks.17.attn.query.bias": "model-00005-of-00005.safetensors",154 "encoder.blocks.17.attn.query.weight": "model-00005-of-00005.safetensors",155 "encoder.blocks.17.attn.value.bias": "model-00005-of-00005.safetensors",156 "encoder.blocks.17.attn.value.weight": "model-00005-of-00005.safetensors",157 "encoder.blocks.17.attn_ln.bias": "model-00005-of-00005.safetensors",158 "encoder.blocks.17.attn_ln.weight": "model-00005-of-00005.safetensors",159 "encoder.blocks.17.mlp.0.bias": "model-00005-of-00005.safetensors",160 "encoder.blocks.17.mlp.0.weight": "model-00005-of-00005.safetensors",161 "encoder.blocks.17.mlp.2.bias": "model-00005-of-00005.safetensors",162 "encoder.blocks.17.mlp.2.weight": "model-00005-of-00005.safetensors",163 "encoder.blocks.17.mlp_ln.bias": "model-00005-of-00005.safetensors",164 "encoder.blocks.17.mlp_ln.weight": "model-00005-of-00005.safetensors",165 "encoder.blocks.18.attn.key.weight": "model-00005-of-00005.safetensors",166 "encoder.blocks.18.attn.out.bias": "model-00005-of-00005.safetensors",167 "encoder.blocks.18.attn.out.weight": "model-00005-of-00005.safetensors",168 "encoder.blocks.18.attn.query.bias": "model-00005-of-00005.safetensors",169 "encoder.blocks.18.attn.query.weight": "model-00005-of-00005.safetensors",170 "encoder.blocks.18.attn.value.bias": "model-00005-of-00005.safetensors",171 "encoder.blocks.18.attn.value.weight": "model-00005-of-00005.safetensors",172 "encoder.blocks.18.attn_ln.bias": "model-00005-of-00005.safetensors",173 "encoder.blocks.18.attn_ln.weight": "model-00005-of-00005.safetensors",174 "encoder.blocks.18.mlp.0.bias": "model-00005-of-00005.safetensors",175 "encoder.blocks.18.mlp.0.weight": "model-00005-of-00005.safetensors",176 "encoder.blocks.18.mlp.2.bias": "model-00005-of-00005.safetensors",177 "encoder.blocks.18.mlp.2.weight": "model-00005-of-00005.safetensors",178 "encoder.blocks.18.mlp_ln.bias": "model-00005-of-00005.safetensors",179 "encoder.blocks.18.mlp_ln.weight": "model-00005-of-00005.safetensors",180 "encoder.blocks.19.attn.key.weight": "model-00005-of-00005.safetensors",181 "encoder.blocks.19.attn.out.bias": "model-00005-of-00005.safetensors",182 "encoder.blocks.19.attn.out.weight": "model-00005-of-00005.safetensors",183 "encoder.blocks.19.attn.query.bias": "model-00005-of-00005.safetensors",184 "encoder.blocks.19.attn.query.weight": "model-00005-of-00005.safetensors",185 "encoder.blocks.19.attn.value.bias": "model-00005-of-00005.safetensors",186 "encoder.blocks.19.attn.value.weight": "model-00005-of-00005.safetensors",187 "encoder.blocks.19.attn_ln.bias": "model-00005-of-00005.safetensors",188 "encoder.blocks.19.attn_ln.weight": "model-00005-of-00005.safetensors",189 "encoder.blocks.19.mlp.0.bias": "model-00005-of-00005.safetensors",190 "encoder.blocks.19.mlp.0.weight": "model-00005-of-00005.safetensors",191 "encoder.blocks.19.mlp.2.bias": "model-00005-of-00005.safetensors",192 "encoder.blocks.19.mlp.2.weight": "model-00005-of-00005.safetensors",193 "encoder.blocks.19.mlp_ln.bias": "model-00005-of-00005.safetensors",194 "encoder.blocks.19.mlp_ln.weight": "model-00005-of-00005.safetensors",195 "encoder.blocks.2.attn.key.weight": "model-00004-of-00005.safetensors",196 "encoder.blocks.2.attn.out.bias": "model-00004-of-00005.safetensors",197 "encoder.blocks.2.attn.out.weight": "model-00004-of-00005.safetensors",198 "encoder.blocks.2.attn.query.bias": "model-00004-of-00005.safetensors",199 "encoder.blocks.2.attn.query.weight": "model-00004-of-00005.safetensors",200 "encoder.blocks.2.attn.value.bias": "model-00004-of-00005.safetensors",201 "encoder.blocks.2.attn.value.weight": "model-00004-of-00005.safetensors",202 "encoder.blocks.2.attn_ln.bias": "model-00004-of-00005.safetensors",203 "encoder.blocks.2.attn_ln.weight": "model-00004-of-00005.safetensors",204 "encoder.blocks.2.mlp.0.bias": "model-00004-of-00005.safetensors",205 "encoder.blocks.2.mlp.0.weight": "model-00004-of-00005.safetensors",206 "encoder.blocks.2.mlp.2.bias": "model-00004-of-00005.safetensors",207 "encoder.blocks.2.mlp.2.weight": "model-00004-of-00005.safetensors",208 "encoder.blocks.2.mlp_ln.bias": "model-00004-of-00005.safetensors",209 "encoder.blocks.2.mlp_ln.weight": "model-00004-of-00005.safetensors",210 "encoder.blocks.20.attn.key.weight": "model-00005-of-00005.safetensors",211 "encoder.blocks.20.attn.out.bias": "model-00005-of-00005.safetensors",212 "encoder.blocks.20.attn.out.weight": "model-00005-of-00005.safetensors",213 "encoder.blocks.20.attn.query.bias": "model-00005-of-00005.safetensors",214 "encoder.blocks.20.attn.query.weight": "model-00005-of-00005.safetensors",215 "encoder.blocks.20.attn.value.bias": "model-00005-of-00005.safetensors",216 "encoder.blocks.20.attn.value.weight": "model-00005-of-00005.safetensors",217 "encoder.blocks.20.attn_ln.bias": "model-00005-of-00005.safetensors",218 "encoder.blocks.20.attn_ln.weight": "model-00005-of-00005.safetensors",219 "encoder.blocks.20.mlp.0.bias": "model-00005-of-00005.safetensors",220 "encoder.blocks.20.mlp.0.weight": "model-00005-of-00005.safetensors",221 "encoder.blocks.20.mlp.2.bias": "model-00005-of-00005.safetensors",222 "encoder.blocks.20.mlp.2.weight": "model-00005-of-00005.safetensors",223 "encoder.blocks.20.mlp_ln.bias": "model-00005-of-00005.safetensors",224 "encoder.blocks.20.mlp_ln.weight": "model-00005-of-00005.safetensors",225 "encoder.blocks.21.attn.key.weight": "model-00005-of-00005.safetensors",226 "encoder.blocks.21.attn.out.bias": "model-00005-of-00005.safetensors",227 "encoder.blocks.21.attn.out.weight": "model-00005-of-00005.safetensors",228 "encoder.blocks.21.attn.query.bias": "model-00005-of-00005.safetensors",229 "encoder.blocks.21.attn.query.weight": "model-00005-of-00005.safetensors",230 "encoder.blocks.21.attn.value.bias": "model-00005-of-00005.safetensors",231 "encoder.blocks.21.attn.value.weight": "model-00005-of-00005.safetensors",232 "encoder.blocks.21.attn_ln.bias": "model-00005-of-00005.safetensors",233 "encoder.blocks.21.attn_ln.weight": "model-00005-of-00005.safetensors",234 "encoder.blocks.21.mlp.0.bias": "model-00005-of-00005.safetensors",235 "encoder.blocks.21.mlp.0.weight": "model-00005-of-00005.safetensors",236 "encoder.blocks.21.mlp.2.bias": "model-00005-of-00005.safetensors",237 "encoder.blocks.21.mlp.2.weight": "model-00005-of-00005.safetensors",238 "encoder.blocks.21.mlp_ln.bias": "model-00005-of-00005.safetensors",239 "encoder.blocks.21.mlp_ln.weight": "model-00005-of-00005.safetensors",240 "encoder.blocks.22.attn.key.weight": "model-00005-of-00005.safetensors",241 "encoder.blocks.22.attn.out.bias": "model-00005-of-00005.safetensors",242 "encoder.blocks.22.attn.out.weight": "model-00005-of-00005.safetensors",243 "encoder.blocks.22.attn.query.bias": "model-00005-of-00005.safetensors",244 "encoder.blocks.22.attn.query.weight": "model-00005-of-00005.safetensors",245 "encoder.blocks.22.attn.value.bias": "model-00005-of-00005.safetensors",246 "encoder.blocks.22.attn.value.weight": "model-00005-of-00005.safetensors",247 "encoder.blocks.22.attn_ln.bias": "model-00005-of-00005.safetensors",248 "encoder.blocks.22.attn_ln.weight": "model-00005-of-00005.safetensors",249 "encoder.blocks.22.mlp.0.bias": "model-00005-of-00005.safetensors",250 "encoder.blocks.22.mlp.0.weight": "model-00005-of-00005.safetensors",251 "encoder.blocks.22.mlp.2.bias": "model-00005-of-00005.safetensors",252 "encoder.blocks.22.mlp.2.weight": "model-00005-of-00005.safetensors",253 "encoder.blocks.22.mlp_ln.bias": "model-00005-of-00005.safetensors",254 "encoder.blocks.22.mlp_ln.weight": "model-00005-of-00005.safetensors",255 "encoder.blocks.23.attn.key.weight": "model-00005-of-00005.safetensors",256 "encoder.blocks.23.attn.out.bias": "model-00005-of-00005.safetensors",257 "encoder.blocks.23.attn.out.weight": "model-00005-of-00005.safetensors",258 "encoder.blocks.23.attn.query.bias": "model-00005-of-00005.safetensors",259 "encoder.blocks.23.attn.query.weight": "model-00005-of-00005.safetensors",260 "encoder.blocks.23.attn.value.bias": "model-00005-of-00005.safetensors",261 "encoder.blocks.23.attn.value.weight": "model-00005-of-00005.safetensors",262 "encoder.blocks.23.attn_ln.bias": "model-00005-of-00005.safetensors",263 "encoder.blocks.23.attn_ln.weight": "model-00005-of-00005.safetensors",264 "encoder.blocks.23.mlp.0.bias": "model-00005-of-00005.safetensors",265 "encoder.blocks.23.mlp.0.weight": "model-00005-of-00005.safetensors",266 "encoder.blocks.23.mlp.2.bias": "model-00005-of-00005.safetensors",267 "encoder.blocks.23.mlp.2.weight": "model-00005-of-00005.safetensors",268 "encoder.blocks.23.mlp_ln.bias": "model-00005-of-00005.safetensors",269 "encoder.blocks.23.mlp_ln.weight": "model-00005-of-00005.safetensors",270 "encoder.blocks.24.attn.key.weight": "model-00005-of-00005.safetensors",271 "encoder.blocks.24.attn.out.bias": "model-00005-of-00005.safetensors",272 "encoder.blocks.24.attn.out.weight": "model-00005-of-00005.safetensors",273 "encoder.blocks.24.attn.query.bias": "model-00005-of-00005.safetensors",274 "encoder.blocks.24.attn.query.weight": "model-00005-of-00005.safetensors",275 "encoder.blocks.24.attn.value.bias": "model-00005-of-00005.safetensors",276 "encoder.blocks.24.attn.value.weight": "model-00005-of-00005.safetensors",277 "encoder.blocks.24.attn_ln.bias": "model-00005-of-00005.safetensors",278 "encoder.blocks.24.attn_ln.weight": "model-00005-of-00005.safetensors",279 "encoder.blocks.24.mlp.0.bias": "model-00005-of-00005.safetensors",280 "encoder.blocks.24.mlp.0.weight": "model-00005-of-00005.safetensors",281 "encoder.blocks.24.mlp.2.bias": "model-00005-of-00005.safetensors",282 "encoder.blocks.24.mlp.2.weight": "model-00005-of-00005.safetensors",283 "encoder.blocks.24.mlp_ln.bias": "model-00005-of-00005.safetensors",284 "encoder.blocks.24.mlp_ln.weight": "model-00005-of-00005.safetensors",285 "encoder.blocks.25.attn.key.weight": "model-00005-of-00005.safetensors",286 "encoder.blocks.25.attn.out.bias": "model-00005-of-00005.safetensors",287 "encoder.blocks.25.attn.out.weight": "model-00005-of-00005.safetensors",288 "encoder.blocks.25.attn.query.bias": "model-00005-of-00005.safetensors",289 "encoder.blocks.25.attn.query.weight": "model-00005-of-00005.safetensors",290 "encoder.blocks.25.attn.value.bias": "model-00005-of-00005.safetensors",291 "encoder.blocks.25.attn.value.weight": "model-00005-of-00005.safetensors",292 "encoder.blocks.25.attn_ln.bias": "model-00005-of-00005.safetensors",293 "encoder.blocks.25.attn_ln.weight": "model-00005-of-00005.safetensors",294 "encoder.blocks.25.mlp.0.bias": "model-00005-of-00005.safetensors",295 "encoder.blocks.25.mlp.0.weight": "model-00005-of-00005.safetensors",296 "encoder.blocks.25.mlp.2.bias": "model-00005-of-00005.safetensors",297 "encoder.blocks.25.mlp.2.weight": "model-00005-of-00005.safetensors",298 "encoder.blocks.25.mlp_ln.bias": "model-00005-of-00005.safetensors",299 "encoder.blocks.25.mlp_ln.weight": "model-00005-of-00005.safetensors",300 "encoder.blocks.26.attn.key.weight": "model-00005-of-00005.safetensors",301 "encoder.blocks.26.attn.out.bias": "model-00005-of-00005.safetensors",302 "encoder.blocks.26.attn.out.weight": "model-00005-of-00005.safetensors",303 "encoder.blocks.26.attn.query.bias": "model-00005-of-00005.safetensors",304 "encoder.blocks.26.attn.query.weight": "model-00005-of-00005.safetensors",305 "encoder.blocks.26.attn.value.bias": "model-00005-of-00005.safetensors",306 "encoder.blocks.26.attn.value.weight": "model-00005-of-00005.safetensors",307 "encoder.blocks.26.attn_ln.bias": "model-00005-of-00005.safetensors",308 "encoder.blocks.26.attn_ln.weight": "model-00005-of-00005.safetensors",309 "encoder.blocks.26.mlp.0.bias": "model-00005-of-00005.safetensors",310 "encoder.blocks.26.mlp.0.weight": "model-00005-of-00005.safetensors",311 "encoder.blocks.26.mlp.2.bias": "model-00005-of-00005.safetensors",312 "encoder.blocks.26.mlp.2.weight": "model-00005-of-00005.safetensors",313 "encoder.blocks.26.mlp_ln.bias": "model-00005-of-00005.safetensors",314 "encoder.blocks.26.mlp_ln.weight": "model-00005-of-00005.safetensors",315 "encoder.blocks.27.attn.key.weight": "model-00005-of-00005.safetensors",316 "encoder.blocks.27.attn.out.bias": "model-00005-of-00005.safetensors",317 "encoder.blocks.27.attn.out.weight": "model-00005-of-00005.safetensors",318 "encoder.blocks.27.attn.query.bias": "model-00005-of-00005.safetensors",319 "encoder.blocks.27.attn.query.weight": "model-00005-of-00005.safetensors",320 "encoder.blocks.27.attn.value.bias": "model-00005-of-00005.safetensors",321 "encoder.blocks.27.attn.value.weight": "model-00005-of-00005.safetensors",322 "encoder.blocks.27.attn_ln.bias": "model-00005-of-00005.safetensors",323 "encoder.blocks.27.attn_ln.weight": "model-00005-of-00005.safetensors",324 "encoder.blocks.27.mlp.0.bias": "model-00005-of-00005.safetensors",325 "encoder.blocks.27.mlp.0.weight": "model-00005-of-00005.safetensors",326 "encoder.blocks.27.mlp.2.bias": "model-00005-of-00005.safetensors",327 "encoder.blocks.27.mlp.2.weight": "model-00005-of-00005.safetensors",328 "encoder.blocks.27.mlp_ln.bias": "model-00005-of-00005.safetensors",329 "encoder.blocks.27.mlp_ln.weight": "model-00005-of-00005.safetensors",330 "encoder.blocks.28.attn.key.weight": "model-00005-of-00005.safetensors",331 "encoder.blocks.28.attn.out.bias": "model-00005-of-00005.safetensors",332 "encoder.blocks.28.attn.out.weight": "model-00005-of-00005.safetensors",333 "encoder.blocks.28.attn.query.bias": "model-00005-of-00005.safetensors",334 "encoder.blocks.28.attn.query.weight": "model-00005-of-00005.safetensors",335 "encoder.blocks.28.attn.value.bias": "model-00005-of-00005.safetensors",336 "encoder.blocks.28.attn.value.weight": "model-00005-of-00005.safetensors",337 "encoder.blocks.28.attn_ln.bias": "model-00005-of-00005.safetensors",338 "encoder.blocks.28.attn_ln.weight": "model-00005-of-00005.safetensors",339 "encoder.blocks.28.mlp.0.bias": "model-00005-of-00005.safetensors",340 "encoder.blocks.28.mlp.0.weight": "model-00005-of-00005.safetensors",341 "encoder.blocks.28.mlp.2.bias": "model-00005-of-00005.safetensors",342 "encoder.blocks.28.mlp.2.weight": "model-00005-of-00005.safetensors",343 "encoder.blocks.28.mlp_ln.bias": "model-00005-of-00005.safetensors",344 "encoder.blocks.28.mlp_ln.weight": "model-00005-of-00005.safetensors",345 "encoder.blocks.29.attn.key.weight": "model-00005-of-00005.safetensors",346 "encoder.blocks.29.attn.out.bias": "model-00005-of-00005.safetensors",347 "encoder.blocks.29.attn.out.weight": "model-00005-of-00005.safetensors",348 "encoder.blocks.29.attn.query.bias": "model-00005-of-00005.safetensors",349 "encoder.blocks.29.attn.query.weight": "model-00005-of-00005.safetensors",350 "encoder.blocks.29.attn.value.bias": "model-00005-of-00005.safetensors",351 "encoder.blocks.29.attn.value.weight": "model-00005-of-00005.safetensors",352 "encoder.blocks.29.attn_ln.bias": "model-00005-of-00005.safetensors",353 "encoder.blocks.29.attn_ln.weight": "model-00005-of-00005.safetensors",354 "encoder.blocks.29.mlp.0.bias": "model-00005-of-00005.safetensors",355 "encoder.blocks.29.mlp.0.weight": "model-00005-of-00005.safetensors",356 "encoder.blocks.29.mlp.2.bias": "model-00005-of-00005.safetensors",357 "encoder.blocks.29.mlp.2.weight": "model-00005-of-00005.safetensors",358 "encoder.blocks.29.mlp_ln.bias": "model-00005-of-00005.safetensors",359 "encoder.blocks.29.mlp_ln.weight": "model-00005-of-00005.safetensors",360 "encoder.blocks.3.attn.key.weight": "model-00004-of-00005.safetensors",361 "encoder.blocks.3.attn.out.bias": "model-00004-of-00005.safetensors",362 "encoder.blocks.3.attn.out.weight": "model-00004-of-00005.safetensors",363 "encoder.blocks.3.attn.query.bias": "model-00004-of-00005.safetensors",364 "encoder.blocks.3.attn.query.weight": "model-00004-of-00005.safetensors",365 "encoder.blocks.3.attn.value.bias": "model-00004-of-00005.safetensors",366 "encoder.blocks.3.attn.value.weight": "model-00004-of-00005.safetensors",367 "encoder.blocks.3.attn_ln.bias": "model-00004-of-00005.safetensors",368 "encoder.blocks.3.attn_ln.weight": "model-00004-of-00005.safetensors",369 "encoder.blocks.3.mlp.0.bias": "model-00004-of-00005.safetensors",370 "encoder.blocks.3.mlp.0.weight": "model-00004-of-00005.safetensors",371 "encoder.blocks.3.mlp.2.bias": "model-00004-of-00005.safetensors",372 "encoder.blocks.3.mlp.2.weight": "model-00004-of-00005.safetensors",373 "encoder.blocks.3.mlp_ln.bias": "model-00004-of-00005.safetensors",374 "encoder.blocks.3.mlp_ln.weight": "model-00004-of-00005.safetensors",375 "encoder.blocks.30.attn.key.weight": "model-00005-of-00005.safetensors",376 "encoder.blocks.30.attn.out.bias": "model-00005-of-00005.safetensors",377 "encoder.blocks.30.attn.out.weight": "model-00005-of-00005.safetensors",378 "encoder.blocks.30.attn.query.bias": "model-00005-of-00005.safetensors",379 "encoder.blocks.30.attn.query.weight": "model-00005-of-00005.safetensors",380 "encoder.blocks.30.attn.value.bias": "model-00005-of-00005.safetensors",381 "encoder.blocks.30.attn.value.weight": "model-00005-of-00005.safetensors",382 "encoder.blocks.30.attn_ln.bias": "model-00005-of-00005.safetensors",383 "encoder.blocks.30.attn_ln.weight": "model-00005-of-00005.safetensors",384 "encoder.blocks.30.mlp.0.bias": "model-00005-of-00005.safetensors",385 "encoder.blocks.30.mlp.0.weight": "model-00005-of-00005.safetensors",386 "encoder.blocks.30.mlp.2.bias": "model-00005-of-00005.safetensors",387 "encoder.blocks.30.mlp.2.weight": "model-00005-of-00005.safetensors",388 "encoder.blocks.30.mlp_ln.bias": "model-00005-of-00005.safetensors",389 "encoder.blocks.30.mlp_ln.weight": "model-00005-of-00005.safetensors",390 "encoder.blocks.31.attn.key.weight": "model-00005-of-00005.safetensors",391 "encoder.blocks.31.attn.out.bias": "model-00005-of-00005.safetensors",392 "encoder.blocks.31.attn.out.weight": "model-00005-of-00005.safetensors",393 "encoder.blocks.31.attn.query.bias": "model-00005-of-00005.safetensors",394 "encoder.blocks.31.attn.query.weight": "model-00005-of-00005.safetensors",395 "encoder.blocks.31.attn.value.bias": "model-00005-of-00005.safetensors",396 "encoder.blocks.31.attn.value.weight": "model-00005-of-00005.safetensors",397 "encoder.blocks.31.attn_ln.bias": "model-00005-of-00005.safetensors",398 "encoder.blocks.31.attn_ln.weight": "model-00005-of-00005.safetensors",399 "encoder.blocks.31.mlp.0.bias": "model-00005-of-00005.safetensors",400 "encoder.blocks.31.mlp.0.weight": "model-00005-of-00005.safetensors",401 "encoder.blocks.31.mlp.2.bias": "model-00005-of-00005.safetensors",402 "encoder.blocks.31.mlp.2.weight": "model-00005-of-00005.safetensors",403 "encoder.blocks.31.mlp_ln.bias": "model-00005-of-00005.safetensors",404 "encoder.blocks.31.mlp_ln.weight": "model-00005-of-00005.safetensors",405 "encoder.blocks.4.attn.key.weight": "model-00004-of-00005.safetensors",406 "encoder.blocks.4.attn.out.bias": "model-00004-of-00005.safetensors",407 "encoder.blocks.4.attn.out.weight": "model-00004-of-00005.safetensors",408 "encoder.blocks.4.attn.query.bias": "model-00004-of-00005.safetensors",409 "encoder.blocks.4.attn.query.weight": "model-00004-of-00005.safetensors",410 "encoder.blocks.4.attn.value.bias": "model-00004-of-00005.safetensors",411 "encoder.blocks.4.attn.value.weight": "model-00004-of-00005.safetensors",412 "encoder.blocks.4.attn_ln.bias": "model-00004-of-00005.safetensors",413 "encoder.blocks.4.attn_ln.weight": "model-00004-of-00005.safetensors",414 "encoder.blocks.4.mlp.0.bias": "model-00004-of-00005.safetensors",415 "encoder.blocks.4.mlp.0.weight": "model-00004-of-00005.safetensors",416 "encoder.blocks.4.mlp.2.bias": "model-00004-of-00005.safetensors",417 "encoder.blocks.4.mlp.2.weight": "model-00004-of-00005.safetensors",418 "encoder.blocks.4.mlp_ln.bias": "model-00004-of-00005.safetensors",419 "encoder.blocks.4.mlp_ln.weight": "model-00004-of-00005.safetensors",420 "encoder.blocks.5.attn.key.weight": "model-00004-of-00005.safetensors",421 "encoder.blocks.5.attn.out.bias": "model-00004-of-00005.safetensors",422 "encoder.blocks.5.attn.out.weight": "model-00004-of-00005.safetensors",423 "encoder.blocks.5.attn.query.bias": "model-00004-of-00005.safetensors",424 "encoder.blocks.5.attn.query.weight": "model-00004-of-00005.safetensors",425 "encoder.blocks.5.attn.value.bias": "model-00004-of-00005.safetensors",426 "encoder.blocks.5.attn.value.weight": "model-00004-of-00005.safetensors",427 "encoder.blocks.5.attn_ln.bias": "model-00004-of-00005.safetensors",428 "encoder.blocks.5.attn_ln.weight": "model-00004-of-00005.safetensors",429 "encoder.blocks.5.mlp.0.bias": "model-00004-of-00005.safetensors",430 "encoder.blocks.5.mlp.0.weight": "model-00004-of-00005.safetensors",431 "encoder.blocks.5.mlp.2.bias": "model-00004-of-00005.safetensors",432 "encoder.blocks.5.mlp.2.weight": "model-00004-of-00005.safetensors",433 "encoder.blocks.5.mlp_ln.bias": "model-00004-of-00005.safetensors",434 "encoder.blocks.5.mlp_ln.weight": "model-00004-of-00005.safetensors",435 "encoder.blocks.6.attn.key.weight": "model-00004-of-00005.safetensors",436 "encoder.blocks.6.attn.out.bias": "model-00004-of-00005.safetensors",437 "encoder.blocks.6.attn.out.weight": "model-00004-of-00005.safetensors",438 "encoder.blocks.6.attn.query.bias": "model-00004-of-00005.safetensors",439 "encoder.blocks.6.attn.query.weight": "model-00004-of-00005.safetensors",440 "encoder.blocks.6.attn.value.bias": "model-00004-of-00005.safetensors",441 "encoder.blocks.6.attn.value.weight": "model-00004-of-00005.safetensors",442 "encoder.blocks.6.attn_ln.bias": "model-00004-of-00005.safetensors",443 "encoder.blocks.6.attn_ln.weight": "model-00004-of-00005.safetensors",444 "encoder.blocks.6.mlp.0.bias": "model-00004-of-00005.safetensors",445 "encoder.blocks.6.mlp.0.weight": "model-00004-of-00005.safetensors",446 "encoder.blocks.6.mlp.2.bias": "model-00004-of-00005.safetensors",447 "encoder.blocks.6.mlp.2.weight": "model-00004-of-00005.safetensors",448 "encoder.blocks.6.mlp_ln.bias": "model-00004-of-00005.safetensors",449 "encoder.blocks.6.mlp_ln.weight": "model-00004-of-00005.safetensors",450 "encoder.blocks.7.attn.key.weight": "model-00004-of-00005.safetensors",451 "encoder.blocks.7.attn.out.bias": "model-00004-of-00005.safetensors",452 "encoder.blocks.7.attn.out.weight": "model-00004-of-00005.safetensors",453 "encoder.blocks.7.attn.query.bias": "model-00004-of-00005.safetensors",454 "encoder.blocks.7.attn.query.weight": "model-00004-of-00005.safetensors",455 "encoder.blocks.7.attn.value.bias": "model-00004-of-00005.safetensors",456 "encoder.blocks.7.attn.value.weight": "model-00004-of-00005.safetensors",457 "encoder.blocks.7.attn_ln.bias": "model-00004-of-00005.safetensors",458 "encoder.blocks.7.attn_ln.weight": "model-00004-of-00005.safetensors",459 "encoder.blocks.7.mlp.0.bias": "model-00004-of-00005.safetensors",460 "encoder.blocks.7.mlp.0.weight": "model-00004-of-00005.safetensors",461 "encoder.blocks.7.mlp.2.bias": "model-00004-of-00005.safetensors",462 "encoder.blocks.7.mlp.2.weight": "model-00004-of-00005.safetensors",463 "encoder.blocks.7.mlp_ln.bias": "model-00004-of-00005.safetensors",464 "encoder.blocks.7.mlp_ln.weight": "model-00004-of-00005.safetensors",465 "encoder.blocks.8.attn.key.weight": "model-00004-of-00005.safetensors",466 "encoder.blocks.8.attn.out.bias": "model-00004-of-00005.safetensors",467 "encoder.blocks.8.attn.out.weight": "model-00004-of-00005.safetensors",468 "encoder.blocks.8.attn.query.bias": "model-00004-of-00005.safetensors",469 "encoder.blocks.8.attn.query.weight": "model-00004-of-00005.safetensors",470 "encoder.blocks.8.attn.value.bias": "model-00004-of-00005.safetensors",471 "encoder.blocks.8.attn.value.weight": "model-00004-of-00005.safetensors",472 "encoder.blocks.8.attn_ln.bias": "model-00004-of-00005.safetensors",473 "encoder.blocks.8.attn_ln.weight": "model-00004-of-00005.safetensors",474 "encoder.blocks.8.mlp.0.bias": "model-00004-of-00005.safetensors",475 "encoder.blocks.8.mlp.0.weight": "model-00004-of-00005.safetensors",476 "encoder.blocks.8.mlp.2.bias": "model-00004-of-00005.safetensors",477 "encoder.blocks.8.mlp.2.weight": "model-00004-of-00005.safetensors",478 "encoder.blocks.8.mlp_ln.bias": "model-00004-of-00005.safetensors",479 "encoder.blocks.8.mlp_ln.weight": "model-00004-of-00005.safetensors",480 "encoder.blocks.9.attn.key.weight": "model-00004-of-00005.safetensors",481 "encoder.blocks.9.attn.out.bias": "model-00004-of-00005.safetensors",482 "encoder.blocks.9.attn.out.weight": "model-00004-of-00005.safetensors",483 "encoder.blocks.9.attn.query.bias": "model-00004-of-00005.safetensors",484 "encoder.blocks.9.attn.query.weight": "model-00004-of-00005.safetensors",485 "encoder.blocks.9.attn.value.bias": "model-00004-of-00005.safetensors",486 "encoder.blocks.9.attn.value.weight": "model-00004-of-00005.safetensors",487 "encoder.blocks.9.attn_ln.bias": "model-00004-of-00005.safetensors",488 "encoder.blocks.9.attn_ln.weight": "model-00004-of-00005.safetensors",489 "encoder.blocks.9.mlp.0.bias": "model-00004-of-00005.safetensors",490 "encoder.blocks.9.mlp.0.weight": "model-00004-of-00005.safetensors",491 "encoder.blocks.9.mlp.2.bias": "model-00004-of-00005.safetensors",492 "encoder.blocks.9.mlp.2.weight": "model-00004-of-00005.safetensors",493 "encoder.blocks.9.mlp_ln.bias": "model-00004-of-00005.safetensors",494 "encoder.blocks.9.mlp_ln.weight": "model-00004-of-00005.safetensors",495 "encoder.conv1.bias": "model-00004-of-00005.safetensors",496 "encoder.conv1.weight": "model-00004-of-00005.safetensors",497 "encoder.conv2.bias": "model-00004-of-00005.safetensors",498 "encoder.conv2.weight": "model-00004-of-00005.safetensors",499 "encoder.positional_embedding.weight": "model-00004-of-00005.safetensors",500 "lm_head.weight": "model-00005-of-00005.safetensors",501 "model.embed_tokens.weight": "model-00001-of-00005.safetensors",502 "model.layers.0.input_layernorm.weight": "model-00001-of-00005.safetensors",503 "model.layers.0.mlp.down_proj.input_global_scale": "model-00001-of-00005.safetensors",504 "model.layers.0.mlp.down_proj.weight_global_scale": "model-00001-of-00005.safetensors",505 "model.layers.0.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors",506 "model.layers.0.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors",507 "model.layers.0.mlp.gate_proj.input_global_scale": "model-00001-of-00005.safetensors",508 "model.layers.0.mlp.gate_proj.weight_global_scale": "model-00001-of-00005.safetensors",509 "model.layers.0.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors",510 "model.layers.0.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors",511 "model.layers.0.mlp.up_proj.input_global_scale": "model-00001-of-00005.safetensors",512 "model.layers.0.mlp.up_proj.weight_global_scale": "model-00001-of-00005.safetensors",513 "model.layers.0.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors",514 "model.layers.0.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors",515 "model.layers.0.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",516 "model.layers.0.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",517 "model.layers.0.self_attn.k_proj.input_global_scale": "model-00001-of-00005.safetensors",518 "model.layers.0.self_attn.k_proj.weight_global_scale": "model-00001-of-00005.safetensors",519 "model.layers.0.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors",520 "model.layers.0.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors",521 "model.layers.0.self_attn.o_proj.input_global_scale": "model-00001-of-00005.safetensors",522 "model.layers.0.self_attn.o_proj.weight_global_scale": "model-00001-of-00005.safetensors",523 "model.layers.0.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors",524 "model.layers.0.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors",525 "model.layers.0.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",526 "model.layers.0.self_attn.q_proj.input_global_scale": "model-00001-of-00005.safetensors",527 "model.layers.0.self_attn.q_proj.weight_global_scale": "model-00001-of-00005.safetensors",528 "model.layers.0.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors",529 "model.layers.0.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors",530 "model.layers.0.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",531 "model.layers.0.self_attn.v_proj.input_global_scale": "model-00001-of-00005.safetensors",532 "model.layers.0.self_attn.v_proj.weight_global_scale": "model-00001-of-00005.safetensors",533 "model.layers.0.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors",534 "model.layers.0.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors",535 "model.layers.1.input_layernorm.weight": "model-00001-of-00005.safetensors",536 "model.layers.1.mlp.down_proj.input_global_scale": "model-00001-of-00005.safetensors",537 "model.layers.1.mlp.down_proj.weight_global_scale": "model-00001-of-00005.safetensors",538 "model.layers.1.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors",539 "model.layers.1.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors",540 "model.layers.1.mlp.gate_proj.input_global_scale": "model-00001-of-00005.safetensors",541 "model.layers.1.mlp.gate_proj.weight_global_scale": "model-00001-of-00005.safetensors",542 "model.layers.1.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors",543 "model.layers.1.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors",544 "model.layers.1.mlp.up_proj.input_global_scale": "model-00001-of-00005.safetensors",545 "model.layers.1.mlp.up_proj.weight_global_scale": "model-00001-of-00005.safetensors",546 "model.layers.1.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors",547 "model.layers.1.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors",548 "model.layers.1.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",549 "model.layers.1.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",550 "model.layers.1.self_attn.k_proj.input_global_scale": "model-00001-of-00005.safetensors",551 "model.layers.1.self_attn.k_proj.weight_global_scale": "model-00001-of-00005.safetensors",552 "model.layers.1.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors",553 "model.layers.1.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors",554 "model.layers.1.self_attn.o_proj.input_global_scale": "model-00001-of-00005.safetensors",555 "model.layers.1.self_attn.o_proj.weight_global_scale": "model-00001-of-00005.safetensors",556 "model.layers.1.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors",557 "model.layers.1.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors",558 "model.layers.1.