Upload folder using huggingface_hub
Browse filesThis view is limited to 50 files because it contains too many changes. See raw diff
- config.json +398 -454
- model-00001-of-00098.safetensors +3 -0
- model-00002-of-00098.safetensors +3 -0
- model-00003-of-00098.safetensors +3 -0
- model-00004-of-00098.safetensors +3 -0
- model-00005-of-00098.safetensors +3 -0
- model-00006-of-00098.safetensors +3 -0
- model-00007-of-00098.safetensors +3 -0
- model-00008-of-00098.safetensors +3 -0
- model-00009-of-00098.safetensors +3 -0
- model-00010-of-00098.safetensors +3 -0
- model-00011-of-00098.safetensors +3 -0
- model-00012-of-00098.safetensors +3 -0
- model-00013-of-00098.safetensors +3 -0
- model-00014-of-00098.safetensors +3 -0
- model-00015-of-00098.safetensors +3 -0
- model-00016-of-00098.safetensors +3 -0
- model-00017-of-00098.safetensors +3 -0
- model-00018-of-00098.safetensors +3 -0
- model-00019-of-00098.safetensors +3 -0
- model-00020-of-00098.safetensors +3 -0
- model-00021-of-00098.safetensors +3 -0
- model-00022-of-00098.safetensors +3 -0
- model-00023-of-00098.safetensors +3 -0
- model-00024-of-00098.safetensors +3 -0
- model-00025-of-00098.safetensors +3 -0
- model-00026-of-00098.safetensors +3 -0
- model-00027-of-00098.safetensors +3 -0
- model-00028-of-00098.safetensors +3 -0
- model-00029-of-00098.safetensors +3 -0
- model-00030-of-00098.safetensors +3 -0
- model-00031-of-00098.safetensors +3 -0
- model-00032-of-00098.safetensors +3 -0
- model-00033-of-00098.safetensors +3 -0
- model-00034-of-00098.safetensors +3 -0
- model-00035-of-00098.safetensors +3 -0
- model-00036-of-00098.safetensors +3 -0
- model-00037-of-00098.safetensors +3 -0
- model-00038-of-00098.safetensors +3 -0
- model-00039-of-00098.safetensors +3 -0
- model-00040-of-00098.safetensors +3 -0
- model-00041-of-00098.safetensors +3 -0
- model-00042-of-00098.safetensors +3 -0
- model-00043-of-00098.safetensors +3 -0
- model-00044-of-00098.safetensors +3 -0
- model-00045-of-00098.safetensors +3 -0
- model-00046-of-00098.safetensors +3 -0
- model-00047-of-00098.safetensors +3 -0
- model-00048-of-00098.safetensors +3 -0
- model-00049-of-00098.safetensors +3 -0
config.json
CHANGED
|
@@ -159,76 +159,26 @@
|
|
| 159 |
"bits": 16,
|
| 160 |
"data_type": "float"
|
| 161 |
},
|
| 162 |
-
".*layers\\.46.*": {
|
| 163 |
-
"bits": 8
|
| 164 |
-
},
|
| 165 |
-
".*layers\\.47.*": {
|
| 166 |
-
"bits": 8
|
| 167 |
-
},
|
| 168 |
-
".*mlp.*": {
|
| 169 |
-
"bits": 8
|
| 170 |
-
},
|
| 171 |
".*moe\\.gate.*": {
|
| 172 |
"bits": 16,
|
| 173 |
"data_type": "float"
|
| 174 |
},
|
| 175 |
-
".*
|
| 176 |
-
"bits":
|
|
|
|
| 177 |
},
|
| 178 |
".*shared_head.*": {
|
| 179 |
"bits": 16,
|
| 180 |
"data_type": "float"
|
| 181 |
},
|
| 182 |
-
"model.layers.0.mlp.down_proj": {
|
| 183 |
-
"bits": 8
|
| 184 |
-
},
|
| 185 |
-
"model.layers.0.mlp.gate_proj": {
|
| 186 |
-
"bits": 8
|
| 187 |
-
},
|
| 188 |
-
"model.layers.0.mlp.up_proj": {
|
| 189 |
-
"bits": 8
|
| 190 |
-
},
|
| 191 |
"model.layers.0.self_attn.g_proj": {
|
| 192 |
"bits": 16,
|
| 193 |
"data_type": "float"
|
| 194 |
},
|
| 195 |
-
"model.layers.0.self_attn.k_proj": {
|
| 196 |
-
"bits": 8
|
| 197 |
-
},
|
| 198 |
-
"model.layers.0.self_attn.o_proj": {
|
| 199 |
-
"bits": 8
|
| 200 |
-
},
|
| 201 |
-
"model.layers.0.self_attn.q_proj": {
|
| 202 |
-
"bits": 8
|
| 203 |
-
},
|
| 204 |
-
"model.layers.0.self_attn.v_proj": {
|
| 205 |
-
"bits": 8
|
| 206 |
-
},
|
| 207 |
-
"model.layers.1.mlp.down_proj": {
|
| 208 |
-
"bits": 8
|
| 209 |
-
},
|
| 210 |
-
"model.layers.1.mlp.gate_proj": {
|
| 211 |
-
"bits": 8
|
| 212 |
-
},
|
| 213 |
-
"model.layers.1.mlp.up_proj": {
|
| 214 |
-
"bits": 8
|
| 215 |
-
},
|
| 216 |
"model.layers.1.self_attn.g_proj": {
|
| 217 |
"bits": 16,
|
| 218 |
"data_type": "float"
|
| 219 |
},
|
| 220 |
-
"model.layers.1.self_attn.k_proj": {
|
| 221 |
-
"bits": 8
|
| 222 |
-
},
|
| 223 |
-
"model.layers.1.self_attn.o_proj": {
|
| 224 |
-
"bits": 8
|
| 225 |
-
},
|
| 226 |
-
"model.layers.1.self_attn.q_proj": {
|
| 227 |
-
"bits": 8
|
| 228 |
-
},
|
| 229 |
-
"model.layers.1.self_attn.v_proj": {
|
| 230 |
-
"bits": 8
|
| 231 |
-
},
|
| 232 |
"model.layers.10.moe.gate": {
|
| 233 |
"bits": 16,
|
| 234 |
"data_type": "float"
|
|
@@ -237,17 +187,17 @@
|
|
| 237 |
"bits": 16,
|
| 238 |
"data_type": "float"
|
| 239 |
},
|
| 240 |
-
"model.layers.10.
|
| 241 |
-
"bits":
|
| 242 |
-
|
| 243 |
-
"model.layers.10.self_attn.o_proj": {
|
| 244 |
-
"bits": 8
|
| 245 |
},
|
| 246 |
-
"model.layers.10.
|
| 247 |
-
"bits":
|
|
|
|
| 248 |
},
|
| 249 |
-
"model.layers.10.
|
| 250 |
-
"bits":
|
|
|
|
| 251 |
},
|
| 252 |
"model.layers.11.moe.gate": {
|
| 253 |
"bits": 16,
|
|
@@ -257,17 +207,17 @@
|
|
| 257 |
"bits": 16,
|
| 258 |
"data_type": "float"
|
| 259 |
},
|
| 260 |
-
"model.layers.11.
|
| 261 |
-
"bits":
|
| 262 |
-
|
| 263 |
-
"model.layers.11.self_attn.o_proj": {
|
| 264 |
-
"bits": 8
|
| 265 |
},
|
| 266 |
-
"model.layers.11.
|
| 267 |
-
"bits":
|
|
|
|
| 268 |
},
|
| 269 |
-
"model.layers.11.
|
| 270 |
-
"bits":
|
|
|
|
| 271 |
},
|
| 272 |
"model.layers.12.moe.gate": {
|
| 273 |
"bits": 16,
|
|
@@ -277,17 +227,17 @@
|
|
| 277 |
"bits": 16,
|
| 278 |
"data_type": "float"
|
| 279 |
},
|
| 280 |
-
"model.layers.12.
|
| 281 |
-
"bits":
|
| 282 |
-
|
| 283 |
-
"model.layers.12.self_attn.o_proj": {
|
| 284 |
-
"bits": 8
|
| 285 |
},
|
| 286 |
-
"model.layers.12.
|
| 287 |
-
"bits":
|
|
|
|
| 288 |
},
|
| 289 |
-
"model.layers.12.
|
| 290 |
-
"bits":
|
|
|
|
| 291 |
},
|
| 292 |
"model.layers.13.moe.gate": {
|
| 293 |
"bits": 16,
|
|
@@ -297,17 +247,17 @@
|
|
| 297 |
"bits": 16,
|
| 298 |
"data_type": "float"
|
| 299 |
},
|
| 300 |
-
"model.layers.13.
|
| 301 |
-
"bits":
|
| 302 |
-
|
| 303 |
-
"model.layers.13.self_attn.o_proj": {
|
| 304 |
-
"bits": 8
|
| 305 |
},
|
| 306 |
-
"model.layers.13.
|
| 307 |
-
"bits":
|
|
|
|
| 308 |
},
|
| 309 |
-
"model.layers.13.
|
| 310 |
-
"bits":
|
|
|
|
| 311 |
},
|
| 312 |
"model.layers.14.moe.gate": {
|
| 313 |
"bits": 16,
|
|
@@ -317,17 +267,17 @@
|
|
| 317 |
"bits": 16,
|
| 318 |
"data_type": "float"
|
| 319 |
},
|
| 320 |
-
"model.layers.14.
|
| 321 |
-
"bits":
|
| 322 |
-
|
| 323 |
-
"model.layers.14.self_attn.o_proj": {
|
| 324 |
-
"bits": 8
|
| 325 |
},
|
| 326 |
-
"model.layers.14.
|
| 327 |
-
"bits":
|
|
|
|
| 328 |
},
|
| 329 |
-
"model.layers.14.
