bigcode/octocoder
71644
1{2 "metadata": {3 "total_size": 620698255364 },5 "weight_map": {6 "lm_head.weight": "model-00001-of-00007.safetensors",7 "transformer.h.0.attn.c_attn.bias": "model-00001-of-00007.safetensors",8 "transformer.h.0.attn.c_attn.weight": "model-00001-of-00007.safetensors",9 "transformer.h.0.attn.c_proj.bias": "model-00001-of-00007.safetensors",10 "transformer.h.0.attn.c_proj.weight": "model-00001-of-00007.safetensors",11 "transformer.h.0.ln_1.bias": "model-00001-of-00007.safetensors",12 "transformer.h.0.ln_1.weight": "model-00001-of-00007.safetensors",13 "transformer.h.0.ln_2.bias": "model-00001-of-00007.safetensors",14 "transformer.h.0.ln_2.weight": "model-00001-of-00007.safetensors",15 "transformer.h.0.mlp.c_fc.bias": "model-00001-of-00007.safetensors",16 "transformer.h.0.mlp.c_fc.weight": "model-00001-of-00007.safetensors",17 "transformer.h.0.mlp.c_proj.bias": "model-00001-of-00007.safetensors",18 "transformer.h.0.mlp.c_proj.weight": "model-00001-of-00007.safetensors",19 "transformer.h.1.attn.c_attn.bias": "model-00001-of-00007.safetensors",20 "transformer.h.1.attn.c_attn.weight": "model-00001-of-00007.safetensors",21 "transformer.h.1.attn.c_proj.bias": "model-00001-of-00007.safetensors",22 "transformer.h.1.attn.c_proj.weight": "model-00001-of-00007.safetensors",23 "transformer.h.1.ln_1.bias": "model-00001-of-00007.safetensors",24 "transformer.h.1.ln_1.weight": "model-00001-of-00007.safetensors",25 "transformer.h.1.ln_2.bias": "model-00001-of-00007.safetensors",26 "transformer.h.1.ln_2.weight": "model-00001-of-00007.safetensors",27 "transformer.h.1.mlp.c_fc.bias": "model-00001-of-00007.safetensors",28 "transformer.h.1.mlp.c_fc.weight": "model-00001-of-00007.safetensors",29 "transformer.h.1.mlp.c_proj.bias": "model-00001-of-00007.safetensors",30 "transformer.h.1.mlp.c_proj.weight": "model-00001-of-00007.safetensors",31 "transformer.h.10.attn.c_attn.bias": "model-00002-of-00007.safetensors",32 "transformer.h.10.attn.c_attn.weight": "model-00002-of-00007.safetensors",33 "transformer.h.10.attn.c_proj.bias": "model-00002-of-00007.safetensors",34 "transformer.h.10.attn.c_proj.weight": "model-00002-of-00007.safetensors",35 "transformer.h.10.ln_1.bias": "model-00002-of-00007.safetensors",36 "transformer.h.10.ln_1.weight": "model-00002-of-00007.safetensors",37 "transformer.h.10.ln_2.bias": "model-00002-of-00007.safetensors",38 "transformer.h.10.ln_2.weight": "model-00002-of-00007.safetensors",39 "transformer.h.10.mlp.c_fc.bias": "model-00002-of-00007.safetensors",40 "transformer.h.10.mlp.c_fc.weight": "model-00002-of-00007.safetensors",41 "transformer.h.10.mlp.c_proj.bias": "model-00002-of-00007.safetensors",42 "transformer.h.10.mlp.c_proj.weight": "model-00002-of-00007.safetensors",43 "transformer.h.11.attn.c_attn.bias": "model-00002-of-00007.safetensors",44 "transformer.h.11.attn.c_attn.weight": "model-00002-of-00007.safetensors",45 "transformer.h.11.attn.c_proj.bias": "model-00002-of-00007.safetensors",46 "transformer.h.11.attn.c_proj.weight": "model-00002-of-00007.safetensors",47 "transformer.h.11.ln_1.bias": "model-00002-of-00007.safetensors",48 "transformer.h.11.ln_1.weight": "model-00002-of-00007.safetensors",49 "transformer.h.11.ln_2.bias": "model-00002-of-00007.safetensors",50 "transformer.h.11.ln_2.weight": "model-00002-of-00007.safetensors",51 "transformer.h.11.mlp.c_fc.bias": "model-00002-of-00007.safetensors",52 "transformer.h.11.mlp.c_fc.weight": "model-00002-of-00007.safetensors",53 "transformer.h.11.mlp.c_proj.bias": "model-00002-of-00007.safetensors",54 "transformer.h.11.mlp.c_proj.weight": "model-00002-of-00007.safetensors",55 "transformer.h.12.attn.c_attn.bias": "model-00002-of-00007.safetensors",56 "transformer.h.12.attn.c_attn.weight": "model-00002-of-00007.safetensors",57 "transformer.h.12.attn.c_proj.bias": "model-00003-of-00007.safetensors",58 "transformer.h.12.attn.c_proj.weight": "model-00003-of-00007.safetensors",59 "transformer.h.12.ln_1.bias": "model-00002-of-00007.safetensors",60 "transformer.h.12.ln_1.weight": "model-00002-of-00007.safetensors",61 "transformer.h.12.ln_2.bias": "model-00003-of-00007.safetensors",62 "transformer.h.12.ln_2.weight": "model-00003-of-00007.safetensors",63 "transformer.h.12.mlp.c_fc.bias": "model-00003-of-00007.safetensors",64 "transformer.h.12.mlp.c_fc.weight": "model-00003-of-00007.safetensors",65 "transformer.h.12.mlp.c_proj.bias": "model-00003-of-00007.safetensors",66 "transformer.h.12.mlp.c_proj.weight": "model-00003-of-00007.safetensors",67 "transformer.h.13.attn.c_attn.bias": "model-00003-of-00007.safetensors",68 "transformer.h.13.attn.c_attn.weight": "model-00003-of-00007.safetensors",69 "transformer.h.13.attn.c_proj.bias": "model-00003-of-00007.safetensors",70 "transformer.h.13.attn.c_proj.weight": "model-00003-of-00007.safetensors",71 "transformer.h.13.ln_1.bias": "model-00003-of-00007.safetensors",72 "transformer.h.13.ln_1.weight": "model-00003-of-00007.safetensors",73 "transformer.h.13.ln_2.bias": "model-00003-of-00007.safetensors",74 "transformer.h.13.ln_2.weight": "model-00003-of-00007.safetensors",75 "transformer.h.13.mlp.c_fc.bias": "model-00003-of-00007.safetensors",76 "transformer.h.13.mlp.c_fc.weight": "model-00003-of-00007.safetensors",77 "transformer.h.13.mlp.c_proj.bias": "model-00003-of-00007.safetensors",78 "transformer.h.13.mlp.c_proj.weight": "model-00003-of-00007.safetensors",79 "transformer.h.14.attn.c_attn.bias": "model-00003-of-00007.safetensors",80 "transformer.h.14.attn.c_attn.weight": "model-00003-of-00007.safetensors",81 "transformer.h.14.attn.c_proj.bias": "model-00003-of-00007.safetensors",82 "transformer.h.14.attn.c_proj.weight": "model-00003-of-00007.safetensors",83 "transformer.h.14.ln_1.bias": "model-00003-of-00007.safetensors",84 "transformer.h.14.ln_1.weight": "model-00003-of-00007.safetensors",85 "transformer.h.14.ln_2.bias": "model-00003-of-00007.safetensors",86 "transformer.h.14.ln_2.weight": "model-00003-of-00007.safetensors",87 "transformer.h.14.mlp.c_fc.bias": "model-00003-of-00007.safetensors",88 "transformer.h.14.mlp.c_fc.weight": "model-00003-of-00007.safetensors",89 "transformer.h.14.mlp.c_proj.bias": "model-00003-of-00007.safetensors",90 "transformer.h.14.mlp.c_proj.weight": "model-00003-of-00007.safetensors",91 "transformer.h.15.attn.c_attn.bias": "model-00003-of-00007.safetensors",92 "transformer.h.15.attn.c_attn.weight": "model-00003-of-00007.safetensors",93 "transformer.h.15.attn.c_proj.bias": "model-00003-of-00007.safetensors",94 "transformer.h.15.attn.c_proj.weight": "model-00003-of-00007.safetensors",95 "transformer.h.15.ln_1.bias": "model-00003-of-00007.safetensors",96 "transformer.h.15.ln_1.weight": "model-00003-of-00007.safetensors",97 "transformer.h.15.ln_2.bias": "model-00003-of-00007.safetensors",98 "transformer.h.15.ln_2.weight": "model-00003-of-00007.safetensors",99 "transformer.h.15.mlp.c_fc.bias": "model-00003-of-00007.safetensors",100 "transformer.h.15.mlp.c_fc.weight": "model-00003-of-00007.safetensors",101 "transformer.h.15.mlp.c_proj.bias": "model-00003-of-00007.safetensors",102 "transformer.h.15.mlp.c_proj.weight": "model-00003-of-00007.safetensors",103 "transformer.h.16.attn.c_attn.bias": "model-00003-of-00007.safetensors",104 "transformer.h.16.attn.c_attn.weight": "model-00003-of-00007.safetensors",105 "transformer.h.16.attn.c_proj.bias": "model-00003-of-00007.safetensors",106 "transformer.h.16.attn.c_proj.weight": "model-00003-of-00007.safetensors",107 "transformer.h.16.ln_1.bias": "model-00003-of-00007.safetensors",108 "transformer.h.16.ln_1.weight": "model-00003-of-00007.safetensors",109 "transformer.h.16.ln_2.bias": "model-00003-of-00007.safetensors",110 "transformer.h.16.ln_2.weight": "model-00003-of-00007.safetensors",111 "transformer.h.16.mlp.c_fc.bias": "model-00003-of-00007.safetensors",112 "transformer.h.16.mlp.c_fc.weight": "model-00003-of-00007.safetensors",113 "transformer.h.16.mlp.c_proj.bias": "model-00003-of-00007.safetensors",114 "transformer.h.16.mlp.c_proj.weight": "model-00003-of-00007.safetensors",115 "transformer.h.17.attn.c_attn.bias": "model-00003-of-00007.safetensors",116 "transformer.h.17.attn.c_attn.weight": "model-00003-of-00007.safetensors",117 "transformer.h.17.attn.c_proj.bias": "model-00003-of-00007.safetensors",118 "transformer.h.17.attn.c_proj.weight": "model-00003-of-00007.safetensors",119 "transformer.h.17.ln_1.bias": "model-00003-of-00007.safetensors",120 "transformer.h.17.ln_1.weight": "model-00003-of-00007.safetensors",121 "transformer.h.17.ln_2.bias": "model-00003-of-00007.safetensors",122 "transformer.h.17.ln_2.weight": "model-00003-of-00007.safetensors",123 "transformer.h.17.mlp.c_fc.bias": "model-00003-of-00007.safetensors",124 "transformer.h.17.mlp.c_fc.weight": "model-00003-of-00007.safetensors",125 "transformer.h.17.mlp.c_proj.bias": "model-00003-of-00007.safetensors",126 "transformer.h.17.mlp.c_proj.weight": "model-00003-of-00007.safetensors",127 "transformer.h.18.attn.c_attn.bias": "model-00003-of-00007.safetensors",128 "transformer.h.18.attn.c_attn.weight": "model-00003-of-00007.safetensors",129 "transformer.h.18.attn.c_proj.bias": "model-00003-of-00007.safetensors",130 "transformer.h.18.attn.c_proj.weight": "model-00003-of-00007.safetensors",131 "transformer.h.18.ln_1.bias": "model-00003-of-00007.safetensors",132 "transformer.h.18.ln_1.weight": "model-00003-of-00007.safetensors",133 "transformer.h.18.ln_2.bias": "model-00003-of-00007.safetensors",134 "transformer.h.18.ln_2.weight": "model-00003-of-00007.safetensors",135 "transformer.h.18.mlp.c_fc.bias": "model-00003-of-00007.safetensors",136 "transformer.h.18.mlp.c_fc.weight": "model-00003-of-00007.safetensors",137 "transformer.h.18.mlp.c_proj.bias": "model-00004-of-00007.safetensors",138 "transformer.h.18.mlp.c_proj.weight": "model-00004-of-00007.safetensors",139 "transformer.h.19.attn.c_attn.bias": "model-00004-of-00007.safetensors",140 "transformer.h.19.attn.c_attn.weight": "model-00004-of-00007.safetensors",141 "transformer.h.19.attn.c_proj.bias": "model-00004-of-00007.safetensors",142 "transformer.h.19.attn.c_proj.weight": "model-00004-of-00007.safetensors",143 "transformer.h.19.ln_1.bias": "model-00004-of-00007.safetensors",144 "transformer.h.19.ln_1.weight": "model-00004-of-00007.safetensors",145 "transformer.h.19.ln_2.bias": "model-00004-of-00007.safetensors",146 "transformer.h.19.ln_2.weight": "model-00004-of-00007.safetensors",147 "transformer.h.19.mlp.c_fc.bias": "model-00004-of-00007.safetensors",148 "transformer.h.19.mlp.c_fc.weight": "model-00004-of-00007.safetensors",149 "transformer.h.19.mlp.c_proj.bias": "model-00004-of-00007.safetensors",150 "transformer.h.19.mlp.c_proj.weight": "model-00004-of-00007.safetensors",151 "transformer.h.2.attn.c_attn.bias": "model-00001-of-00007.safetensors",152 "transformer.h.2.attn.c_attn.weight": "model-00001-of-00007.safetensors",153 "transformer.h.2.attn.c_proj.bias": "model-00001-of-00007.safetensors",154 "transformer.h.2.attn.c_proj.weight": "model-00001-of-00007.safetensors",155 "transformer.h.2.ln_1.bias": "model-00001-of-00007.safetensors",156 "transformer.h.2.ln_1.weight": "model-00001-of-00007.safetensors",157 "transformer.h.2.ln_2.bias": "model-00001-of-00007.safetensors",158 "transformer.h.2.ln_2.weight": "model-00001-of-00007.safetensors",159 "transformer.h.2.mlp.c_fc.bias": "model-00001-of-00007.safetensors",160 "transformer.h.2.mlp.c_fc.weight": "model-00001-of-00007.safetensors",161 "transformer.h.2.mlp.c_proj.bias": "model-00001-of-00007.safetensors",162 "transformer.h.2.mlp.c_proj.weight": "model-00001-of-00007.safetensors",163 "transformer.h.20.attn.c_attn.bias": "model-00004-of-00007.safetensors",164 "transformer.h.20.attn.c_attn.weight": "model-00004-of-00007.safetensors",165 "transformer.h.20.attn.c_proj.bias": "model-00004-of-00007.safetensors",166 "transformer.h.20.attn.c_proj.weight": "model-00004-of-00007.safetensors",167 "transformer.h.20.ln_1.bias": "model-00004-of-00007.safetensors",168 "transformer.h.20.ln_1.weight": "model-00004-of-00007.safetensors",169 "transformer.h.20.ln_2.bias": "model-00004-of-00007.safetensors",170 "transformer.h.20.ln_2.weight": "model-00004-of-00007.safetensors",171 "transformer.h.20.mlp.c_fc.bias": "model-00004-of-00007.safetensors",172 "transformer.h.20.mlp.c_fc.weight": "model-00004-of-00007.safetensors",173 "transformer.h.20.mlp.c_proj.bias": "model-00004-of-00007.safetensors",174 "transformer.h.20.mlp.c_proj.weight": "model-00004-of-00007.safetensors",175 "transformer.h.21.attn.c_attn.bias": "model-00004-of-00007.safetensors",176 "transformer.h.21.attn.c_attn.weight": "model-00004-of-00007.safetensors",177 "transformer.h.21.attn.c_proj.bias": "model-00004-of-00007.safetensors",178 "transformer.h.21.attn.c_proj.weight": "model-00004-of-00007.safetensors",179 "transformer.h.21.ln_1.bias": "model-00004-of-00007.safetensors",180 "transformer.h.21.ln_1.weight": "model-00004-of-00007.safetensors",181 "transformer.h.21.ln_2.bias": "model-00004-of-00007.safetensors",182 "transformer.h.21.ln_2.weight": "model-00004-of-00007.safetensors",183 "transformer.h.21.mlp.c_fc.bias": "model-00004-of-00007.safetensors",184 "transformer.h.21.mlp.c_fc.weight": "model-00004-of-00007.safetensors",185 "transformer.h.21.mlp.c_proj.bias": "model-00004-of-00007.safetensors",186 "transformer.h.21.mlp.c_proj.weight": "model-00004-of-00007.safetensors",187 "transformer.h.22.attn.c_attn.bias": "model-00004-of-00007.safetensors",188 "transformer.h.22.attn.c_attn.weight": "model-00004-of-00007.safetensors",189 "transformer.h.22.attn.c_proj.bias": "model-00004-of-00007.safetensors",190 "transformer.h.22.attn.c_proj.weight": "model-00004-of-00007.safetensors",191 "transformer.h.22.ln_1.bias": "model-00004-of-00007.safetensors",192 "transformer.h.22.ln_1.weight": "model-00004-of-00007.safetensors",193 "transformer.h.22.ln_2.bias": "model-00004-of-00007.safetensors",194 "transformer.h.22.ln_2.weight": "model-00004-of-00007.safetensors",195 "transformer.h.22.mlp.c_fc.bias": "model-00004-of-00007.safetensors",196 "transformer.h.22.mlp.c_fc.weight": "model-00004-of-00007.safetensors",197 "transformer.h.22.mlp.c_proj.bias": "model-00004-of-00007.safetensors",198 "transformer.h.22.mlp.c_proj.weight": "model-00004-of-00007.safetensors",199 "transformer.h.23.attn.c_attn.bias": "model-00004-of-00007.safetensors",200 "transformer.h.23.attn.c_attn.weight": "model-00004-of-00007.safetensors",201 "transformer.h.23.attn.c_proj.bias": "model-00004-of-00007.safetensors",202 "transformer.h.23.attn.c_proj.weight": "model-00004-of-00007.safetensors",203 "transformer.h.23.ln_1.bias": "model-00004-of-00007.safetensors",204 "transformer.h.23.ln_1.weight": "model-00004-of-00007.safetensors",205 "transformer.h.23.ln_2.bias": "model-00004-of-00007.safetensors",206 "transformer.h.23.ln_2.weight": "model-00004-of-00007.safetensors",207 "transformer.h.23.mlp.c_fc.bias": "model-00004-of-00007.safetensors",208 "transformer.h.23.mlp.c_fc.weight": "model-00004-of-00007.safetensors",209 "transformer.h.23.mlp.c_proj.bias": "model-00004-of-00007.safetensors",210 "transformer.h.23.mlp.c_proj.weight": "model-00004-of-00007.safetensors",211 "transformer.h.24.attn.c_attn.bias": "model-00004-of-00007.safetensors",212 "transformer.h.24.attn.c_attn.weight": "model-00004-of-00007.safetensors",213 "transformer.h.24.attn.c_proj.bias": "model-00004-of-00007.safetensors",214 "transformer.h.24.attn.c_proj.weight": "model-00004-of-00007.safetensors",215 "transformer.h.24.ln_1.bias": "model-00004-of-00007.safetensors",216 "transformer.h.24.ln_1.weight": "model-00004-of-00007.safetensors",217 "transformer.h.24.ln_2.bias": "model-00004-of-00007.safetensors",218 "transformer.h.24.ln_2.weight": "model-00004-of-00007.safetensors",219 "transformer.h.24.mlp.c_fc.bias": "model-00004-of-00007.safetensors",220 "transformer.h.24.mlp.c_fc.weight": "model-00004-of-00007.safetensors",221 "transformer.h.24.mlp.c_proj.bias": "model-00004-of-00007.safetensors",222 "transformer.h.24.mlp.c_proj.weight": "model-00004-of-00007.safetensors",223 "transformer.h.25.attn.c_attn.bias": "model-00004-of-00007.safetensors",224 "transformer.h.25.attn.c_attn.weight": "model-00004-of-00007.safetensors",225 "transformer.h.25.attn.c_proj.bias": "model-00005-of-00007.safetensors",226 "transformer.h.25.attn.c_proj.weight": "model-00005-of-00007.safetensors",227 "transformer.h.25.ln_1.bias": "model-00004-of-00007.safetensors",228 "transformer.h.25.ln_1.weight": "model-00004-of-00007.safetensors",229 "transformer.h.25.ln_2.bias": "model-00005-of-00007.safetensors",230 "transformer.h.25.ln_2.weight": "model-00005-of-00007.safetensors",231 "transformer.h.25.mlp.c_fc.bias": "model-00005-of-00007.safetensors",232 "transformer.h.25.mlp.c_fc.weight": "model-00005-of-00007.safetensors",233 "transformer.h.25.mlp.c_proj.bias": "model-00005-of-00007.safetensors",234 "transformer.h.25.mlp.c_proj.weight": "model-00005-of-00007.safetensors",235 "transformer.h.26.attn.c_attn.bias": "model-00005-of-00007.safetensors",236 "transformer.h.26.attn.c_attn.weight": "model-00005-of-00007.safetensors",237 "transformer.h.26.attn.c_proj.bias": "model-00005-of-00007.safetensors",238 "transformer.h.26.attn.c_proj.weight": "model-00005-of-00007.safetensors",239 "transformer.h.26.ln_1.bias": "model-00005-of-00007.safetensors",240 "transformer.h.26.ln_1.weight": "model-00005-of-00007.safetensors",241 "transformer.h.26.ln_2.bias": "model-00005-of-00007.safetensors",242 "transformer.h.26.ln_2.weight": "model-00005-of-00007.safetensors",243 "transformer.h.26.mlp.c_fc.bias": "model-00005-of-00007.safetensors",244 "transformer.h.26.mlp.c_fc.weight": "model-00005-of-00007.safetensors",245 "transformer.h.26.mlp.c_proj.bias": "model-00005-of-00007.safetensors",246 "transformer.h.26.mlp.c_proj.weight": "model-00005-of-00007.safetensors",247 "transformer.h.27.attn.c_attn.bias": "model-00005-of-00007.safetensors",248 "transformer.h.27.attn.c_attn.weight": "model-00005-of-00007.safetensors",249 "transformer.h.27.attn.c_proj.bias": "model-00005-of-00007.safetensors",250 "transformer.h.27.attn.c_proj.weight": "model-00005-of-00007.safetensors",251 "transformer.h.27.ln_1.bias": "model-00005-of-00007.safetensors",252 "transformer.h.27.ln_1.weight": "model-00005-of-00007.safetensors",253 "transformer.h.27.ln_2.bias": "model-00005-of-00007.safetensors",254 "transformer.h.27.ln_2.weight": "model-00005-of-00007.safetensors",255 "transformer.h.27.mlp.c_fc.bias": "model-00005-of-00007.safetensors",256 "transformer.h.27.mlp.c_fc.weight": "model-00005-of-00007.safetensors",257 "transformer.h.27.mlp.c_proj.bias": "model-00005-of-00007.safetensors",258 "transformer.h.27.mlp.c_proj.weight": "model-00005-of-00007.safetensors",259 "transformer.h.28.attn.c_attn.bias": "model-00005-of-00007.safetensors",260 "transformer.h.28.attn.c_attn.weight": "model-00005-of-00007.safetensors",261 "transformer.h.28.attn.c_proj.bias": "model-00005-of-00007.safetensors",262 "transformer.h.28.attn.c_proj.weight": "model-00005-of-00007.safetensors",263 "transformer.h.28.ln_1.bias": "model-00005-of-00007.safetensors",264 "transformer.h.28.ln_1.weight": "model-00005-of-00007.safetensors",265 "transformer.h.28.ln_2.bias": "model-00005-of-00007.safetensors",266 "transformer.h.28.ln_2.weight": "model-00005-of-00007.safetensors",267 "transformer.h.28.mlp.c_fc.bias": "model-00005-of-00007.safetensors",268 "transformer.h.28.mlp.c_fc.weight": "model-00005-of-00007.safetensors",269 "transformer.h.28.mlp.c_proj.bias": "model-00005-of-00007.safetensors",270 "transformer.h.28.mlp.c_proj.weight": "model-00005-of-00007.safetensors",271 "transformer.h.29.attn.c_attn.bias": "model-00005-of-00007.safetensors",272 "transformer.h.29.attn.c_attn.weight": "model-00005-of-00007.safetensors",273 "transformer.h.29.attn.c_proj.bias": "model-00005-of-00007.safetensors",274 "transformer.h.29.attn.c_proj.weight": "model-00005-of-00007.safetensors",275 "transformer.h.29.ln_1.bias": "model-00005-of-00007.safetensors",276 "transformer.h.29.ln_1.weight": "model-00005-of-00007.safetensors",277 "transformer.h.29.ln_2.bias": "model-00005-of-00007.safetensors",278 "transformer.h.29.ln_2.weight": "model-00005-of-00007.safetensors",279 "transformer.h.29.mlp.c_fc.bias": "model-00005-of-00007.safetensors",280 "transformer.h.29.mlp.c_fc.weight": "model-00005-of-00007.safetensors",281 "transformer.h.29.mlp.c_proj.bias": "model-00005-of-00007.safetensors",282 "transformer.h.29.mlp.c_proj.weight": "model-00005-of-00007.safetensors",283 "transformer.h.3.attn.c_attn.bias": "model-00001-of-00007.safetensors",284 "transformer.h.3.attn.c_attn.weight": "model-00001-of-00007.safetensors",285 "transformer.h.3.attn.c_proj.bias": "model-00001-of-00007.safetensors",286 "transformer.h.3.attn.c_proj.weight": "model-00001-of-00007.safetensors",287 "transformer.h.3.ln_1.bias": "model-00001-of-00007.safetensors",288 "transformer.h.3.ln_1.weight": "model-00001-of-00007.safetensors",289 "transformer.h.3.ln_2.bias": "model-00001-of-00007.safetensors",290 "transformer.h.3.ln_2.weight": "model-00001-of-00007.safetensors",291 "transformer.h.3.mlp.c_fc.bias": "model-00001-of-00007.safetensors",292 "transformer.h.3.mlp.c_fc.weight": "model-00001-of-00007.safetensors",293 "transformer.h.3.mlp.c_proj.bias": "model-00001-of-00007.safetensors",294 "transformer.h.3.mlp.c_proj.weight": "model-00001-of-00007.safetensors",295 "transformer.h.30.attn.c_attn.bias": "model-00005-of-00007.safetensors",296 "transformer.h.30.attn.c_attn.weight": "model-00005-of-00007.safetensors",297 "transformer.h.30.attn.c_proj.bias": "model-00005-of-00007.safetensors",298 "transformer.h.30.attn.c_proj.weight": "model-00005-of-00007.safetensors",299 "transformer.h.30.ln_1.bias": "model-00005-of-00007.safetensors",300 "transformer.h.30.ln_1.weight": "model-00005-of-00007.safetensors",301 "transformer.h.30.ln_2.bias": "model-00005-of-00007.safetensors",302 "transformer.h.30.ln_2.weight": "model-00005-of-00007.safetensors",303 "transformer.h.30.mlp.c_fc.bias": "model-00005-of-00007.safetensors",304 "transformer.h.30.mlp.c_fc.weight": "model-00005-of-00007.safetensors",305 "transformer.h.30.mlp.c_proj.bias": "model-00005-of-00007.safetensors",306 "transformer.h.30.mlp.c_proj.weight": "model-00005-of-00007.safetensors",307 "transformer.h.31.attn.c_attn.bias": "model-00005-of-00007.safetensors",308 "transformer.h.31.attn.c_attn.weight": "model-00005-of-00007.safetensors",309 "transformer.h.31.attn.c_proj.bias": "model-00005-of-00007.safetensors",310 "transformer.h.31.attn.c_proj.weight": "model-00005-of-00007.safetensors",311 "transformer.h.31.ln_1.bias": "model-00005-of-00007.safetensors",312 "transformer.h.31.ln_1.weight": "model-00005-of-00007.safetensors",313 "transformer.h.31.ln_2.bias": "model-00005-of-00007.safetensors",314 "transformer.h.31.ln_2.weight": "model-00005-of-00007.safetensors",315 "transformer.h.31.mlp.c_fc.bias": "model-00005-of-00007.safetensors",316 "transformer.h.31.mlp.c_fc.weight": "model-00005-of-00007.safetensors",317 "transformer.h.31.mlp.c_proj.bias": "model-00006-of-00007.safetensors",318 "transformer.h.31.mlp.c_proj.weight": "model-00006-of-00007.safetensors",319 "transformer.h.32.attn.c_attn.bias": "model-00006-of-00007.safetensors",320 "transformer.h.32.attn.c_attn.weight": "model-00006-of-00007.safetensors",321 "transformer.h.32.attn.c_proj.bias": "model-00006-of-00007.safetensors",322 "transformer.h.32.attn.c_proj.weight": "model-00006-of-00007.safetensors",323 "transformer.h.32.ln_1.bias": "model-00006-of-00007.safetensors",324 "transformer.h.32.ln_1.weight": "model-00006-of-00007.safetensors",325 "transformer.h.32.ln_2.bias": "model-00006-of-00007.safetensors",326 "transformer.h.32.ln_2.weight": "model-00006-of-00007.safetensors",327 "transformer.h.32.mlp.c_fc.bias": "model-00006-of-00007.safetensors",328 "transformer.h.32.mlp.c_fc.weight": "model-00006-of-00007.safetensors",329 "transformer.h.32.mlp.c_proj.bias": "model-00006-of-00007.safetensors",330 "transformer.h.32.mlp.c_proj.weight": "model-00006-of-00007.safetensors",331 "transformer.h.33.attn.c_attn.bias": "model-00006-of-00007.safetensors",332 "transformer.h.33.attn.c_attn.weight": "model-00006-of-00007.safetensors",333 "transformer.h.33.attn.c_proj.bias": "model-00006-of-00007.safetensors",334 "transformer.h.33.attn.c_proj.weight": "model-00006-of-00007.safetensors",335 "transformer.h.33.ln_1.bias": "model-00006-of-00007.safetensors",336 "transformer.h.33.ln_1.weight": "model-00006-of-00007.safetensors",337 "transformer.h.33.ln_2.bias": "model-00006-of-00007.safetensors",338 "transformer.h.33.ln_2.weight": "model-00006-of-00007.safetensors",339 "transformer.h.33.mlp.c_fc.bias": "model-00006-of-00007.safetensors",340 "transformer.h.33.mlp.c_fc.weight": "model-00006-of-00007.safetensors",341 "transformer.h.33.mlp.c_proj.bias": "model-00006-of-00007.safetensors",342 "transformer.h.33.mlp.c_proj.weight": "model-00006-of-00007.safetensors",343 "transformer.h.34.attn.c_attn.bias": "model-00006-of-00007.safetensors",344 "transformer.h.34.attn.c_attn.weight": "model-00006-of-00007.safetensors",345 "transformer.h.34.attn.c_proj.bias": "model-00006-of-00007.safetensors",346 "transformer.h.34.attn.c_proj.weight": "model-00006-of-00007.safetensors",347 "transformer.h.34.ln_1.bias": "model-00006-of-00007.safetensors",348 "transformer.h.34.ln_1.weight": "model-00006-of-00007.safetensors",349 "transformer.h.34.ln_2.bias": "model-00006-of-00007.safetensors",350 "transformer.h.34.ln_2.weight": "model-00006-of-00007.safetensors",351 "transformer.h.34.mlp.c_fc.bias": "model-00006-of-00007.safetensors",352 "transformer.h.34.mlp.c_fc.weight": "model-00006-of-00007.safetensors",353 "transformer.h.34.mlp.c_proj.bias": "model-00006-of-00007.safetensors",354 "transformer.h.34.mlp.c_proj.weight": "model-00006-of-00007.safetensors",355 "transformer.h.35.attn.c_attn.bias": "model-00006-of-00007.safetensors",356 "transformer.h.35.attn.c_attn.weight": "model-00006-of-00007.safetensors",357 "transformer.h.35.attn.c_proj.bias": "model-00006-of-00007.safetensors",358 "transformer.h.35.attn.c_proj.weight": "model-00006-of-00007.safetensors",359 "transformer.h.35.ln_1.bias": "model-00006-of-00007.safetensors",360 "transformer.h.35.ln_1.weight": "model-00006-of-00007.safetensors",361 "transformer.h.35.ln_2.bias": "model-00006-of-00007.safetensors",362 "transformer.h.35.ln_2.weight": "model-00006-of-00007.safetensors",363 "transformer.h.35.mlp.c_fc.bias": "model-00006-of-00007.safetensors",364 "transformer.h.35.mlp.c_fc.weight": "model-00006-of-00007.safetensors",365 "transformer.h.35.mlp.c_proj.bias": "model-00006-of-00007.safetensors",366 "transformer.h.35.mlp.c_proj.weight": "model-00006-of-00007.safetensors",367 "transformer.h.36.attn.c_attn.bias": "model-00006-of-00007.safetensors",368 "transformer.h.36.attn.c_attn.weight": "model-00006-of-00007.safetensors",369 "transformer.h.36.attn.c_proj.bias": "model-00006-of-00007.safetensors",370 "transformer.h.36.attn.c_proj.weight": "model-00006-of-00007.safetensors",371 "transformer.h.36.ln_1.bias": "model-00006-of-00007.safetensors",372 "transformer.h.36.ln_1.weight": "model-00006-of-00007.safetensors",373 "transformer.h.36.ln_2.bias": "model-00006-of-00007.safetensors",374 "transformer.h.36.ln_2.weight": "model-00006-of-00007.safetensors",375 "transformer.h.36.mlp.c_fc.bias": "model-00006-of-00007.safetensors",376 "transformer.h.36.mlp.c_fc.weight": "model-00006-of-00007.safetensors",377 "transformer.h.36.mlp.c_proj.bias": "model-00006-of-00007.safetensors",378 "transformer.h.36.mlp.c_proj.weight": "model-00006-of-00007.safetensors",379 "transformer.h.37.attn.c_attn.bias": "model-00006-of-00007.safetensors",380 "transformer.h.37.attn.c_attn.weight": "model-00006-of-00007.safetensors",381 "transformer.h.37.attn.c_proj.bias": "model-00006-of-00007.safetensors",382 "transformer.h.37.attn.c_proj.weight": "model-00006-of-00007.safetensors",383 "transformer.h.37.ln_1.bias": "model-00006-of-00007.safetensors",384 "transformer.h.37.ln_1.weight": "model-00006-of-00007.safetensors",385 "transformer.h.37.ln_2.bias": "model-00006-of-00007.safetensors",386 "transformer.h.37.ln_2.weight": "model-00006-of-00007.safetensors",387 "transformer.h.37.mlp.c_fc.bias": "model-00006-of-00007.safetensors",388 "transformer.h.37.mlp.c_fc.weight": "model-00006-of-00007.safetensors",389 "transformer.h.37.mlp.c_proj.bias": "model-00006-of-00007.safetensors",390 "transformer.h.37.mlp.c_proj.weight": "model-00006-of-00007.safetensors",391 "transformer.h.38.attn.c_attn.bias": "model-00006-of-00007.safetensors",392 "transformer.h.38.attn.c_attn.weight": "model-00006-of-00007.safetensors",393 "transformer.h.38.attn.c_proj.bias": "model-00007-of-00007.safetensors",394 "transformer.h.38.attn.c_proj.weight": "model-00007-of-00007.safetensors",395 "transformer.h.38.ln_1.bias": "model-00006-of-00007.safetensors",396 "transformer.h.38.ln_1.weight": "model-00006-of-00007.safetensors",397 "transformer.h.38.ln_2.bias": "model-00007-of-00007.safetensors",398 "transformer.h.38.ln_2.weight": "model-00007-of-00007.safetensors",399 "transformer.h.38.mlp.c_fc.bias": "model-00007-of-00007.safetensors",400 "transformer.h.38.mlp.c_fc.weight": "model-00007-of-00007.safetensors",401 "transformer.h.38.mlp.c_proj.bias": "model-00007-of-00007.safetensors",402 "transformer.h.38.mlp.c_proj.weight": "model-00007-of-00007.safetensors",403 "transformer.h.39.attn.c_attn.bias": "model-00007-of-00007.safetensors",404 "transformer.h.39.attn.c_attn.weight": "model-00007-of-00007.safetensors",405 "transformer.h.39.attn.c_proj.bias": "model-00007-of-00007.safetensors",406 "transformer.h.39.attn.c_proj.weight": "model-00007-of-00007.safetensors",407 "transformer.h.39.ln_1.bias": "model-00007-of-00007.safetensors",408 "transformer.h.39.ln_1.weight": "model-00007-of-00007.safetensors",409 "transformer.h.39.ln_2.bias": "model-00007-of-00007.safetensors",410 "transformer.h.39.ln_2.weight": "model-00007-of-00007.safetensors",411 "transformer.h.39.mlp.c_fc.bias": "model-00007-of-00007.safetensors",412 "transformer.h.39.mlp.c_fc.weight": "model-00007-of-00007.safetensors",413 "transformer.h.39.mlp.c_proj.bias": "model-00007-of-00007.safetensors",414 "transformer.h.39.mlp.c_proj.weight": "model-00007-of-00007.safetensors",415 "transformer.h.4.attn.c_attn.bias": "model-00001-of-00007.safetensors",416 "transformer.h.4.attn.c_attn.weight": "model-00001-of-00007.safetensors",417 "transformer.h.4.attn.c_proj.bias": "model-00001-of-00007.safetensors",418 "transformer.h.4.attn.c_proj.weight": "model-00001-of-00007.safetensors",419 "transformer.h.4.ln_1.bias": "model-00001-of-00007.safetensors",420 "transformer.h.4.ln_1.weight": "model-00001-of-00007.safetensors",421 "transformer.h.4.ln_2.bias": "model-00001-of-00007.safetensors",422 "transformer.h.4.ln_2.weight": "model-00001-of-00007.safetensors",423 "transformer.h.4.mlp.c_fc.bias": "model-00001-of-00007.safetensors",424 "transformer.h.4.mlp.c_fc.weight": "model-00001-of-00007.safetensors",425 "transformer.h.4.mlp.c_proj.bias": "model-00001-of-00007.safetensors",426 "transformer.h.4.mlp.c_proj.weight": "model-00001-of-00007.safetensors",427 "transformer.h.5.attn.c_attn.bias": "model-00001-of-00007.safetensors",428 "transformer.h.5.attn.c_attn.weight": "model-00001-of-00007.safetensors",429 "transformer.h.5.attn.c_proj.bias": "model-00001-of-00007.safetensors",430 "transformer.h.5.attn.c_proj.weight": "model-00001-of-00007.safetensors",431 "transformer.h.5.ln_1.bias": "model-00001-of-00007.safetensors",432 "transformer.h.5.ln_1.weight": "model-00001-of-00007.safetensors",433 "transformer.h.5.ln_2.bias": "model-00001-of-00007.safetensors",434 "transformer.h.5.ln_2.weight": "model-00001-of-00007.safetensors",435 "transformer.h.5.mlp.c_fc.bias": "model-00001-of-00007.safetensors",436 "transformer.h.5.mlp.c_fc.weight": "model-00001-of-00007.safetensors",437 "transformer.h.5.mlp.c_proj.bias": "model-00002-of-00007.safetensors",438 "transformer.h.5.mlp.c_proj.weight": "model-00002-of-00007.safetensors",439 "transformer.h.6.attn.c_attn.bias": "model-00002-of-00007.safetensors",440 "transformer.h.6.attn.c_attn.weight": "model-00002-of-00007.safetensors",441 "transformer.h.6.attn.c_proj.bias": "model-00002-of-00007.safetensors",442 "transformer.h.6.attn.c_proj.weight": "model-00002-of-00007.safetensors",443 "transformer.h.6.ln_1.bias": "model-00002-of-00007.safetensors",444 "transformer.h.6.ln_1.weight": "model-00002-of-00007.safetensors",445 "transformer.h.6.ln_2.bias": "model-00002-of-00007.safetensors",446 "transformer.h.6.ln_2.weight": "model-00002-of-00007.safetensors",447 "transformer.h.6.mlp.c_fc.bias": "model-00002-of-00007.safetensors",448 "transformer.h.6.mlp.c_fc.weight": "model-00002-of-00007.safetensors",449 "transformer.h.6.mlp.c_proj.bias": "model-00002-of-00007.safetensors",450 "transformer.h.6.mlp.c_proj.weight": "model-00002-of-00007.safetensors",451 "transformer.h.7.attn.c_attn.bias": "model-00002-of-00007.safetensors",452 "transformer.h.7.attn.c_attn.weight": "model-00002-of-00007.safetensors",453 "transformer.h.7.attn.c_proj.bias": "model-00002-of-00007.safetensors",454 "transformer.h.7.attn.c_proj.weight": "model-00002-of-00007.safetensors",455 "transformer.h.7.ln_1.bias": "model-00002-of-00007.safetensors",456 "transformer.h.7.ln_1.weight": "model-00002-of-00007.safetensors",457 "transformer.h.7.ln_2.bias": "model-00002-of-00007.safetensors",458 "transformer.h.7.ln_2.weight": "model-00002-of-00007.safetensors",459 "transformer.h.7.mlp.c_fc.bias": "model-00002-of-00007.safetensors",460 "transformer.h.7.mlp.c_fc.weight": "model-00002-of-00007.safetensors",461 "transformer.h.7.mlp.c_proj.bias": "model-00002-of-00007.safetensors",462 "transformer.h.7.mlp.c_proj.weight": "model-00002-of-00007.safetensors",463 "transformer.h.8.attn.c_attn.bias": "model-00002-of-00007.safetensors",464 "transformer.h.8.attn.c_attn.weight": "model-00002-of-00007.safetensors",465 "transformer.h.8.attn.c_proj.bias": "model-00002-of-00007.safetensors",466 "transformer.h.8.attn.c_proj.weight": "model-00002-of-00007.safetensors",467 "transformer.h.8.ln_1.bias": "model-00002-of-00007.safetensors",468 "transformer.h.8.ln_1.weight": "model-00002-of-00007.safetensors",469 "transformer.h.8.ln_2.bias": "model-00002-of-00007.safetensors",470 "transformer.h.8.ln_2.weight": "model-00002-of-00007.safetensors",471 "transformer.h.8.mlp.c_fc.bias": "model-00002-of-00007.safetensors",472 "transformer.h.8.mlp.c_fc.weight": "model-00002-of-00007.safetensors",473 "transformer.h.8.mlp.c_proj.bias": "model-00002-of-00007.safetensors",474 "transformer.h.8.mlp.c_proj.weight": "model-00002-of-00007.safetensors",475 "transformer.h.9.attn.c_attn.bias": "model-00002-of-00007.safetensors",476 "transformer.h.9.attn.c_attn.weight": "model-00002-of-00007.safetensors",477 "transformer.h.9.attn.c_proj.bias": "model-00002-of-00007.safetensors",478 "transformer.h.9.attn.c_proj.weight": "model-00002-of-00007.safetensors",479 "transformer.h.9.ln_1.bias": "model-00002-of-00007.safetensors",480 "transformer.h.9.ln_1.weight": "model-00002-of-00007.safetensors",481 "transformer.h.9.ln_2.bias": "model-00002-of-00007.safetensors",482 "transformer.h.9.ln_2.weight": "model-00002-of-00007.safetensors",483 "transformer.h.9.mlp.c_fc.bias": "model-00002-of-00007.safetensors",484 "transformer.h.9.mlp.c_fc.weight": "model-00002-of-00007.safetensors",485 "transformer.h.9.mlp.c_proj.bias": "model-00002-of-00007.safetensors",486 "transformer.h.9.mlp.c_proj.weight": "model-00002-of-00007.safetensors",487 "transformer.ln_f.bias": "model-00007-of-00007.safetensors",488 "transformer.ln_f.weight": "model-00007-of-00007.safetensors",489 "transformer.wpe.weight": "model-00001-of-00007.safetensors",490 "transformer.wte.weight": "model-00001-of-00007.safetensors"491 }492}