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",559 "model.layers.1.self_attn.q_proj.input_global_scale": "model-00001-of-00005.safetensors",560 "model.layers.1.self_attn.q_proj.weight_global_scale": "model-00001-of-00005.safetensors",561 "model.layers.1.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors",562 "model.layers.1.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors",563 "model.layers.1.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",564 "model.layers.1.self_attn.v_proj.input_global_scale": "model-00001-of-00005.safetensors",565 "model.layers.1.self_attn.v_proj.weight_global_scale": "model-00001-of-00005.safetensors",566 "model.layers.1.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors",567 "model.layers.1.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors",568 "model.layers.10.input_layernorm.weight": "model-00001-of-00005.safetensors",569 "model.layers.10.mlp.down_proj.input_global_scale": "model-00001-of-00005.safetensors",570 "model.layers.10.mlp.down_proj.weight_global_scale": "model-00001-of-00005.safetensors",571 "model.layers.10.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors",572 "model.layers.10.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors",573 "model.layers.10.mlp.gate_proj.input_global_scale": "model-00001-of-00005.safetensors",574 "model.layers.10.mlp.gate_proj.weight_global_scale": "model-00001-of-00005.safetensors",575 "model.layers.10.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors",576 "model.layers.10.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors",577 "model.layers.10.mlp.up_proj.input_global_scale": "model-00001-of-00005.safetensors",578 "model.layers.10.mlp.up_proj.weight_global_scale": "model-00001-of-00005.safetensors",579 "model.layers.10.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors",580 "model.layers.10.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors",581 "model.layers.10.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",582 "model.layers.10.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",583 "model.layers.10.self_attn.k_proj.input_global_scale": "model-00001-of-00005.safetensors",584 "model.layers.10.self_attn.k_proj.weight_global_scale": "model-00001-of-00005.safetensors",585 "model.layers.10.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors",586 "model.layers.10.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors",587 "model.layers.10.self_attn.o_proj.input_global_scale": "model-00001-of-00005.safetensors",588 "model.layers.10.self_attn.o_proj.weight_global_scale": "model-00001-of-00005.safetensors",589 "model.layers.10.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors",590 "model.layers.10.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors",591 "model.layers.10.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",592 "model.layers.10.self_attn.q_proj.input_global_scale": "model-00001-of-00005.safetensors",593 "model.layers.10.self_attn.q_proj.weight_global_scale": "model-00001-of-00005.safetensors",594 "model.layers.10.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors",595 "model.layers.10.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors",596 "model.layers.10.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",597 "model.layers.10.self_attn.v_proj.input_global_scale": "model-00001-of-00005.safetensors",598 "model.layers.10.self_attn.v_proj.weight_global_scale": "model-00001-of-00005.safetensors",599 "model.layers.10.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors",600 "model.layers.10.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors",601 "model.layers.11.input_layernorm.weight": "model-00001-of-00005.safetensors",602 "model.layers.11.mlp.down_proj.input_global_scale": "model-00001-of-00005.safetensors",603 "model.layers.11.mlp.down_proj.weight_global_scale": "model-00001-of-00005.safetensors",604 "model.layers.11.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors",605 "model.layers.11.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors",606 "model.layers.11.mlp.gate_proj.input_global_scale": "model-00001-of-00005.safetensors",607 "model.layers.11.mlp.gate_proj.weight_global_scale": "model-00001-of-00005.safetensors",608 "model.layers.11.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors",609 "model.layers.11.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors",610 "model.layers.11.mlp.up_proj.input_global_scale": "model-00001-of-00005.safetensors",611 "model.layers.11.mlp.up_proj.weight_global_scale": "model-00001-of-00005.safetensors",612 "model.layers.11.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors",613 "model.layers.11.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors",614 "model.layers.11.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",615 "model.layers.11.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",616 "model.layers.11.self_attn.k_proj.input_global_scale": "model-00001-of-00005.safetensors",617 "model.layers.11.self_attn.k_proj.weight_global_scale": "model-00001-of-00005.safetensors",618 "model.layers.11.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors",619 "model.layers.11.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors",620 "model.layers.11.self_attn.o_proj.input_global_scale": "model-00001-of-00005.safetensors",621 "model.layers.11.self_attn.o_proj.weight_global_scale": "model-00001-of-00005.safetensors",622 "model.layers.11.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors",623 "model.layers.11.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors",624 "model.layers.11.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",625 "model.layers.11.self_attn.q_proj.input_global_scale": "model-00001-of-00005.safetensors",626 "model.layers.11.self_attn.q_proj.weight_global_scale": "model-00001-of-00005.safetensors",627 "model.layers.11.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors",628 "model.layers.11.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors",629 "model.layers.11.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",630 "model.layers.11.self_attn.v_proj.input_global_scale": "model-00001-of-00005.safetensors",631 "model.layers.11.self_attn.v_proj.weight_global_scale": "model-00001-of-00005.safetensors",632 "model.layers.11.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors",633 "model.layers.11.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors",634 "model.layers.12.input_layernorm.weight": "model-00002-of-00005.safetensors",635 "model.layers.12.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",636 "model.layers.12.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",637 "model.layers.12.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",638 "model.layers.12.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",639 "model.layers.12.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",640 "model.layers.12.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",641 "model.layers.12.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",642 "model.layers.12.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",643 "model.layers.12.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",644 "model.layers.12.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",645 "model.layers.12.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",646 "model.layers.12.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",647 "model.layers.12.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",648 "model.layers.12.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",649 "model.layers.12.self_attn.k_proj.input_global_scale": "model-00001-of-00005.safetensors",650 "model.layers.12.self_attn.k_proj.weight_global_scale": "model-00001-of-00005.safetensors",651 "model.layers.12.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors",652 "model.layers.12.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors",653 "model.layers.12.self_attn.o_proj.input_global_scale": "model-00001-of-00005.safetensors",654 "model.layers.12.self_attn.o_proj.weight_global_scale": "model-00001-of-00005.safetensors",655 "model.layers.12.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors",656 "model.layers.12.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors",657 "model.layers.12.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",658 "model.layers.12.self_attn.q_proj.input_global_scale": "model-00001-of-00005.safetensors",659 "model.layers.12.self_attn.q_proj.weight_global_scale": "model-00001-of-00005.safetensors",660 "model.layers.12.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors",661 "model.layers.12.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors",662 "model.layers.12.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",663 "model.layers.12.self_attn.v_proj.input_global_scale": "model-00001-of-00005.safetensors",664 "model.layers.12.self_attn.v_proj.weight_global_scale": "model-00001-of-00005.safetensors",665 "model.layers.12.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors",666 "model.layers.12.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors",667 "model.layers.13.input_layernorm.weight": "model-00002-of-00005.safetensors",668 "model.layers.13.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",669 "model.layers.13.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",670 "model.layers.13.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",671 "model.layers.13.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",672 "model.layers.13.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",673 "model.layers.13.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",674 "model.layers.13.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",675 "model.layers.13.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",676 "model.layers.13.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",677 "model.layers.13.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",678 "model.layers.13.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",679 "model.layers.13.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",680 "model.layers.13.