|
| 330 |
-
"bits":
|
|
|
|
| 331 |
},
|
| 332 |
"model.layers.15.moe.gate": {
|
| 333 |
"bits": 16,
|
|
@@ -337,17 +287,17 @@
|
|
| 337 |
"bits": 16,
|
| 338 |
"data_type": "float"
|
| 339 |
},
|
| 340 |
-
"model.layers.15.
|
| 341 |
-
"bits":
|
| 342 |
-
|
| 343 |
-
"model.layers.15.self_attn.o_proj": {
|
| 344 |
-
"bits": 8
|
| 345 |
},
|
| 346 |
-
"model.layers.15.
|
| 347 |
-
"bits":
|
|
|
|
| 348 |
},
|
| 349 |
-
"model.layers.15.
|
| 350 |
-
"bits":
|
|
|
|
| 351 |
},
|
| 352 |
"model.layers.16.moe.gate": {
|
| 353 |
"bits": 16,
|
|
@@ -357,17 +307,17 @@
|
|
| 357 |
"bits": 16,
|
| 358 |
"data_type": "float"
|
| 359 |
},
|
| 360 |
-
"model.layers.16.
|
| 361 |
-
"bits":
|
| 362 |
-
|
| 363 |
-
"model.layers.16.self_attn.o_proj": {
|
| 364 |
-
"bits": 8
|
| 365 |
},
|
| 366 |
-
"model.layers.16.
|
| 367 |
-
"bits":
|
|
|
|
| 368 |
},
|
| 369 |
-
"model.layers.16.
|
| 370 |
-
"bits":
|
|
|
|
| 371 |
},
|
| 372 |
"model.layers.17.moe.gate": {
|
| 373 |
"bits": 16,
|
|
@@ -377,17 +327,17 @@
|
|
| 377 |
"bits": 16,
|
| 378 |
"data_type": "float"
|
| 379 |
},
|
| 380 |
-
"model.layers.17.
|
| 381 |
-
"bits":
|
| 382 |
-
|
| 383 |
-
"model.layers.17.self_attn.o_proj": {
|
| 384 |
-
"bits": 8
|
| 385 |
},
|
| 386 |
-
"model.layers.17.
|
| 387 |
-
"bits":
|
|
|
|
| 388 |
},
|
| 389 |
-
"model.layers.17.
|
| 390 |
-
"bits":
|
|
|
|
| 391 |
},
|
| 392 |
"model.layers.18.moe.gate": {
|
| 393 |
"bits": 16,
|
|
@@ -397,17 +347,17 @@
|
|
| 397 |
"bits": 16,
|
| 398 |
"data_type": "float"
|
| 399 |
},
|
| 400 |
-
"model.layers.18.
|
| 401 |
-
"bits":
|
| 402 |
-
|
| 403 |
-
"model.layers.18.self_attn.o_proj": {
|
| 404 |
-
"bits": 8
|
| 405 |
},
|
| 406 |
-
"model.layers.18.
|
| 407 |
-
"bits":
|
|
|
|
| 408 |
},
|
| 409 |
-
"model.layers.18.
|
| 410 |
-
"bits":
|
|
|
|
| 411 |
},
|
| 412 |
"model.layers.19.moe.gate": {
|
| 413 |
"bits": 16,
|
|
@@ -417,43 +367,22 @@
|
|
| 417 |
"bits": 16,
|
| 418 |
"data_type": "float"
|
| 419 |
},
|
| 420 |
-
"model.layers.19.
|
| 421 |
-
"bits":
|
| 422 |
-
|
| 423 |
-
"model.layers.19.self_attn.o_proj": {
|
| 424 |
-
"bits": 8
|
| 425 |
-
},
|
| 426 |
-
"model.layers.19.self_attn.q_proj": {
|
| 427 |
-
"bits": 8
|
| 428 |
-
},
|
| 429 |
-
"model.layers.19.self_attn.v_proj": {
|
| 430 |
-
"bits": 8
|
| 431 |
-
},
|
| 432 |
-
"model.layers.2.mlp.down_proj": {
|
| 433 |
-
"bits": 8
|
| 434 |
},
|
| 435 |
-
"model.layers.
|
| 436 |
-
"bits":
|
|
|
|
| 437 |
},
|
| 438 |
-
"model.layers.
|
| 439 |
-
"bits":
|
|
|
|
| 440 |
},
|
| 441 |
"model.layers.2.self_attn.g_proj": {
|
| 442 |
"bits": 16,
|
| 443 |
"data_type": "float"
|
| 444 |
},
|
| 445 |
-
"model.layers.2.self_attn.k_proj": {
|
| 446 |
-
"bits": 8
|
| 447 |
-
},
|
| 448 |
-
"model.layers.2.self_attn.o_proj": {
|
| 449 |
-
"bits": 8
|
| 450 |
-
},
|
| 451 |
-
"model.layers.2.self_attn.q_proj": {
|
| 452 |
-
"bits": 8
|
| 453 |
-
},
|
| 454 |
-
"model.layers.2.self_attn.v_proj": {
|
| 455 |
-
"bits": 8
|
| 456 |
-
},
|
| 457 |
"model.layers.20.moe.gate": {
|
| 458 |
"bits": 16,
|
| 459 |
"data_type": "float"
|
|
@@ -462,17 +391,17 @@
|
|
| 462 |
"bits": 16,
|
| 463 |
"data_type": "float"
|
| 464 |
},
|
| 465 |
-
"model.layers.20.
|
| 466 |
-
"bits":
|
| 467 |
-
|
| 468 |
-
"model.layers.20.self_attn.o_proj": {
|
| 469 |
-
"bits": 8
|
| 470 |
},
|
| 471 |
-
"model.layers.20.
|
| 472 |
-
"bits":
|
|
|
|
| 473 |
},
|
| 474 |
-
"model.layers.20.
|
| 475 |
-
"bits":
|
|
|
|
| 476 |
},
|
| 477 |
"model.layers.21.moe.gate": {
|
| 478 |
"bits": 16,
|
|
@@ -482,17 +411,17 @@
|
|
| 482 |
"bits": 16,
|
| 483 |
"data_type": "float"
|
| 484 |
},
|
| 485 |
-
"model.layers.21.
|
| 486 |
-
"bits":
|
| 487 |
-
|
| 488 |
-
"model.layers.21.self_attn.o_proj": {
|
| 489 |
-
"bits": 8
|
| 490 |
},
|
| 491 |
-
"model.layers.21.
|
| 492 |
-
"bits":
|
|
|
|
| 493 |
},
|
| 494 |
-
"model.layers.21.
|
| 495 |
-
"bits":
|
|
|
|
| 496 |
},
|
| 497 |
"model.layers.22.moe.gate": {
|
| 498 |
"bits": 16,
|
|
@@ -502,17 +431,17 @@
|
|
| 502 |
"bits": 16,
|
| 503 |
"data_type": "float"
|
| 504 |
},
|
| 505 |
-
"model.layers.22.
|
| 506 |
-
"bits":
|
| 507 |
-
|
| 508 |
-
"model.layers.22.self_attn.o_proj": {
|
| 509 |
-
"bits": 8
|
| 510 |
},
|
| 511 |
-
"model.layers.22.
|
| 512 |
-
"bits":
|
|
|
|
| 513 |
},
|
| 514 |
-
"model.layers.22.
|
| 515 |
-
"bits":
|
|
|
|
| 516 |
},
|
| 517 |
"model.layers.23.moe.gate": {
|
| 518 |
"bits": 16,
|
|
@@ -522,17 +451,17 @@
|
|
| 522 |
"bits": 16,
|
| 523 |
"data_type": "float"
|
| 524 |
},
|
| 525 |
-
"model.layers.23.
|
| 526 |
-
"bits":
|
| 527 |
-
|
| 528 |
-
"model.layers.23.self_attn.o_proj": {
|
| 529 |
-
"bits": 8
|
| 530 |
},
|
| 531 |
-
"model.layers.23.
|
| 532 |
-
"bits":
|
|
|
|
| 533 |
},
|
| 534 |
-
"model.layers.23.
|
| 535 |
-
"bits":
|
|
|
|
| 536 |
},
|
| 537 |
"model.layers.24.moe.gate": {
|
| 538 |
"bits": 16,
|
|
@@ -542,17 +471,17 @@
|
|
| 542 |
"bits": 16,
|
| 543 |
"data_type": "float"
|
| 544 |
},
|
| 545 |
-
"model.layers.24.
|
| 546 |
-
"bits":
|
| 547 |
-
|
| 548 |
-
"model.layers.24.self_attn.o_proj": {
|
| 549 |
-
"bits": 8
|
| 550 |
},
|
| 551 |
-
"model.layers.24.
|
| 552 |
-
"bits":
|
|
|
|
| 553 |
},
|
| 554 |
-
"model.layers.24.
|
| 555 |
-
"bits":
|
|
|
|
| 556 |
},
|
| 557 |
"model.layers.25.moe.gate": {
|
| 558 |
"bits": 16,
|
|
@@ -562,17 +491,17 @@
|
|
| 562 |
"bits": 16,
|
| 563 |
"data_type": "float"
|
| 564 |
},
|
| 565 |
-
"model.layers.25.
|
| 566 |
-
"bits":
|
| 567 |
-
|
| 568 |
-
"model.layers.25.self_attn.o_proj": {
|
| 569 |
-
"bits": 8
|
| 570 |
},
|
| 571 |
-
"model.layers.25.
|
| 572 |
-
"bits":
|
|
|
|
| 573 |
},
|
| 574 |
-
"model.layers.25.
