File size: 39,496 Bytes
09f7b1e |
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 |
{
"metadata": {
"total_size": 2908701696
},
"weight_map": {
"embedder.embeddings.LayerNorm.bias": "model-00010-of-00010.safetensors",
"embedder.embeddings.LayerNorm.weight": "model-00010-of-00010.safetensors",
"embedder.embeddings.position_embeddings.weight": "model-00010-of-00010.safetensors",
"embedder.embeddings.word_embeddings.weight": "model-00009-of-00010.safetensors",
"embedder.transformer.layer.0.attention.k_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.k_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.out_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.out_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.q_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.q_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.v_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.attention.v_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.ffn.lin1.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.ffn.lin1.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.ffn.lin2.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.ffn.lin2.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.output_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.output_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.0.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.k_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.k_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.out_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.out_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.q_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.q_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.v_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.attention.v_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.ffn.lin1.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.ffn.lin1.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.ffn.lin2.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.ffn.lin2.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.output_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.output_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.1.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.k_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.k_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.out_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.out_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.q_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.q_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.v_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.attention.v_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.ffn.lin1.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.ffn.lin1.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.ffn.lin2.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.ffn.lin2.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.output_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.output_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.2.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.k_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.k_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.out_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.out_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.q_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.q_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.v_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.attention.v_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.ffn.lin1.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.ffn.lin1.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.ffn.lin2.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.ffn.lin2.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.output_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.output_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.3.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.k_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.k_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.out_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.out_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.q_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.q_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.v_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.attention.v_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.ffn.lin1.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.ffn.lin1.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.ffn.lin2.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.ffn.lin2.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.output_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.output_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.4.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.k_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.k_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.out_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.out_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.q_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.q_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.v_lin.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.attention.v_lin.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.ffn.lin1.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.ffn.lin1.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.ffn.lin2.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.ffn.lin2.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.output_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.output_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.sa_layer_norm.bias": "model-00010-of-00010.safetensors",
"embedder.transformer.layer.5.sa_layer_norm.weight": "model-00010-of-00010.safetensors",
"embedding_transform.0.bias": "model-00008-of-00010.safetensors",
"embedding_transform.0.weight": "model-00008-of-00010.safetensors",
"embedding_transform.3.bias": "model-00008-of-00010.safetensors",
"embedding_transform.3.weight": "model-00008-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.1.EncDecAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.2.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.0.layer.2.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.1.EncDecAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.1.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.10.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.2.DenseReluDense.wo.weight": "model-00006-of-00010.safetensors",
"encoder_decoder.decoder.block.11.layer.2.layer_norm.weight": "model-00006-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.2.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.3.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.4.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wi_1.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.2.DenseReluDense.wo.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.5.layer.2.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.0.SelfAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.0.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.k.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.o.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.q.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.1.EncDecAttention.v.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.1.layer_norm.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi_0.weight": "model-00004-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.6.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.7.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.8.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.0.SelfAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.0.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.k.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.o.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.q.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.1.EncDecAttention.v.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.1.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi_0.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wi_1.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.2.DenseReluDense.wo.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.block.9.layer.2.layer_norm.weight": "model-00005-of-00010.safetensors",
"encoder_decoder.decoder.final_layer_norm.weight": "model-00006-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.relative_attention_bias.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.0.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.1.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.10.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.11.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.2.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.3.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.4.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.5.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.k.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.o.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.q.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.0.SelfAttention.v.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.0.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi_0.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wi_1.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.1.DenseReluDense.wo.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.6.layer.1.layer_norm.weight": "model-00002-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.7.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.8.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.k.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.o.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.q.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.0.SelfAttention.v.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.0.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi_0.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wi_1.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.1.DenseReluDense.wo.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.block.9.layer.1.layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.encoder.final_layer_norm.weight": "model-00003-of-00010.safetensors",
"encoder_decoder.lm_head.weight": "model-00007-of-00010.safetensors",
"encoder_decoder.shared.weight": "model-00001-of-00010.safetensors"
}
}
|