File size: 28,030 Bytes
fa8e1f6 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 |
{
"metadata": {
"total_size": 6484624384
},
"weight_map": {
"embedding.weight": "model-00001-of-00002.safetensors",
"layer_norm.bias": "model-00002-of-00002.safetensors",
"layer_norm.weight": "model-00002-of-00002.safetensors",
"layers.0.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.0.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.0.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.0.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.0.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.0.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.0.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.0.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.0.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.0.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.0.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.0.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.0.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.0.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.0.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.0.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.1.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.1.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.1.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.1.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.1.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.1.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.1.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.1.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.1.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.1.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.1.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.1.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.1.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.1.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.1.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.1.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.10.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.10.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.10.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.10.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.10.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.10.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.10.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.10.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.10.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.10.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.10.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.10.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.10.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.10.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.10.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.10.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.11.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.11.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.11.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.11.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.11.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.11.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.11.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.11.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.11.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.11.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.11.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.11.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.11.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.11.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.11.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.11.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.12.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.12.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.12.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.12.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.12.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.12.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.12.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.12.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.12.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.12.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.12.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.12.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.12.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.12.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.12.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.12.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.13.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.13.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.13.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.13.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.13.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.13.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.13.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.13.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.13.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.13.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.13.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.13.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.13.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.13.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.13.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.13.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.14.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.14.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.14.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.14.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.14.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.14.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.14.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.14.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.14.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.14.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.14.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.14.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.14.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.14.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.14.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.14.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.15.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.15.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.15.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.15.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.15.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.15.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.15.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.15.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.15.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.15.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.15.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.15.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.15.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.15.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.15.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.15.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.16.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.16.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.16.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.16.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.16.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.16.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.16.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.16.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.16.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.16.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.16.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.16.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.16.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.16.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.16.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.16.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.17.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.17.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.17.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.17.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.17.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.17.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.17.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.17.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.17.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.17.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.17.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.17.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.17.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.17.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.17.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.17.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.18.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.18.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.18.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.18.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.18.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.18.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.18.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.18.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.18.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.18.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.18.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.18.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.18.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.18.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.18.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.18.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.19.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.19.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.19.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.19.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.19.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.19.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.19.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.19.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.19.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.19.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.19.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.19.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.19.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.19.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.19.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.19.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.2.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.2.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.2.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.2.