|
| 575 |
-
"bits":
|
|
|
|
| 576 |
},
|
| 577 |
"model.layers.26.moe.gate": {
|
| 578 |
"bits": 16,
|
|
@@ -582,17 +511,17 @@
|
|
| 582 |
"bits": 16,
|
| 583 |
"data_type": "float"
|
| 584 |
},
|
| 585 |
-
"model.layers.26.
|
| 586 |
-
"bits":
|
| 587 |
-
|
| 588 |
-
"model.layers.26.self_attn.o_proj": {
|
| 589 |
-
"bits": 8
|
| 590 |
},
|
| 591 |
-
"model.layers.26.
|
| 592 |
-
"bits":
|
|
|
|
| 593 |
},
|
| 594 |
-
"model.layers.26.
|
| 595 |
-
"bits":
|
|
|
|
| 596 |
},
|
| 597 |
"model.layers.27.moe.gate": {
|
| 598 |
"bits": 16,
|
|
@@ -602,17 +531,17 @@
|
|
| 602 |
"bits": 16,
|
| 603 |
"data_type": "float"
|
| 604 |
},
|
| 605 |
-
"model.layers.27.
|
| 606 |
-
"bits":
|
| 607 |
-
|
| 608 |
-
"model.layers.27.self_attn.o_proj": {
|
| 609 |
-
"bits": 8
|
| 610 |
},
|
| 611 |
-
"model.layers.27.
|
| 612 |
-
"bits":
|
|
|
|
| 613 |
},
|
| 614 |
-
"model.layers.27.
|
| 615 |
-
"bits":
|
|
|
|
| 616 |
},
|
| 617 |
"model.layers.28.moe.gate": {
|
| 618 |
"bits": 16,
|
|
@@ -622,17 +551,17 @@
|
|
| 622 |
"bits": 16,
|
| 623 |
"data_type": "float"
|
| 624 |
},
|
| 625 |
-
"model.layers.28.
|
| 626 |
-
"bits":
|
| 627 |
-
|
| 628 |
-
"model.layers.28.self_attn.o_proj": {
|
| 629 |
-
"bits": 8
|
| 630 |
},
|
| 631 |
-
"model.layers.28.
|
| 632 |
-
"bits":
|
|
|
|
| 633 |
},
|
| 634 |
-
"model.layers.28.
|
| 635 |
-
"bits":
|
|
|
|
| 636 |
},
|
| 637 |
"model.layers.29.moe.gate": {
|
| 638 |
"bits": 16,
|
|
@@ -642,17 +571,17 @@
|
|
| 642 |
"bits": 16,
|
| 643 |
"data_type": "float"
|
| 644 |
},
|
| 645 |
-
"model.layers.29.
|
| 646 |
-
"bits":
|
| 647 |
-
|
| 648 |
-
"model.layers.29.self_attn.o_proj": {
|
| 649 |
-
"bits": 8
|
| 650 |
},
|
| 651 |
-
"model.layers.29.
|
| 652 |
-
"bits":
|
|
|
|
| 653 |
},
|
| 654 |
-
"model.layers.29.
|
| 655 |
-
"bits":
|
|
|
|
| 656 |
},
|
| 657 |
"model.layers.3.moe.gate": {
|
| 658 |
"bits": 16,
|
|
@@ -662,17 +591,17 @@
|
|
| 662 |
"bits": 16,
|
| 663 |
"data_type": "float"
|
| 664 |
},
|
| 665 |
-
"model.layers.3.
|
| 666 |
-
"bits":
|
| 667 |
-
|
| 668 |
-
"model.layers.3.self_attn.o_proj": {
|
| 669 |
-
"bits": 8
|
| 670 |
},
|
| 671 |
-
"model.layers.3.
|
| 672 |
-
"bits":
|
|
|
|
| 673 |
},
|
| 674 |
-
"model.layers.3.
|
| 675 |
-
"bits":
|
|
|
|
| 676 |
},
|
| 677 |
"model.layers.30.moe.gate": {
|
| 678 |
"bits": 16,
|
|
@@ -682,17 +611,17 @@
|
|
| 682 |
"bits": 16,
|
| 683 |
"data_type": "float"
|
| 684 |
},
|
| 685 |
-
"model.layers.30.
|
| 686 |
-
"bits":
|
| 687 |
-
|
| 688 |
-
"model.layers.30.self_attn.o_proj": {
|
| 689 |
-
"bits": 8
|
| 690 |
},
|
| 691 |
-
"model.layers.30.
|
| 692 |
-
"bits":
|
|
|
|
| 693 |
},
|
| 694 |
-
"model.layers.30.
|
| 695 |
-
"bits":
|
|
|
|
| 696 |
},
|
| 697 |
"model.layers.31.moe.gate": {
|
| 698 |
"bits": 16,
|
|
@@ -702,17 +631,17 @@
|
|
| 702 |
"bits": 16,
|
| 703 |
"data_type": "float"
|
| 704 |
},
|
| 705 |
-
"model.layers.31.
|
| 706 |
-
"bits":
|
| 707 |
-
|
| 708 |
-
"model.layers.31.self_attn.o_proj": {
|
| 709 |
-
"bits": 8
|
| 710 |
},
|
| 711 |
-
"model.layers.31.
|
| 712 |
-
"bits":
|
|
|
|
| 713 |
},
|
| 714 |
-
"model.layers.31.
|
| 715 |
-
"bits":
|
|
|
|
| 716 |
},
|
| 717 |
"model.layers.32.moe.gate": {
|
| 718 |
"bits": 16,
|
|
@@ -722,17 +651,17 @@
|
|
| 722 |
"bits": 16,
|
| 723 |
"data_type": "float"
|
| 724 |
},
|
| 725 |
-
"model.layers.32.
|
| 726 |
-
"bits":
|
| 727 |
-
|
| 728 |
-
"model.layers.32.self_attn.o_proj": {
|
| 729 |
-
"bits": 8
|
| 730 |
},
|
| 731 |
-
"model.layers.32.
|
| 732 |
-
"bits":
|
|
|
|
| 733 |
},
|
| 734 |
-
"model.layers.32.
|
| 735 |
-
"bits":
|
|
|
|
| 736 |
},
|
| 737 |
"model.layers.33.moe.gate": {
|
| 738 |
"bits": 16,
|
|
@@ -742,17 +671,17 @@
|
|
| 742 |
"bits": 16,
|
| 743 |
"data_type": "float"
|
| 744 |
},
|
| 745 |
-
"model.layers.33.
|
| 746 |
-
"bits":
|
| 747 |
-
|
| 748 |
-
"model.layers.33.self_attn.o_proj": {
|
| 749 |
-
"bits": 8
|
| 750 |
},
|
| 751 |
-
"model.layers.33.
|
| 752 |
-
"bits":
|
|
|
|
| 753 |
},
|
| 754 |
-
"model.layers.33.
|
| 755 |
-
"bits":
|
|
|
|
| 756 |
},
|
| 757 |
"model.layers.34.moe.gate": {
|
| 758 |
"bits": 16,
|
|
@@ -762,17 +691,17 @@
|
|
| 762 |
"bits": 16,
|
| 763 |
"data_type": "float"
|
| 764 |
},
|
| 765 |
-
"model.layers.34.
|
| 766 |
-
"bits":
|
| 767 |
-
|
| 768 |
-
"model.layers.34.self_attn.o_proj": {
|
| 769 |
-
"bits": 8
|
| 770 |
},
|
| 771 |
-
"model.layers.34.
|
| 772 |
-
"bits":
|
|
|
|
| 773 |
},
|
| 774 |
-
"model.layers.34.
|
| 775 |
-
"bits":
|
|
|
|
| 776 |
},
|
| 777 |
"model.layers.35.moe.gate": {
|
| 778 |
"bits": 16,
|
|
@@ -782,17 +711,17 @@
|
|
| 782 |
"bits": 16,
|
| 783 |
"data_type": "float"
|
| 784 |
},
|
| 785 |
-
"model.layers.35.
|
| 786 |
-
"bits":
|
| 787 |
-
|
| 788 |
-
"model.layers.35.self_attn.o_proj": {
|
| 789 |
-
"bits": 8
|
| 790 |
},
|
| 791 |
-
"model.layers.35.
|
| 792 |
-
"bits":
|
|
|
|
| 793 |
},
|
| 794 |
-
"model.layers.35.
|
| 795 |
-
"bits":
|
|
|
|
| 796 |
},
|
| 797 |
"model.layers.36.moe.gate": {
|
| 798 |
"bits": 16,
|
|
@@ -802,17 +731,17 @@
|
|
| 802 |
"bits": 16,
|
| 803 |
"data_type": "float"
|
| 804 |
},
|
| 805 |
-
"model.layers.36.
|
| 806 |
-
"bits":
|
| 807 |
-
|
| 808 |
-
"model.layers.36.self_attn.o_proj": {
|
| 809 |
-
"bits": 8
|
| 810 |
},
|
| 811 |
-
"model.layers.36.
|
| 812 |
-
"bits":
|
|
|
|
| 813 |
},
|
| 814 |
-
"model.layers.36.
|
| 815 |
-
"bits":
|
|
|
|
| 816 |
},
|
| 817 |
"model.layers.37.moe.gate": {
|
| 818 |
"bits": 16,
|
|
@@ -822,17 +751,17 @@
|
|
| 822 |
"bits": 16,
|
| 823 |
"data_type": "float"
|
| 824 |
},
|
| 825 |
-
"model.layers.37.
|
| 826 |
-
"bits":
|
| 827 |
-
|
| 828 |
-
"model.layers.37.self_attn.o_proj": {
|
| 829 |
-
"bits": 8
|
| 830 |
},
|
| 831 |
-
"model.layers.37.
|
| 832 |
-
"bits":
|
|
|
|
| 833 |
},
|
| 834 |
-
"model.layers.37.