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",681 "model.layers.13.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",682 "model.layers.13.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",683 "model.layers.13.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",684 "model.layers.13.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",685 "model.layers.13.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",686 "model.layers.13.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",687 "model.layers.13.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",688 "model.layers.13.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",689 "model.layers.13.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",690 "model.layers.13.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",691 "model.layers.13.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",692 "model.layers.13.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",693 "model.layers.13.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",694 "model.layers.13.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",695 "model.layers.13.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",696 "model.layers.13.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",697 "model.layers.13.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",698 "model.layers.13.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",699 "model.layers.13.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",700 "model.layers.14.input_layernorm.weight": "model-00002-of-00005.safetensors",701 "model.layers.14.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",702 "model.layers.14.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",703 "model.layers.14.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",704 "model.layers.14.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",705 "model.layers.14.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",706 "model.layers.14.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",707 "model.layers.14.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",708 "model.layers.14.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",709 "model.layers.14.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",710 "model.layers.14.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",711 "model.layers.14.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",712 "model.layers.14.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",713 "model.layers.14.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",714 "model.layers.14.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",715 "model.layers.14.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",716 "model.layers.14.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",717 "model.layers.14.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",718 "model.layers.14.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",719 "model.layers.14.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",720 "model.layers.14.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",721 "model.layers.14.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",722 "model.layers.14.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",723 "model.layers.14.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",724 "model.layers.14.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",725 "model.layers.14.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",726 "model.layers.14.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",727 "model.layers.14.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",728 "model.layers.14.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",729 "model.layers.14.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",730 "model.layers.14.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",731 "model.layers.14.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",732 "model.layers.14.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",733 "model.layers.15.input_layernorm.weight": "model-00002-of-00005.safetensors",734 "model.layers.15.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",735 "model.layers.15.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",736 "model.layers.15.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",737 "model.layers.15.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",738 "model.layers.15.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",739 "model.layers.15.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",740 "model.layers.15.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",741 "model.layers.15.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",742 "model.layers.15.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",743 "model.layers.15.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",744 "model.layers.15.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",745 "model.layers.15.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",746 "model.layers.15.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",747 "model.layers.15.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",748 "model.layers.15.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",749 "model.layers.15.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",750 "model.layers.15.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",751 "model.layers.15.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",752 "model.layers.15.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",753 "model.layers.15.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",754 "model.layers.15.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",755 "model.layers.15.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",756 "model.layers.15.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",757 "model.layers.15.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",758 "model.layers.15.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",759 "model.layers.15.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",760 "model.layers.15.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",761 "model.layers.15.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",762 "model.layers.15.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",763 "model.layers.15.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",764 "model.layers.15.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",765 "model.layers.15.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",766 "model.layers.16.input_layernorm.weight": "model-00002-of-00005.safetensors",767 "model.layers.16.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",768 "model.layers.16.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",769 "model.layers.16.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",770 "model.layers.16.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",771 "model.layers.16.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",772 "model.layers.16.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",773 "model.layers.16.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",774 "model.layers.16.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",775 "model.layers.16.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",776 "model.layers.16.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",777 "model.layers.16.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",778 "model.layers.16.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",779 "model.layers.16.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",780 "model.layers.16.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",781 "model.layers.16.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",782 "model.layers.16.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",783 "model.layers.16.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",784 "model.layers.16.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",785 "model.layers.16.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",786 "model.layers.16.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",787 "model.layers.16.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",788 "model.layers.16.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",789 "model.layers.16.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",790 "model.layers.16.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",791 "model.layers.16.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",792 "model.layers.16.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",793 "model.layers.16.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",794 "model.layers.16.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",795 "model.layers.16.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",796 "model.layers.16.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",797 "model.layers.16.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",798 "model.layers.16.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",799 "model.layers.17.input_layernorm.weight": "model-00002-of-00005.safetensors",800 "model.layers.17.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",801 "model.layers.17.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",802 "model.layers.17.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",803 "model.layers.17.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",804 "model.layers.17.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",805 "model.layers.17.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",806 "model.layers.17.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",807 "model.layers.17.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",808 "model.layers.17.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",809 "model.layers.17.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",810 "model.layers.17.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",811 "model.layers.17.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",812 "model.layers.17.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",813 "model.layers.17.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",814 "model.layers.17.