File size: 30,833 Bytes
2dd3b31 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 |
{
"metadata": {
"total_size": 6444642304
},
"weight_map": {
"logits_dense.weight": "model-00002-of-00002.safetensors",
"model.decoder.embeddings.embed.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.0.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.1.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.10.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.11.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.12.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.13.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.13.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.13.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.14.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.pre_ca_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.pre_mlp_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.pre_sa_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.self_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.self_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.self_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.14.self_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.pre_ca_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.pre_mlp_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.pre_sa_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.self_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.self_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.self_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.15.self_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.pre_ca_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.pre_mlp_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.pre_sa_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.self_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.self_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.self_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.16.self_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.cross_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.cross_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.cross_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.cross_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.mlp.gate_up_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.pre_ca_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.pre_mlp_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.pre_sa_norm.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.self_attention.k_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.self_attention.o_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.self_attention.q_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.17.self_attention.v_proj.weight": "model-00002-of-00002.safetensors",
"model.decoder.layers.2.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.2.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.3.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.4.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.5.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.6.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.7.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.8.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.cross_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.cross_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.cross_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.cross_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.pre_ca_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.pre_mlp_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.layers.9.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.decoder.norm.weight": "model-00002-of-00002.safetensors",
"model.encoder.embedding.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.0.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.1.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.10.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.11.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.2.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.3.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.4.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.5.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.6.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.7.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.8.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.mlp.gate_up_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.post_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.pre_sa_norm.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.self_attention.k_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.self_attention.o_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.self_attention.q_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.layers.9.self_attention.v_proj.weight": "model-00001-of-00002.safetensors",
"model.encoder.norm.weight": "model-00001-of-00002.safetensors"
}
}
|