|
| 835 |
-
"bits":
|
|
|
|
| 836 |
},
|
| 837 |
"model.layers.38.moe.gate": {
|
| 838 |
"bits": 16,
|
|
@@ -842,17 +771,17 @@
|
|
| 842 |
"bits": 16,
|
| 843 |
"data_type": "float"
|
| 844 |
},
|
| 845 |
-
"model.layers.38.
|
| 846 |
-
"bits":
|
| 847 |
-
|
| 848 |
-
"model.layers.38.self_attn.o_proj": {
|
| 849 |
-
"bits": 8
|
| 850 |
},
|
| 851 |
-
"model.layers.38.
|
| 852 |
-
"bits":
|
|
|
|
| 853 |
},
|
| 854 |
-
"model.layers.38.
|
| 855 |
-
"bits":
|
|
|
|
| 856 |
},
|
| 857 |
"model.layers.39.moe.gate": {
|
| 858 |
"bits": 16,
|
|
@@ -862,17 +791,17 @@
|
|
| 862 |
"bits": 16,
|
| 863 |
"data_type": "float"
|
| 864 |
},
|
| 865 |
-
"model.layers.39.
|
| 866 |
-
"bits":
|
| 867 |
-
|
| 868 |
-
"model.layers.39.self_attn.o_proj": {
|
| 869 |
-
"bits": 8
|
| 870 |
},
|
| 871 |
-
"model.layers.39.
|
| 872 |
-
"bits":
|
|
|
|
| 873 |
},
|
| 874 |
-
"model.layers.39.
|
| 875 |
-
"bits":
|
|
|
|
| 876 |
},
|
| 877 |
"model.layers.4.moe.gate": {
|
| 878 |
"bits": 16,
|
|
@@ -882,17 +811,17 @@
|
|
| 882 |
"bits": 16,
|
| 883 |
"data_type": "float"
|
| 884 |
},
|
| 885 |
-
"model.layers.4.
|
| 886 |
-
"bits":
|
| 887 |
-
|
| 888 |
-
"model.layers.4.self_attn.o_proj": {
|
| 889 |
-
"bits": 8
|
| 890 |
},
|
| 891 |
-
"model.layers.4.
|
| 892 |
-
"bits":
|
|
|
|
| 893 |
},
|
| 894 |
-
"model.layers.4.
|
| 895 |
-
"bits":
|
|
|
|
| 896 |
},
|
| 897 |
"model.layers.40.moe.gate": {
|
| 898 |
"bits": 16,
|
|
@@ -902,17 +831,17 @@
|
|
| 902 |
"bits": 16,
|
| 903 |
"data_type": "float"
|
| 904 |
},
|
| 905 |
-
"model.layers.40.
|
| 906 |
-
"bits":
|
| 907 |
-
|
| 908 |
-
"model.layers.40.self_attn.o_proj": {
|
| 909 |
-
"bits": 8
|
| 910 |
},
|
| 911 |
-
"model.layers.40.
|
| 912 |
-
"bits":
|
|
|
|
| 913 |
},
|
| 914 |
-
"model.layers.40.
|
| 915 |
-
"bits":
|
|
|
|
| 916 |
},
|
| 917 |
"model.layers.41.moe.gate": {
|
| 918 |
"bits": 16,
|
|
@@ -922,17 +851,17 @@
|
|
| 922 |
"bits": 16,
|
| 923 |
"data_type": "float"
|
| 924 |
},
|
| 925 |
-
"model.layers.41.
|
| 926 |
-
"bits":
|
| 927 |
-
|
| 928 |
-
"model.layers.41.self_attn.o_proj": {
|
| 929 |
-
"bits": 8
|
| 930 |
},
|
| 931 |
-
"model.layers.41.
|
| 932 |
-
"bits":
|
|
|
|
| 933 |
},
|
| 934 |
-
"model.layers.41.
|
| 935 |
-
"bits":
|
|
|
|
| 936 |
},
|
| 937 |
"model.layers.42.moe.gate": {
|
| 938 |
"bits": 16,
|
|
@@ -942,17 +871,17 @@
|
|
| 942 |
"bits": 16,
|
| 943 |
"data_type": "float"
|
| 944 |
},
|
| 945 |
-
"model.layers.42.
|
| 946 |
-
"bits":
|
| 947 |
-
|
| 948 |
-
"model.layers.42.self_attn.o_proj": {
|
| 949 |
-
"bits": 8
|
| 950 |
},
|
| 951 |
-
"model.layers.42.
|
| 952 |
-
"bits":
|
|
|
|
| 953 |
},
|
| 954 |
-
"model.layers.42.
|
| 955 |
-
"bits":
|
|
|
|
| 956 |
},
|
| 957 |
"model.layers.43.moe.gate": {
|
| 958 |
"bits": 16,
|
|
@@ -962,17 +891,17 @@
|
|
| 962 |
"bits": 16,
|
| 963 |
"data_type": "float"
|
| 964 |
},
|
| 965 |
-
"model.layers.43.
|
| 966 |
-
"bits":
|
| 967 |
-
|
| 968 |
-
"model.layers.43.self_attn.o_proj": {
|
| 969 |
-
"bits": 8
|
| 970 |
},
|
| 971 |
-
"model.layers.43.
|
| 972 |
-
"bits":
|
|
|
|
| 973 |
},
|
| 974 |
-
"model.layers.43.
|
| 975 |
-
"bits":
|
|
|
|
| 976 |
},
|
| 977 |
"model.layers.44.moe.gate": {
|
| 978 |
"bits": 16,
|
|
@@ -982,17 +911,17 @@
|
|
| 982 |
"bits": 16,
|
| 983 |
"data_type": "float"
|
| 984 |
},
|
| 985 |
-
"model.layers.44.
|
| 986 |
-
"bits":
|
| 987 |
-
|
| 988 |
-
"model.layers.44.self_attn.o_proj": {
|
| 989 |
-
"bits": 8
|
| 990 |
},
|
| 991 |
-
"model.layers.44.
|
| 992 |
-
"bits":
|
|
|
|
| 993 |
},
|
| 994 |
-
"model.layers.44.
|
| 995 |
-
"bits":
|
|
|
|
| 996 |
},
|
| 997 |
"model.layers.5.moe.gate": {
|
| 998 |
"bits": 16,
|
|
@@ -1002,17 +931,17 @@
|
|
| 1002 |
"bits": 16,
|
| 1003 |
"data_type": "float"
|
| 1004 |
},
|
| 1005 |
-
"model.layers.5.
|
| 1006 |
-
"bits":
|
| 1007 |
-
|
| 1008 |
-
"model.layers.5.self_attn.o_proj": {
|
| 1009 |
-
"bits": 8
|
| 1010 |
},
|
| 1011 |
-
"model.layers.5.
|
| 1012 |
-
"bits":
|
|
|
|
| 1013 |
},
|
| 1014 |
-
"model.layers.5.
|
| 1015 |
-
"bits":
|
|
|
|
| 1016 |
},
|
| 1017 |
"model.layers.6.moe.gate": {
|
| 1018 |
"bits": 16,
|
|
@@ -1022,17 +951,17 @@
|
|
| 1022 |
"bits": 16,
|
| 1023 |
"data_type": "float"
|
| 1024 |
},
|
| 1025 |
-
"model.layers.6.
|
| 1026 |
-
"bits":
|
| 1027 |
-
|
| 1028 |
-
"model.layers.6.self_attn.o_proj": {
|
| 1029 |
-
"bits": 8
|
| 1030 |
},
|
| 1031 |
-
"model.layers.6.
|
| 1032 |
-
"bits":
|
|
|
|
| 1033 |
},
|
| 1034 |
-
"model.layers.6.
|
| 1035 |
-
"bits":
|
|
|
|
| 1036 |
},
|
| 1037 |
"model.layers.7.moe.gate": {
|
| 1038 |
"bits": 16,
|
|
@@ -1042,17 +971,17 @@
|
|
| 1042 |
"bits": 16,
|
| 1043 |
"data_type": "float"
|
| 1044 |
},
|
| 1045 |
-
"model.layers.7.
|
| 1046 |
-
"bits":
|
| 1047 |
-
|
| 1048 |
-
"model.layers.7.self_attn.o_proj": {
|
| 1049 |
-
"bits": 8
|
| 1050 |
},
|
| 1051 |
-
"model.layers.7.
|
| 1052 |
-
"bits":
|
|
|
|
| 1053 |
},
|
| 1054 |
-
"model.layers.7.
|
| 1055 |
-
"bits":
|
|
|
|
| 1056 |
},
|
| 1057 |
"model.layers.8.moe.gate": {
|
| 1058 |
"bits": 16,
|
|
@@ -1062,17 +991,17 @@
|
|
| 1062 |
"bits": 16,
|
| 1063 |
"data_type": "float"
|
| 1064 |
},
|
| 1065 |
-
"model.layers.8.
|
| 1066 |
-
"bits":
|
| 1067 |
-
|
| 1068 |
-
"model.layers.8.self_attn.o_proj": {
|
| 1069 |
-
"bits": 8
|
| 1070 |
},
|
| 1071 |
-
"model.layers.8.
|
| 1072 |
-
"bits":
|
|
|
|
| 1073 |
},
|
| 1074 |
-
"model.layers.8.
|
| 1075 |
-
"bits":
|
|
|
|
| 1076 |
},
|
| 1077 |
"model.layers.9.moe.gate": {
|
| 1078 |
"bits": 16,
|
|
@@ -1082,17 +1011,17 @@
|
|
| 1082 |
"bits": 16,
|
| 1083 |
"data_type": "float"
|
| 1084 |
},
|
| 1085 |
-
"model.layers.9.
|
| 1086 |
-
"bits":
|
| 1087 |
-
|
| 1088 |
-
"model.layers.9.self_attn.o_proj": {
|
| 1089 |
-
"bits": 8
|
| 1090 |
},
|
| 1091 |
-
"model.layers.9.