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",815 "model.layers.17.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",816 "model.layers.17.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",817 "model.layers.17.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",818 "model.layers.17.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",819 "model.layers.17.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",820 "model.layers.17.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",821 "model.layers.17.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",822 "model.layers.17.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",823 "model.layers.17.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",824 "model.layers.17.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",825 "model.layers.17.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",826 "model.layers.17.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",827 "model.layers.17.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",828 "model.layers.17.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",829 "model.layers.17.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",830 "model.layers.17.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",831 "model.layers.17.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",832 "model.layers.18.input_layernorm.weight": "model-00002-of-00005.safetensors",833 "model.layers.18.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",834 "model.layers.18.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",835 "model.layers.18.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",836 "model.layers.18.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",837 "model.layers.18.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",838 "model.layers.18.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",839 "model.layers.18.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",840 "model.layers.18.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",841 "model.layers.18.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",842 "model.layers.18.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",843 "model.layers.18.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",844 "model.layers.18.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",845 "model.layers.18.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",846 "model.layers.18.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",847 "model.layers.18.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",848 "model.layers.18.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",849 "model.layers.18.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",850 "model.layers.18.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",851 "model.layers.18.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",852 "model.layers.18.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",853 "model.layers.18.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",854 "model.layers.18.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",855 "model.layers.18.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",856 "model.layers.18.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",857 "model.layers.18.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",858 "model.layers.18.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",859 "model.layers.18.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",860 "model.layers.18.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",861 "model.layers.18.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",862 "model.layers.18.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",863 "model.layers.18.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",864 "model.layers.18.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",865 "model.layers.19.input_layernorm.weight": "model-00002-of-00005.safetensors",866 "model.layers.19.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",867 "model.layers.19.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",868 "model.layers.19.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",869 "model.layers.19.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",870 "model.layers.19.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",871 "model.layers.19.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",872 "model.layers.19.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",873 "model.layers.19.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",874 "model.layers.19.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",875 "model.layers.19.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",876 "model.layers.19.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",877 "model.layers.19.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",878 "model.layers.19.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",879 "model.layers.19.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",880 "model.layers.19.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",881 "model.layers.19.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",882 "model.layers.19.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",883 "model.layers.19.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",884 "model.layers.19.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",885 "model.layers.19.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",886 "model.layers.19.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",887 "model.layers.19.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",888 "model.layers.19.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",889 "model.layers.19.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",890 "model.layers.19.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",891 "model.layers.19.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",892 "model.layers.19.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",893 "model.layers.19.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",894 "model.layers.19.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",895 "model.layers.19.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",896 "model.layers.19.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",897 "model.layers.19.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",898 "model.layers.2.input_layernorm.weight": "model-00001-of-00005.safetensors",899 "model.layers.2.mlp.down_proj.input_global_scale": "model-00001-of-00005.safetensors",900 "model.layers.2.mlp.down_proj.weight_global_scale": "model-00001-of-00005.safetensors",901 "model.layers.2.mlp.down_proj.weight_packed": "model-00001-of-00005.safetensors",902 "model.layers.2.mlp.down_proj.weight_scale": "model-00001-of-00005.safetensors",903 "model.layers.2.mlp.gate_proj.input_global_scale": "model-00001-of-00005.safetensors",904 "model.layers.2.mlp.gate_proj.weight_global_scale": "model-00001-of-00005.safetensors",905 "model.layers.2.mlp.gate_proj.weight_packed": "model-00001-of-00005.safetensors",906 "model.layers.2.mlp.gate_proj.weight_scale": "model-00001-of-00005.safetensors",907 "model.layers.2.mlp.up_proj.input_global_scale": "model-00001-of-00005.safetensors",908 "model.layers.2.mlp.up_proj.weight_global_scale": "model-00001-of-00005.safetensors",909 "model.layers.2.mlp.up_proj.weight_packed": "model-00001-of-00005.safetensors",910 "model.layers.2.mlp.up_proj.weight_scale": "model-00001-of-00005.safetensors",911 "model.layers.2.post_attention_layernorm.weight": "model-00001-of-00005.safetensors",912 "model.layers.2.self_attn.k_proj.bias": "model-00001-of-00005.safetensors",913 "model.layers.2.self_attn.k_proj.input_global_scale": "model-00001-of-00005.safetensors",914 "model.layers.2.self_attn.k_proj.weight_global_scale": "model-00001-of-00005.safetensors",915 "model.layers.2.self_attn.k_proj.weight_packed": "model-00001-of-00005.safetensors",916 "model.layers.2.self_attn.k_proj.weight_scale": "model-00001-of-00005.safetensors",917 "model.layers.2.self_attn.o_proj.input_global_scale": "model-00001-of-00005.safetensors",918 "model.layers.2.self_attn.o_proj.weight_global_scale": "model-00001-of-00005.safetensors",919 "model.layers.2.self_attn.o_proj.weight_packed": "model-00001-of-00005.safetensors",920 "model.layers.2.self_attn.o_proj.weight_scale": "model-00001-of-00005.safetensors",921 "model.layers.2.self_attn.q_proj.bias": "model-00001-of-00005.safetensors",922 "model.layers.2.self_attn.q_proj.input_global_scale": "model-00001-of-00005.safetensors",923 "model.layers.2.self_attn.q_proj.weight_global_scale": "model-00001-of-00005.safetensors",924 "model.layers.2.self_attn.q_proj.weight_packed": "model-00001-of-00005.safetensors",925 "model.layers.2.self_attn.q_proj.weight_scale": "model-00001-of-00005.safetensors",926 "model.layers.2.self_attn.v_proj.bias": "model-00001-of-00005.safetensors",927 "model.layers.2.self_attn.v_proj.input_global_scale": "model-00001-of-00005.safetensors",928 "model.layers.2.self_attn.v_proj.weight_global_scale": "model-00001-of-00005.safetensors",929 "model.layers.2.self_attn.v_proj.weight_packed": "model-00001-of-00005.safetensors",930 "model.layers.2.self_attn.v_proj.weight_scale": "model-00001-of-00005.safetensors",931 "model.layers.20.input_layernorm.weight": "model-00002-of-00005.safetensors",932 "model.layers.20.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",933 "model.layers.20.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",934 "model.layers.20.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",935 "model.layers.20.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",936 "model.layers.20.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",937 "model.layers.20.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",938 "model.layers.20.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",939 "model.layers.20.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",940 "model.layers.20.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",941 "model.layers.20.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",942 "model.layers.20.