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.2.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.2.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.2.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.2.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.2.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.2.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.2.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.2.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.2.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.2.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.2.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.2.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.20.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.20.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.20.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.20.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.20.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.20.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.20.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.20.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.20.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.20.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.20.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.20.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.20.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.20.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.20.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.20.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.21.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.21.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.21.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.21.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.21.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.21.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.21.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.21.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.21.layer_norm1.bias": "model-00002-of-00002.safetensors",
"layers.21.layer_norm1.weight": "model-00002-of-00002.safetensors",
"layers.21.layer_norm2.bias": "model-00002-of-00002.safetensors",
"layers.21.layer_norm2.weight": "model-00002-of-00002.safetensors",
"layers.21.mlp.0.bias": "model-00002-of-00002.safetensors",
"layers.21.mlp.0.weight": "model-00002-of-00002.safetensors",
"layers.21.mlp.2.bias": "model-00002-of-00002.safetensors",
"layers.21.mlp.2.weight": "model-00002-of-00002.safetensors",
"layers.22.attention.k_proj.bias": "model-00002-of-00002.safetensors",
"layers.22.attention.k_proj.weight": "model-00002-of-00002.safetensors",
"layers.22.attention.out_proj.bias": "model-00002-of-00002.safetensors",
"layers.22.attention.out_proj.weight": "model-00002-of-00002.safetensors",
"layers.22.attention.q_proj.bias": "model-00002-of-00002.safetensors",
"layers.22.attention.q_proj.weight": "model-00002-of-00002.safetensors",
"layers.22.attention.v_proj.bias": "model-00002-of-00002.safetensors",
"layers.22.attention.v_proj.weight": "model-00002-of-00002.safetensors",
"layers.22.layer_norm1.bias": "model-00002-of-00002.safetensors",
"layers.22.layer_norm1.weight": "model-00002-of-00002.safetensors",
"layers.22.layer_norm2.bias": "model-00002-of-00002.safetensors",
"layers.22.layer_norm2.weight": "model-00002-of-00002.safetensors",
"layers.22.mlp.0.bias": "model-00002-of-00002.safetensors",
"layers.22.mlp.0.weight": "model-00002-of-00002.safetensors",
"layers.22.mlp.2.bias": "model-00002-of-00002.safetensors",
"layers.22.mlp.2.weight": "model-00002-of-00002.safetensors",
"layers.23.attention.k_proj.bias": "model-00002-of-00002.safetensors",
"layers.23.attention.k_proj.weight": "model-00002-of-00002.safetensors",
"layers.23.attention.out_proj.bias": "model-00002-of-00002.safetensors",
"layers.23.attention.out_proj.weight": "model-00002-of-00002.safetensors",
"layers.23.attention.q_proj.bias": "model-00002-of-00002.safetensors",
"layers.23.attention.q_proj.weight": "model-00002-of-00002.safetensors",
"layers.23.attention.v_proj.bias": "model-00002-of-00002.safetensors",
"layers.23.attention.v_proj.weight": "model-00002-of-00002.safetensors",
"layers.23.layer_norm1.bias": "model-00002-of-00002.safetensors",
"layers.23.layer_norm1.weight": "model-00002-of-00002.safetensors",
"layers.23.layer_norm2.bias": "model-00002-of-00002.safetensors",
"layers.23.layer_norm2.weight": "model-00002-of-00002.safetensors",
"layers.23.mlp.0.bias": "model-00002-of-00002.safetensors",
"layers.23.mlp.0.weight": "model-00002-of-00002.safetensors",
"layers.23.mlp.2.bias": "model-00002-of-00002.safetensors",
"layers.23.mlp.2.weight": "model-00002-of-00002.safetensors",
"layers.3.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.3.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.3.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.3.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.3.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.3.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.3.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.3.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.3.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.3.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.3.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.3.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.3.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.3.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.3.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.3.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.4.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.4.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.4.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.4.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.4.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.4.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.4.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.4.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.4.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.4.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.4.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.4.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.4.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.4.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.4.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.4.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.5.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.5.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.5.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.5.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.5.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.5.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.5.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.5.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.5.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.5.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.5.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.5.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.5.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.5.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.5.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.5.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.6.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.6.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.6.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.6.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.6.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.6.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.6.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.6.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.6.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.6.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.6.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.6.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.6.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.6.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.6.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.6.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.7.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.7.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.7.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.7.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.7.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.7.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.7.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.7.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.7.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.7.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.7.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.7.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.7.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.7.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.7.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.7.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.8.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.8.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.8.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.8.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.8.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.8.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.8.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.8.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.8.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.8.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.8.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.8.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.8.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.8.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.8.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.8.mlp.2.weight": "model-00001-of-00002.safetensors",
"layers.9.attention.k_proj.bias": "model-00001-of-00002.safetensors",
"layers.9.attention.k_proj.weight": "model-00001-of-00002.safetensors",
"layers.9.attention.out_proj.bias": "model-00001-of-00002.safetensors",
"layers.9.attention.out_proj.weight": "model-00001-of-00002.safetensors",
"layers.9.attention.q_proj.bias": "model-00001-of-00002.safetensors",
"layers.9.attention.q_proj.weight": "model-00001-of-00002.safetensors",
"layers.9.attention.v_proj.bias": "model-00001-of-00002.safetensors",
"layers.9.attention.v_proj.weight": "model-00001-of-00002.safetensors",
"layers.9.layer_norm1.bias": "model-00001-of-00002.safetensors",
"layers.9.layer_norm1.weight": "model-00001-of-00002.safetensors",
"layers.9.layer_norm2.bias": "model-00001-of-00002.safetensors",
"layers.9.layer_norm2.weight": "model-00001-of-00002.safetensors",
"layers.9.mlp.0.bias": "model-00001-of-00002.safetensors",
"layers.9.mlp.0.weight": "model-00001-of-00002.safetensors",
"layers.9.mlp.2.bias": "model-00001-of-00002.safetensors",
"layers.9.mlp.2.weight": "model-00001-of-00002.safetensors",
"output_head.bias": "model-00002-of-00002.safetensors",
"output_head.weight": "model-00002-of-00002.safetensors",
"position_embedding.weight": "model-00001-of-00002.safetensors"
}
}
|