|
| 1092 |
-
"bits":
|
|
|
|
| 1093 |
},
|
| 1094 |
-
"model.layers.9.
|
| 1095 |
-
"bits":
|
|
|
|
| 1096 |
},
|
| 1097 |
"model.layers.45.eh_proj": {
|
| 1098 |
"bits": 16,
|
|
@@ -1134,17 +1063,32 @@
|
|
| 1134 |
"bits": 16,
|
| 1135 |
"data_type": "fp"
|
| 1136 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1137 |
"model.layers.46.transformer.shared_head.output": {
|
| 1138 |
"bits": 16,
|
| 1139 |
"data_type": "fp"
|
| 1140 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1141 |
"model.layers.47.transformer.shared_head.output": {
|
| 1142 |
"bits": 16,
|
| 1143 |
"data_type": "fp"
|
| 1144 |
}
|
| 1145 |
},
|
| 1146 |
"group_size": 128,
|
| 1147 |
-
"iters": 0,
|
| 1148 |
"packing_format": "auto_round:auto_gptq",
|
| 1149 |
"quant_method": "auto-round",
|
| 1150 |
"sym": true,
|
|
@@ -1332,4 +1276,4 @@
|
|
| 1332 |
"full_attention"
|
| 1333 |
],
|
| 1334 |
"zero_centered": true
|
| 1335 |
-
}
|
|
|
|
| 159 |
"bits": 16,
|
| 160 |
"data_type": "float"
|
| 161 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 162 |
".*moe\\.gate.*": {
|
| 163 |
"bits": 16,
|
| 164 |
"data_type": "float"
|
| 165 |
},
|
| 166 |
+
".*share_expert.*": {
|
| 167 |
+
"bits": 16,
|
| 168 |
+
"data_type": "float"
|
| 169 |
},
|
| 170 |
".*shared_head.*": {
|
| 171 |
"bits": 16,
|
| 172 |
"data_type": "float"
|
| 173 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 174 |
"model.layers.0.self_attn.g_proj": {
|
| 175 |
"bits": 16,
|
| 176 |
"data_type": "float"
|
| 177 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 178 |
"model.layers.1.self_attn.g_proj": {
|
| 179 |
"bits": 16,
|
| 180 |
"data_type": "float"
|
| 181 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 182 |
"model.layers.10.moe.gate": {
|
| 183 |
"bits": 16,
|
| 184 |
"data_type": "float"
|
|
|
|
| 187 |
"bits": 16,
|
| 188 |
"data_type": "float"
|
| 189 |
},
|
| 190 |
+
"model.layers.10.share_expert.down_proj": {
|
| 191 |
+
"bits": 16,
|
| 192 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 193 |
},
|
| 194 |
+
"model.layers.10.share_expert.gate_proj": {
|
| 195 |
+
"bits": 16,
|
| 196 |
+
"data_type": "float"
|
| 197 |
},
|
| 198 |
+
"model.layers.10.share_expert.up_proj": {
|
| 199 |
+
"bits": 16,
|
| 200 |
+
"data_type": "float"
|
| 201 |
},
|
| 202 |
"model.layers.11.moe.gate": {
|
| 203 |
"bits": 16,
|
|
|
|
| 207 |
"bits": 16,
|
| 208 |
"data_type": "float"
|
| 209 |
},
|
| 210 |
+
"model.layers.11.share_expert.down_proj": {
|
| 211 |
+
"bits": 16,
|
| 212 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 213 |
},
|
| 214 |
+
"model.layers.11.share_expert.gate_proj": {
|
| 215 |
+
"bits": 16,
|
| 216 |
+
"data_type": "float"
|
| 217 |
},
|
| 218 |
+
"model.layers.11.share_expert.up_proj": {
|
| 219 |
+
"bits": 16,
|
| 220 |
+
"data_type": "float"
|
| 221 |
},
|
| 222 |
"model.layers.12.moe.gate": {
|
| 223 |
"bits": 16,
|
|
|
|
| 227 |
"bits": 16,
|
| 228 |
"data_type": "float"
|
| 229 |
},
|
| 230 |
+
"model.layers.12.share_expert.down_proj": {
|
| 231 |
+
"bits": 16,
|
| 232 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 233 |
},
|
| 234 |
+
"model.layers.12.share_expert.gate_proj": {
|
| 235 |
+
"bits": 16,
|
| 236 |
+
"data_type": "float"
|
| 237 |
},
|
| 238 |
+
"model.layers.12.share_expert.up_proj": {
|
| 239 |
+
"bits": 16,
|
| 240 |
+
"data_type": "float"
|
| 241 |
},
|
| 242 |
"model.layers.13.moe.gate": {
|
| 243 |
"bits": 16,
|
|
|
|
| 247 |
"bits": 16,
|
| 248 |
"data_type": "float"
|
| 249 |
},
|
| 250 |
+
"model.layers.13.share_expert.down_proj": {
|
| 251 |
+
"bits": 16,
|
| 252 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 253 |
},
|
| 254 |
+
"model.layers.13.share_expert.gate_proj": {
|
| 255 |
+
"bits": 16,
|
| 256 |
+
"data_type": "float"
|
| 257 |
},
|
| 258 |
+
"model.layers.13.share_expert.up_proj": {
|
| 259 |
+
"bits": 16,
|
| 260 |
+
"data_type": "float"
|
| 261 |
},
|
| 262 |
"model.layers.14.moe.gate": {
|
| 263 |
"bits": 16,
|
|
|
|
| 267 |
"bits": 16,
|
| 268 |
"data_type": "float"
|
| 269 |
},
|
| 270 |
+
"model.layers.14.share_expert.down_proj": {
|
| 271 |
+
"bits": 16,
|
| 272 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 273 |
},
|
| 274 |
+
"model.layers.14.share_expert.gate_proj": {
|
| 275 |
+
"bits": 16,
|
| 276 |
+
"data_type": "float"
|
| 277 |
},
|
| 278 |
+
"model.layers.14.share_expert.up_proj": {
|
| 279 |
+
"bits": 16,
|
| 280 |
+
"data_type": "float"
|
| 281 |
},
|
| 282 |
"model.layers.15.moe.gate": {
|
| 283 |
"bits": 16,
|
|
|
|
| 287 |
"bits": 16,
|
| 288 |
"data_type": "float"
|
| 289 |
},
|
| 290 |
+
"model.layers.15.share_expert.down_proj": {
|
| 291 |
+
"bits": 16,
|
| 292 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 293 |
},
|
| 294 |
+
"model.layers.15.share_expert.gate_proj": {
|
| 295 |
+
"bits": 16,
|
| 296 |
+
"data_type": "float"
|
| 297 |
},
|
| 298 |
+
"model.layers.15.share_expert.up_proj": {
|
| 299 |
+
"bits": 16,
|
| 300 |
+
"data_type": "float"
|
| 301 |
},
|
| 302 |
"model.layers.16.moe.gate": {
|
| 303 |
"bits": 16,
|
|
|
|
| 307 |
"bits": 16,
|
| 308 |
"data_type": "float"
|
| 309 |
},
|
| 310 |
+
"model.layers.16.share_expert.down_proj": {
|
| 311 |
+
"bits": 16,
|
| 312 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 313 |
},
|
| 314 |
+
"model.layers.16.share_expert.gate_proj": {
|
| 315 |
+
"bits": 16,
|
| 316 |
+
"data_type": "float"
|
| 317 |
},
|
| 318 |
+
"model.layers.16.share_expert.up_proj": {
|
| 319 |
+
"bits": 16,
|
| 320 |
+
"data_type": "float"
|
| 321 |
},
|
| 322 |
"model.layers.17.moe.gate": {
|
| 323 |
"bits": 16,
|
|
|
|
| 327 |
"bits": 16,
|
| 328 |
"data_type": "float"
|
| 329 |
},
|
| 330 |
+
"model.layers.17.share_expert.down_proj": {
|
| 331 |
+
"bits": 16,
|
| 332 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 333 |
},
|
| 334 |
+
"model.layers.17.share_expert.gate_proj": {
|
| 335 |
+
"bits": 16,
|
| 336 |
+
"data_type": "float"
|
| 337 |
},
|
| 338 |
+
"model.layers.17.share_expert.up_proj": {
|
| 339 |
+
"bits": 16,
|
| 340 |
+
"data_type": "float"
|
| 341 |
},
|
| 342 |
"model.layers.18.moe.gate": {
|
| 343 |
"bits": 16,
|
|
|
|
| 347 |
"bits": 16,
|
| 348 |
"data_type": "float"
|
| 349 |
},
|
| 350 |
+
"model.layers.18.share_expert.down_proj": {
|
| 351 |
+
"bits": 16,
|
| 352 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 353 |
},
|
| 354 |
+
"model.layers.18.share_expert.gate_proj": {
|
| 355 |
+
"bits": 16,
|
| 356 |
+
"data_type": "float"
|
| 357 |
},
|
| 358 |
+
"model.layers.18.share_expert.up_proj": {
|
| 359 |
+
"bits": 16,
|
| 360 |
+
"data_type": "float"
|
| 361 |
},
|
| 362 |
"model.layers.19.moe.gate": {
|
| 363 |
"bits": 16,
|
|
|
|
| 367 |
"bits": 16,
|
| 368 |
"data_type": "float"
|
| 369 |
},
|
| 370 |
+
"model.layers.19.share_expert.down_proj": {
|
| 371 |
+
"bits": 16,
|
| 372 |
+
"data_type": "float"
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 373 |
},
|
| 374 |
+
"model.layers.19.share_expert.gate_proj": {
|
| 375 |
+
"bits": 16,
|
| 376 |
+
"data_type": "float"
|
| 377 |
},
|
| 378 |
+
"model.layers.19.share_expert.up_proj": {