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",943 "model.layers.20.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",944 "model.layers.20.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",945 "model.layers.20.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",946 "model.layers.20.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",947 "model.layers.20.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",948 "model.layers.20.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",949 "model.layers.20.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",950 "model.layers.20.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",951 "model.layers.20.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",952 "model.layers.20.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",953 "model.layers.20.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",954 "model.layers.20.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",955 "model.layers.20.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",956 "model.layers.20.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",957 "model.layers.20.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",958 "model.layers.20.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",959 "model.layers.20.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",960 "model.layers.20.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",961 "model.layers.20.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",962 "model.layers.20.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",963 "model.layers.20.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",964 "model.layers.21.input_layernorm.weight": "model-00002-of-00005.safetensors",965 "model.layers.21.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",966 "model.layers.21.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",967 "model.layers.21.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",968 "model.layers.21.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",969 "model.layers.21.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",970 "model.layers.21.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",971 "model.layers.21.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",972 "model.layers.21.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",973 "model.layers.21.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",974 "model.layers.21.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",975 "model.layers.21.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",976 "model.layers.21.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",977 "model.layers.21.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",978 "model.layers.21.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",979 "model.layers.21.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",980 "model.layers.21.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",981 "model.layers.21.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",982 "model.layers.21.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",983 "model.layers.21.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",984 "model.layers.21.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",985 "model.layers.21.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",986 "model.layers.21.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",987 "model.layers.21.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",988 "model.layers.21.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",989 "model.layers.21.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",990 "model.layers.21.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",991 "model.layers.21.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",992 "model.layers.21.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",993 "model.layers.21.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",994 "model.layers.21.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",995 "model.layers.21.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",996 "model.layers.21.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",997 "model.layers.22.input_layernorm.weight": "model-00002-of-00005.safetensors",998 "model.layers.22.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",999 "model.layers.22.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1000 "model.layers.22.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1001 "model.layers.22.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1002 "model.layers.22.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",1003 "model.layers.22.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",1004 "model.layers.22.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",1005 "model.layers.22.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",1006 "model.layers.22.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",1007 "model.layers.22.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",1008 "model.layers.22.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",1009 "model.layers.22.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",1010 "model.layers.22.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",1011 "model.layers.22.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",1012 "model.layers.22.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",1013 "model.layers.22.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",1014 "model.layers.22.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",1015 "model.layers.22.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",1016 "model.layers.22.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",1017 "model.layers.22.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",1018 "model.layers.22.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",1019 "model.layers.22.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",1020 "model.layers.22.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",1021 "model.layers.22.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",1022 "model.layers.22.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",1023 "model.layers.22.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",1024 "model.layers.22.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",1025 "model.layers.22.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",1026 "model.layers.22.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",1027 "model.layers.22.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",1028 "model.layers.22.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",1029 "model.layers.22.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",1030 "model.layers.23.input_layernorm.weight": "model-00002-of-00005.safetensors",1031 "model.layers.23.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",1032 "model.layers.23.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1033 "model.layers.23.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1034 "model.layers.23.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1035 "model.layers.23.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",1036 "model.layers.23.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",1037 "model.layers.23.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",1038 "model.layers.23.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",1039 "model.layers.23.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",1040 "model.layers.23.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",1041 "model.layers.23.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",1042 "model.layers.23.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",1043 "model.layers.23.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",1044 "model.layers.23.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",1045 "model.layers.23.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",1046 "model.layers.23.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",1047 "model.layers.23.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",1048 "model.layers.23.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",1049 "model.layers.23.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",1050 "model.layers.23.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",1051 "model.layers.23.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",1052 "model.layers.23.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",1053 "model.layers.23.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",1054 "model.layers.23.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",1055 "model.layers.23.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",1056 "model.layers.23.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",1057 "model.layers.23.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",1058 "model.layers.23.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",1059 "model.layers.23.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",1060 "model.layers.23.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",1061 "model.layers.23.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",1062 "model.layers.23.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",1063 "model.layers.24.input_layernorm.weight": "model-00002-of-00005.safetensors",1064 "model.layers.24.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",1065 "model.layers.24.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1066 "model.layers.24.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1067 "model.layers.24.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1068 "model.layers.24.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",1069 "model.layers.24.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",1070 "model.layers.24.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",1071 "model.layers.24.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",1072 "model.layers.24.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",1073 "model.layers.24.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",1074 "model.layers.24.