|
| 379 |
+
"bits": 16,
|
| 380 |
+
"data_type": "float"
|
| 381 |
},
|
| 382 |
"model.layers.2.self_attn.g_proj": {
|
| 383 |
"bits": 16,
|
| 384 |
"data_type": "float"
|
| 385 |
},
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 386 |
"model.layers.20.moe.gate": {
|
| 387 |
"bits": 16,
|
| 388 |
"data_type": "float"
|
|
|
|
| 391 |
"bits": 16,
|
| 392 |
"data_type": "float"
|
| 393 |
},
|
| 394 |
+
"model.layers.20.share_expert.down_proj": {
|
| 395 |
+
"bits": 16,
|
| 396 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 397 |
},
|
| 398 |
+
"model.layers.20.share_expert.gate_proj": {
|
| 399 |
+
"bits": 16,
|
| 400 |
+
"data_type": "float"
|
| 401 |
},
|
| 402 |
+
"model.layers.20.share_expert.up_proj": {
|
| 403 |
+
"bits": 16,
|
| 404 |
+
"data_type": "float"
|
| 405 |
},
|
| 406 |
"model.layers.21.moe.gate": {
|
| 407 |
"bits": 16,
|
|
|
|
| 411 |
"bits": 16,
|
| 412 |
"data_type": "float"
|
| 413 |
},
|
| 414 |
+
"model.layers.21.share_expert.down_proj": {
|
| 415 |
+
"bits": 16,
|
| 416 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 417 |
},
|
| 418 |
+
"model.layers.21.share_expert.gate_proj": {
|
| 419 |
+
"bits": 16,
|
| 420 |
+
"data_type": "float"
|
| 421 |
},
|
| 422 |
+
"model.layers.21.share_expert.up_proj": {
|
| 423 |
+
"bits": 16,
|
| 424 |
+
"data_type": "float"
|
| 425 |
},
|
| 426 |
"model.layers.22.moe.gate": {
|
| 427 |
"bits": 16,
|
|
|
|
| 431 |
"bits": 16,
|
| 432 |
"data_type": "float"
|
| 433 |
},
|
| 434 |
+
"model.layers.22.share_expert.down_proj": {
|
| 435 |
+
"bits": 16,
|
| 436 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 437 |
},
|
| 438 |
+
"model.layers.22.share_expert.gate_proj": {
|
| 439 |
+
"bits": 16,
|
| 440 |
+
"data_type": "float"
|
| 441 |
},
|
| 442 |
+
"model.layers.22.share_expert.up_proj": {
|
| 443 |
+
"bits": 16,
|
| 444 |
+
"data_type": "float"
|
| 445 |
},
|
| 446 |
"model.layers.23.moe.gate": {
|
| 447 |
"bits": 16,
|
|
|
|
| 451 |
"bits": 16,
|
| 452 |
"data_type": "float"
|
| 453 |
},
|
| 454 |
+
"model.layers.23.share_expert.down_proj": {
|
| 455 |
+
"bits": 16,
|
| 456 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 457 |
},
|
| 458 |
+
"model.layers.23.share_expert.gate_proj": {
|
| 459 |
+
"bits": 16,
|
| 460 |
+
"data_type": "float"
|
| 461 |
},
|
| 462 |
+
"model.layers.23.share_expert.up_proj": {
|
| 463 |
+
"bits": 16,
|
| 464 |
+
"data_type": "float"
|
| 465 |
},
|
| 466 |
"model.layers.24.moe.gate": {
|
| 467 |
"bits": 16,
|
|
|
|
| 471 |
"bits": 16,
|
| 472 |
"data_type": "float"
|
| 473 |
},
|
| 474 |
+
"model.layers.24.share_expert.down_proj": {
|
| 475 |
+
"bits": 16,
|
| 476 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 477 |
},
|
| 478 |
+
"model.layers.24.share_expert.gate_proj": {
|
| 479 |
+
"bits": 16,
|
| 480 |
+
"data_type": "float"
|
| 481 |
},
|
| 482 |
+
"model.layers.24.share_expert.up_proj": {
|
| 483 |
+
"bits": 16,
|
| 484 |
+
"data_type": "float"
|
| 485 |
},
|
| 486 |
"model.layers.25.moe.gate": {
|
| 487 |
"bits": 16,
|
|
|
|
| 491 |
"bits": 16,
|
| 492 |
"data_type": "float"
|
| 493 |
},
|
| 494 |
+
"model.layers.25.share_expert.down_proj": {
|
| 495 |
+
"bits": 16,
|
| 496 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 497 |
},
|
| 498 |
+
"model.layers.25.share_expert.gate_proj": {
|
| 499 |
+
"bits": 16,
|
| 500 |
+
"data_type": "float"
|
| 501 |
},
|
| 502 |
+
"model.layers.25.share_expert.up_proj": {
|
| 503 |
+
"bits": 16,
|
| 504 |
+
"data_type": "float"
|
| 505 |
},
|
| 506 |
"model.layers.26.moe.gate": {
|
| 507 |
"bits": 16,
|
|
|
|
| 511 |
"bits": 16,
|
| 512 |
"data_type": "float"
|
| 513 |
},
|
| 514 |
+
"model.layers.26.share_expert.down_proj": {
|
| 515 |
+
"bits": 16,
|
| 516 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 517 |
},
|
| 518 |
+
"model.layers.26.share_expert.gate_proj": {
|
| 519 |
+
"bits": 16,
|
| 520 |
+
"data_type": "float"
|
| 521 |
},
|
| 522 |
+
"model.layers.26.share_expert.up_proj": {
|
| 523 |
+
"bits": 16,
|
| 524 |
+
"data_type": "float"
|
| 525 |
},
|
| 526 |
"model.layers.27.moe.gate": {
|
| 527 |
"bits": 16,
|
|
|
|
| 531 |
"bits": 16,
|
| 532 |
"data_type": "float"
|
| 533 |
},
|
| 534 |
+
"model.layers.27.share_expert.down_proj": {
|
| 535 |
+
"bits": 16,
|
| 536 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 537 |
},
|
| 538 |
+
"model.layers.27.share_expert.gate_proj": {
|
| 539 |
+
"bits": 16,
|
| 540 |
+
"data_type": "float"
|
| 541 |
},
|
| 542 |
+
"model.layers.27.share_expert.up_proj": {
|
| 543 |
+
"bits": 16,
|
| 544 |
+
"data_type": "float"
|
| 545 |
},
|
| 546 |
"model.layers.28.moe.gate": {
|
| 547 |
"bits": 16,
|
|
|
|
| 551 |
"bits": 16,
|
| 552 |
"data_type": "float"
|
| 553 |
},
|
| 554 |
+
"model.layers.28.share_expert.down_proj": {
|
| 555 |
+
"bits": 16,
|
| 556 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 557 |
},
|
| 558 |
+
"model.layers.28.share_expert.gate_proj": {
|
| 559 |
+
"bits": 16,
|
| 560 |
+
"data_type": "float"
|
| 561 |
},
|
| 562 |
+
"model.layers.28.share_expert.up_proj": {
|
| 563 |
+
"bits": 16,
|
| 564 |
+
"data_type": "float"
|
| 565 |
},
|
| 566 |
"model.layers.29.moe.gate": {
|
| 567 |
"bits": 16,
|
|
|
|
| 571 |
"bits": 16,
|
| 572 |
"data_type": "float"
|
| 573 |
},
|
| 574 |
+
"model.layers.29.share_expert.down_proj": {
|
| 575 |
+
"bits": 16,
|
| 576 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 577 |
},
|
| 578 |
+
"model.layers.29.share_expert.gate_proj": {
|
| 579 |
+
"bits": 16,
|
| 580 |
+
"data_type": "float"
|
| 581 |
},
|
| 582 |
+
"model.layers.29.share_expert.up_proj": {
|
| 583 |
+
"bits": 16,
|
| 584 |
+
"data_type": "float"
|
| 585 |
},
|
| 586 |
"model.layers.3.moe.gate": {
|
| 587 |
"bits": 16,
|
|
|
|
| 591 |
"bits": 16,
|
| 592 |
"data_type": "float"
|
| 593 |
},
|
| 594 |
+
"model.layers.3.share_expert.down_proj": {
|
| 595 |
+
"bits": 16,
|
| 596 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 597 |
},
|
| 598 |
+
"model.layers.3.share_expert.gate_proj": {
|
| 599 |
+
"bits": 16,
|
| 600 |
+
"data_type": "float"
|
| 601 |
},
|
| 602 |
+
"model.layers.3.share_expert.up_proj": {
|
| 603 |
+
"bits": 16,
|
| 604 |
+
"data_type": "float"
|
| 605 |
},
|
| 606 |
"model.layers.30.moe.gate": {
|
| 607 |
"bits": 16,
|
|
|
|
| 611 |
"bits": 16,
|
| 612 |
"data_type": "float"
|
| 613 |
},
|
| 614 |
+
"model.layers.30.share_expert.down_proj": {
|
| 615 |
+
"bits": 16,
|
| 616 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 617 |
},
|
| 618 |
+
"model.layers.30.share_expert.gate_proj": {
|
| 619 |
+
"bits": 16,
|
| 620 |
+
"data_type": "float"
|
| 621 |
},
|
| 622 |
+
"model.layers.30.share_expert.up_proj": {
|
| 623 |
+
"bits": 16,
|
| 624 |
+
"data_type": "float"
|
| 625 |
},
|
| 626 |
"model.layers.31.moe.gate": {
|
| 627 |
"bits": 16,
|
|
|
|
| 631 |
"bits": 16,
|
| 632 |
"data_type": "float"
|
| 633 |
},
|
| 634 |
+
"model.layers.31.share_expert.down_proj": {
|
| 635 |
+
"bits": 16,
|
| 636 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 637 |
},
|
| 638 |
+
"model.layers.31.share_expert.gate_proj": {
|
| 639 |
+
"bits": 16,
|
| 640 |
+
"data_type": "float"
|
| 641 |
},
|
| 642 |
+
"model.layers.31.share_expert.up_proj": {
|
| 643 |
+
"bits": 16,
|
| 644 |
+
"data_type": "float"
|
| 645 |
},
|
| 646 |
"model.layers.32.moe.gate": {
|
| 647 |
"bits": 16,
|
|
|
|
| 651 |
"bits": 16,
|
| 652 |
"data_type": "float"
|
| 653 |
},
|
| 654 |
+
"model.layers.32.share_expert.down_proj": {
|
| 655 |
+
"bits": 16,
|
| 656 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 657 |
},
|
| 658 |
+
"model.layers.32.share_expert.gate_proj": {
|
| 659 |
+
"bits": 16,
|
| 660 |
+
"data_type": "float"
|
| 661 |
},
|
| 662 |
+
"model.layers.32.share_expert.up_proj": {
|
| 663 |
+
"bits": 16,
|
| 664 |
+
"data_type": "float"
|
| 665 |
},
|
| 666 |
"model.layers.33.moe.gate": {
|
| 667 |
"bits": 16,
|
|
|
|
| 671 |
"bits": 16,
|
| 672 |
"data_type": "float"
|
| 673 |
},
|
| 674 |
+
"model.layers.33.share_expert.down_proj": {
|
| 675 |
+
"bits": 16,
|
| 676 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 677 |
},
|
| 678 |
+
"model.layers.33.share_expert.gate_proj": {
|
| 679 |
+
"bits": 16,
|
| 680 |
+
"data_type": "float"
|
| 681 |
},
|
| 682 |
+
"model.layers.33.share_expert.up_proj": {
|
| 683 |
+
"bits": 16,
|
| 684 |
+
"data_type": "float"
|
| 685 |
},
|
| 686 |
"model.layers.34.moe.gate": {
|
| 687 |
"bits": 16,
|
|
|
|
| 691 |
"bits": 16,
|
| 692 |
"data_type": "float"
|
| 693 |
},
|
| 694 |
+
"model.layers.34.share_expert.down_proj": {
|
| 695 |
+
"bits": 16,
|
| 696 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 697 |
},
|
| 698 |
+
"model.layers.34.share_expert.gate_proj": {
|
| 699 |
+
"bits": 16,
|
| 700 |
+
"data_type": "float"
|
| 701 |
},
|
| 702 |
+
"model.layers.34.share_expert.up_proj": {
|
| 703 |
+
"bits": 16,
|
| 704 |
+
"data_type": "float"
|
| 705 |
},
|
| 706 |
"model.layers.35.moe.gate": {
|
| 707 |
"bits": 16,
|
|
|
|
| 711 |
"bits": 16,
|
| 712 |
"data_type": "float"
|
| 713 |
},
|
| 714 |
+
"model.layers.35.share_expert.down_proj": {
|
| 715 |
+
"bits": 16,
|
| 716 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 717 |
},
|
| 718 |
+
"model.layers.35.share_expert.gate_proj": {
|
| 719 |
+
"bits": 16,
|
| 720 |
+
"data_type": "float"
|
| 721 |
},
|
| 722 |
+
"model.layers.35.share_expert.up_proj": {
|
| 723 |
+
"bits": 16,
|
| 724 |
+
"data_type": "float"
|
| 725 |
},
|
| 726 |
"model.layers.36.moe.gate": {
|
| 727 |
"bits": 16,
|
|
|
|
| 731 |
"bits": 16,
|
| 732 |
"data_type": "float"
|
| 733 |
},
|
| 734 |
+
"model.layers.36.share_expert.down_proj": {
|
| 735 |
+
"bits": 16,
|
| 736 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 737 |
},
|
| 738 |
+
"model.layers.36.share_expert.gate_proj": {
|
| 739 |
+
"bits": 16,
|
| 740 |
+
"data_type": "float"
|
| 741 |
},
|
| 742 |
+
"model.layers.36.share_expert.up_proj": {
|
| 743 |
+
"bits": 16,
|
| 744 |
+
"data_type": "float"
|
| 745 |
},
|
| 746 |
"model.layers.37.moe.gate": {
|
| 747 |
"bits": 16,
|
|
|
|
| 751 |
"bits": 16,
|
| 752 |
"data_type": "float"
|
| 753 |
},
|
| 754 |
+
"model.layers.37.share_expert.down_proj": {
|
| 755 |
+
"bits": 16,
|
| 756 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 757 |
},
|
| 758 |
+
"model.layers.37.share_expert.gate_proj": {
|
| 759 |
+
"bits": 16,
|
| 760 |
+
"data_type": "float"
|
| 761 |
},
|
| 762 |
+
"model.layers.37.share_expert.up_proj": {
|
| 763 |
+
"bits": 16,
|
| 764 |
+
"data_type": "float"
|
| 765 |
},
|
| 766 |
"model.layers.38.moe.gate": {
|
| 767 |
"bits": 16,
|
|
|
|
| 771 |
"bits": 16,
|
| 772 |
"data_type": "float"
|
| 773 |
},
|
| 774 |
+
"model.layers.38.share_expert.down_proj": {
|
| 775 |
+
"bits": 16,
|
| 776 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 777 |
},
|
| 778 |
+
"model.layers.38.share_expert.gate_proj": {
|
| 779 |
+
"bits": 16,
|
| 780 |
+
"data_type": "float"
|
| 781 |
},
|
| 782 |
+
"model.layers.38.share_expert.up_proj": {
|
| 783 |
+
"bits": 16,
|
| 784 |
+
"data_type": "float"
|
| 785 |
},
|
| 786 |
"model.layers.39.moe.gate": {
|
| 787 |
"bits": 16,
|
|
|
|
| 791 |
"bits": 16,
|
| 792 |
"data_type": "float"
|
| 793 |
},
|
| 794 |
+
"model.layers.39.share_expert.down_proj": {
|
| 795 |
+
"bits": 16,
|
| 796 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 797 |
},
|
| 798 |
+
"model.layers.39.share_expert.gate_proj": {
|
| 799 |
+
"bits": 16,
|
| 800 |
+
"data_type": "float"
|
| 801 |
},
|
| 802 |
+
"model.layers.39.share_expert.up_proj": {
|
| 803 |
+
"bits": 16,
|
| 804 |
+
"data_type": "float"
|
| 805 |
},
|
| 806 |
"model.layers.4.moe.gate": {
|
| 807 |
"bits": 16,
|
|
|
|
| 811 |
"bits": 16,
|
| 812 |
"data_type": "float"
|
| 813 |
},
|
| 814 |
+
"model.layers.4.share_expert.down_proj": {
|
| 815 |
+
"bits": 16,
|
| 816 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 817 |
},
|
| 818 |
+
"model.layers.4.share_expert.gate_proj": {
|
| 819 |
+
"bits": 16,
|
| 820 |
+
"data_type": "float"
|
| 821 |
},
|
| 822 |
+
"model.layers.4.share_expert.up_proj": {
|
| 823 |
+
"bits": 16,
|
| 824 |
+
"data_type": "float"
|
| 825 |
},
|
| 826 |
"model.layers.40.moe.gate": {
|
| 827 |
"bits": 16,
|
|
|
|
| 831 |
"bits": 16,
|
| 832 |
"data_type": "float"
|
| 833 |
},
|
| 834 |
+
"model.layers.40.share_expert.down_proj": {
|
| 835 |
+
"bits": 16,
|
| 836 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 837 |
},
|
| 838 |
+
"model.layers.40.share_expert.gate_proj": {
|
| 839 |
+
"bits": 16,
|
| 840 |
+
"data_type": "float"
|
| 841 |
},
|
| 842 |
+
"model.layers.40.share_expert.up_proj": {
|
| 843 |
+
"bits": 16,
|
| 844 |
+
"data_type": "float"
|
| 845 |
},
|
| 846 |
"model.layers.41.moe.gate": {
|
| 847 |
"bits": 16,
|
|
|
|
| 851 |
"bits": 16,
|
| 852 |
"data_type": "float"
|
| 853 |
},
|
| 854 |
+
"model.layers.41.share_expert.down_proj": {
|
| 855 |
+
"bits": 16,
|
| 856 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 857 |
},
|
| 858 |
+
"model.layers.41.share_expert.gate_proj": {
|
| 859 |
+
"bits": 16,
|
| 860 |
+
"data_type": "float"
|
| 861 |
},
|
| 862 |
+
"model.layers.41.share_expert.up_proj": {
|
| 863 |
+
"bits": 16,
|
| 864 |
+
"data_type": "float"
|
| 865 |
},
|
| 866 |
"model.layers.42.moe.gate": {
|
| 867 |
"bits": 16,
|
|
|
|
| 871 |
"bits": 16,
|
| 872 |
"data_type": "float"
|
| 873 |
},
|
| 874 |
+
"model.layers.42.share_expert.down_proj": {
|
| 875 |
+
"bits": 16,
|
| 876 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 877 |
},
|
| 878 |
+
"model.layers.42.share_expert.gate_proj": {
|
| 879 |
+
"bits": 16,
|
| 880 |
+
"data_type": "float"
|
| 881 |
},
|
| 882 |
+
"model.layers.42.share_expert.up_proj": {
|
| 883 |
+
"bits": 16,
|
| 884 |
+
"data_type": "float"
|
| 885 |
},
|
| 886 |
"model.layers.43.moe.gate": {
|
| 887 |
"bits": 16,
|
|
|
|
| 891 |
"bits": 16,
|
| 892 |
"data_type": "float"
|
| 893 |
},
|
| 894 |
+
"model.layers.43.share_expert.down_proj": {
|
| 895 |
+
"bits": 16,
|
| 896 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 897 |
},
|
| 898 |
+
"model.layers.43.share_expert.gate_proj": {
|
| 899 |
+
"bits": 16,
|