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",1075 "model.layers.24.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",1076 "model.layers.24.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",1077 "model.layers.24.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",1078 "model.layers.24.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",1079 "model.layers.24.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",1080 "model.layers.24.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",1081 "model.layers.24.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",1082 "model.layers.24.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",1083 "model.layers.24.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",1084 "model.layers.24.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",1085 "model.layers.24.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",1086 "model.layers.24.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",1087 "model.layers.24.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",1088 "model.layers.24.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",1089 "model.layers.24.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",1090 "model.layers.24.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",1091 "model.layers.24.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",1092 "model.layers.24.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",1093 "model.layers.24.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",1094 "model.layers.24.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",1095 "model.layers.24.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",1096 "model.layers.25.input_layernorm.weight": "model-00002-of-00005.safetensors",1097 "model.layers.25.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",1098 "model.layers.25.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1099 "model.layers.25.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1100 "model.layers.25.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1101 "model.layers.25.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",1102 "model.layers.25.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",1103 "model.layers.25.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",1104 "model.layers.25.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",1105 "model.layers.25.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",1106 "model.layers.25.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",1107 "model.layers.25.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",1108 "model.layers.25.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",1109 "model.layers.25.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",1110 "model.layers.25.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",1111 "model.layers.25.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",1112 "model.layers.25.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",1113 "model.layers.25.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",1114 "model.layers.25.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",1115 "model.layers.25.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",1116 "model.layers.25.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",1117 "model.layers.25.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",1118 "model.layers.25.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",1119 "model.layers.25.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",1120 "model.layers.25.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",1121 "model.layers.25.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",1122 "model.layers.25.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",1123 "model.layers.25.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",1124 "model.layers.25.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",1125 "model.layers.25.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",1126 "model.layers.25.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",1127 "model.layers.25.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",1128 "model.layers.25.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",1129 "model.layers.26.input_layernorm.weight": "model-00002-of-00005.safetensors",1130 "model.layers.26.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",1131 "model.layers.26.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1132 "model.layers.26.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1133 "model.layers.26.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1134 "model.layers.26.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",1135 "model.layers.26.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",1136 "model.layers.26.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",1137 "model.layers.26.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",1138 "model.layers.26.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",1139 "model.layers.26.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",1140 "model.layers.26.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",1141 "model.layers.26.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",1142 "model.layers.26.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",1143 "model.layers.26.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",1144 "model.layers.26.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",1145 "model.layers.26.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",1146 "model.layers.26.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",1147 "model.layers.26.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",1148 "model.layers.26.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",1149 "model.layers.26.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",1150 "model.layers.26.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",1151 "model.layers.26.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",1152 "model.layers.26.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",1153 "model.layers.26.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",1154 "model.layers.26.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",1155 "model.layers.26.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",1156 "model.layers.26.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",1157 "model.layers.26.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",1158 "model.layers.26.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",1159 "model.layers.26.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",1160 "model.layers.26.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",1161 "model.layers.26.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",1162 "model.layers.27.input_layernorm.weight": "model-00002-of-00005.safetensors",1163 "model.layers.27.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",1164 "model.layers.27.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1165 "model.layers.27.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1166 "model.layers.27.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1167 "model.layers.27.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",1168 "model.layers.27.mlp.gate_proj.weight_global_scale": "model-00002-of-00005.safetensors",1169 "model.layers.27.mlp.gate_proj.weight_packed": "model-00002-of-00005.safetensors",1170 "model.layers.27.mlp.gate_proj.weight_scale": "model-00002-of-00005.safetensors",1171 "model.layers.27.mlp.up_proj.input_global_scale": "model-00002-of-00005.safetensors",1172 "model.layers.27.mlp.up_proj.weight_global_scale": "model-00002-of-00005.safetensors",1173 "model.layers.27.mlp.up_proj.weight_packed": "model-00002-of-00005.safetensors",1174 "model.layers.27.mlp.up_proj.weight_scale": "model-00002-of-00005.safetensors",1175 "model.layers.27.post_attention_layernorm.weight": "model-00002-of-00005.safetensors",1176 "model.layers.27.self_attn.k_proj.bias": "model-00002-of-00005.safetensors",1177 "model.layers.27.self_attn.k_proj.input_global_scale": "model-00002-of-00005.safetensors",1178 "model.layers.27.self_attn.k_proj.weight_global_scale": "model-00002-of-00005.safetensors",1179 "model.layers.27.self_attn.k_proj.weight_packed": "model-00002-of-00005.safetensors",1180 "model.layers.27.self_attn.k_proj.weight_scale": "model-00002-of-00005.safetensors",1181 "model.layers.27.self_attn.o_proj.input_global_scale": "model-00002-of-00005.safetensors",1182 "model.layers.27.self_attn.o_proj.weight_global_scale": "model-00002-of-00005.safetensors",1183 "model.layers.27.self_attn.o_proj.weight_packed": "model-00002-of-00005.safetensors",1184 "model.layers.27.self_attn.o_proj.weight_scale": "model-00002-of-00005.safetensors",1185 "model.layers.27.self_attn.q_proj.bias": "model-00002-of-00005.safetensors",1186 "model.layers.27.self_attn.q_proj.input_global_scale": "model-00002-of-00005.safetensors",1187 "model.layers.27.self_attn.q_proj.weight_global_scale": "model-00002-of-00005.safetensors",1188 "model.layers.27.self_attn.q_proj.weight_packed": "model-00002-of-00005.safetensors",1189 "model.layers.27.self_attn.q_proj.weight_scale": "model-00002-of-00005.safetensors",1190 "model.layers.27.self_attn.v_proj.bias": "model-00002-of-00005.safetensors",1191 "model.layers.27.self_attn.v_proj.input_global_scale": "model-00002-of-00005.safetensors",1192 "model.layers.27.self_attn.v_proj.weight_global_scale": "model-00002-of-00005.safetensors",1193 "model.layers.27.self_attn.v_proj.weight_packed": "model-00002-of-00005.safetensors",1194 "model.layers.27.self_attn.v_proj.weight_scale": "model-00002-of-00005.safetensors",1195 "model.layers.28.input_layernorm.weight": "model-00002-of-00005.safetensors",1196 "model.layers.28.mlp.down_proj.input_global_scale": "model-00002-of-00005.safetensors",1197 "model.layers.28.mlp.down_proj.weight_global_scale": "model-00002-of-00005.safetensors",1198 "model.layers.28.mlp.down_proj.weight_packed": "model-00002-of-00005.safetensors",1199 "model.layers.28.mlp.down_proj.weight_scale": "model-00002-of-00005.safetensors",1200 "model.layers.28.mlp.gate_proj.input_global_scale": "model-00002-of-00005.safetensors",