| 900 |
+
"data_type": "float"
|
| 901 |
},
|
| 902 |
+
"model.layers.43.share_expert.up_proj": {
|
| 903 |
+
"bits": 16,
|
| 904 |
+
"data_type": "float"
|
| 905 |
},
|
| 906 |
"model.layers.44.moe.gate": {
|
| 907 |
"bits": 16,
|
|
|
|
| 911 |
"bits": 16,
|
| 912 |
"data_type": "float"
|
| 913 |
},
|
| 914 |
+
"model.layers.44.share_expert.down_proj": {
|
| 915 |
+
"bits": 16,
|
| 916 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 917 |
},
|
| 918 |
+
"model.layers.44.share_expert.gate_proj": {
|
| 919 |
+
"bits": 16,
|
| 920 |
+
"data_type": "float"
|
| 921 |
},
|
| 922 |
+
"model.layers.44.share_expert.up_proj": {
|
| 923 |
+
"bits": 16,
|
| 924 |
+
"data_type": "float"
|
| 925 |
},
|
| 926 |
"model.layers.5.moe.gate": {
|
| 927 |
"bits": 16,
|
|
|
|
| 931 |
"bits": 16,
|
| 932 |
"data_type": "float"
|
| 933 |
},
|
| 934 |
+
"model.layers.5.share_expert.down_proj": {
|
| 935 |
+
"bits": 16,
|
| 936 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 937 |
},
|
| 938 |
+
"model.layers.5.share_expert.gate_proj": {
|
| 939 |
+
"bits": 16,
|
| 940 |
+
"data_type": "float"
|
| 941 |
},
|
| 942 |
+
"model.layers.5.share_expert.up_proj": {
|
| 943 |
+
"bits": 16,
|
| 944 |
+
"data_type": "float"
|
| 945 |
},
|
| 946 |
"model.layers.6.moe.gate": {
|
| 947 |
"bits": 16,
|
|
|
|
| 951 |
"bits": 16,
|
| 952 |
"data_type": "float"
|
| 953 |
},
|
| 954 |
+
"model.layers.6.share_expert.down_proj": {
|
| 955 |
+
"bits": 16,
|
| 956 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 957 |
},
|
| 958 |
+
"model.layers.6.share_expert.gate_proj": {
|
| 959 |
+
"bits": 16,
|
| 960 |
+
"data_type": "float"
|
| 961 |
},
|
| 962 |
+
"model.layers.6.share_expert.up_proj": {
|
| 963 |
+
"bits": 16,
|
| 964 |
+
"data_type": "float"
|
| 965 |
},
|
| 966 |
"model.layers.7.moe.gate": {
|
| 967 |
"bits": 16,
|
|
|
|
| 971 |
"bits": 16,
|
| 972 |
"data_type": "float"
|
| 973 |
},
|
| 974 |
+
"model.layers.7.share_expert.down_proj": {
|
| 975 |
+
"bits": 16,
|
| 976 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 977 |
},
|
| 978 |
+
"model.layers.7.share_expert.gate_proj": {
|
| 979 |
+
"bits": 16,
|
| 980 |
+
"data_type": "float"
|
| 981 |
},
|
| 982 |
+
"model.layers.7.share_expert.up_proj": {
|
| 983 |
+
"bits": 16,
|
| 984 |
+
"data_type": "float"
|
| 985 |
},
|
| 986 |
"model.layers.8.moe.gate": {
|
| 987 |
"bits": 16,
|
|
|
|
| 991 |
"bits": 16,
|
| 992 |
"data_type": "float"
|
| 993 |
},
|
| 994 |
+
"model.layers.8.share_expert.down_proj": {
|
| 995 |
+
"bits": 16,
|
| 996 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 997 |
},
|
| 998 |
+
"model.layers.8.share_expert.gate_proj": {
|
| 999 |
+
"bits": 16,
|
| 1000 |
+
"data_type": "float"
|
| 1001 |
},
|
| 1002 |
+
"model.layers.8.share_expert.up_proj": {
|
| 1003 |
+
"bits": 16,
|
| 1004 |
+
"data_type": "float"
|
| 1005 |
},
|
| 1006 |
"model.layers.9.moe.gate": {
|
| 1007 |
"bits": 16,
|
|
|
|
| 1011 |
"bits": 16,
|
| 1012 |
"data_type": "float"
|
| 1013 |
},
|
| 1014 |
+
"model.layers.9.share_expert.down_proj": {
|
| 1015 |
+
"bits": 16,
|
| 1016 |
+
"data_type": "float"
|
|
|
|
|
|
|
| 1017 |
},
|
| 1018 |
+
"model.layers.9.share_expert.gate_proj": {
|
| 1019 |
+
"bits": 16,
|
| 1020 |
+
"data_type": "float"
|
| 1021 |
},
|
| 1022 |
+
"model.layers.9.share_expert.up_proj": {
|
| 1023 |
+
"bits": 16,
|
| 1024 |
+
"data_type": "float"
|
| 1025 |
},
|
| 1026 |
"model.layers.45.eh_proj": {
|
| 1027 |
"bits": 16,
|
|
|
|
| 1063 |
"bits": 16,
|
| 1064 |
"data_type": "fp"
|
| 1065 |
},
|
| 1066 |
+
"model.layers.46.eh_proj": {
|
| 1067 |
+
"bits": 16,
|
| 1068 |
+
"data_type": "fp"
|
| 1069 |
+
},
|
| 1070 |
+
"model.layers.46.self_attn.g_proj": {
|
| 1071 |
+
"bits": 16,
|
| 1072 |
+
"data_type": "fp"
|
| 1073 |
+
},
|
| 1074 |
"model.layers.46.transformer.shared_head.output": {
|
| 1075 |
"bits": 16,
|
| 1076 |
"data_type": "fp"
|
| 1077 |
},
|
| 1078 |
+
"model.layers.47.eh_proj": {
|
| 1079 |
+
"bits": 16,
|
| 1080 |
+
"data_type": "fp"
|
| 1081 |
+
},
|
| 1082 |
+
"model.layers.47.self_attn.g_proj": {
|
| 1083 |
+
"bits": 16,
|
| 1084 |
+
"data_type": "fp"
|
| 1085 |
+
},
|
| 1086 |
"model.layers.47.transformer.shared_head.output": {
|
| 1087 |
"bits": 16,
|
| 1088 |
"data_type": "fp"
|
| 1089 |
}
|
| 1090 |
},
|
| 1091 |
"group_size": 128,
|
|
|
|
| 1092 |
"packing_format": "auto_round:auto_gptq",
|
| 1093 |
"quant_method": "auto-round",
|
| 1094 |
"sym": true,
|
|
|
|
| 1276 |
"full_attention"
|
| 1277 |
],
|
| 1278 |
"zero_centered": true
|
| 1279 |
+
}
|
model-00001-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:457cc9d06da2f8d61b13bdb3f85eb437e503dee40a794298786fbfb6a4d8b068
|
| 3 |
+
size 1073136648
|
model-00002-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e7c37ec685b4c32d1c4e55a30463a44cd529ca1173e8677fd7483cb9efaea0e5
|
| 3 |
+
size 1073336096
|
model-00003-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d188a626df928294cd4fb0553e42d1ff067f9c6260c8a533a386e17486b8369f
|
| 3 |
+
size 1073367032
|
model-00004-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:8a4c11b7010cfb5c207d27667d00e870c91b443d8d36df0c8ecc68b3a9182e4c
|
| 3 |
+
size 1073335776
|
model-00005-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b39daa7b48357a5f136fa1b48df061fd108779360ca68b691c5ffa7700c1f7e3
|
| 3 |
+
size 1071992680
|
model-00006-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95140bfab86fd8c3442b2286cf8d073c8213f4e0ec556a6e1d278a4b3470714c
|
| 3 |
+
size 1073335432
|
model-00007-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:e1352eaaae5bcef0d9263432433f1a4712084914376e1a4ee67947a9e4cc371a
|
| 3 |
+
size 1073336288
|
model-00008-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:db0e281c0b57c461e6c737aef76fdd8a55bec18b0b2a3e5da0fc29ec1fbd1971
|
| 3 |
+
size 1071991824
|
model-00009-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1c7897ab2dc1ce8eff3f57266bc8cbceee5b56afab325975d76810000db8eec6
|
| 3 |
+
size 1073336280
|
model-00010-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d6e0df6cf06c3072ddf345e655aa51c5c6095244698dbe9377732b4dd938c0d0
|
| 3 |
+
size 1071992136
|
model-00011-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:bf15ca3a54567b0ad6917608a70fe3dc26ba9a4a82c43b26bb8c9f86b4704e70
|
| 3 |
+
size 1073335976
|
model-00012-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:44510a1a6016672018c2cec333bae7a84619e92b7d4948714504a211304f9308
|
| 3 |
+
size 1073367152
|
model-00013-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:378b55acae01c14789a4934a8e43d26906a9f5c3c4c150780f8228f46aef2a2e
|
| 3 |
+
size 1073335664
|
model-00014-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1a3ce921f10053dd1a9d6c42b6dabe2c5ba660a4b0e7b98cb0ead625484fcb5e
|
| 3 |
+
size 1055774904
|
model-00015-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1fe037ced57c7b48123364e9d3829bd9e1f09557ad91480c7282328a2aa8f3f6
|
| 3 |
+
size 1073207912
|
model-00016-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7b73408cd9e1a4fd73bdd1ec4d596b3ea6046e9e5491ab23de13761415fc6bbd
|
| 3 |
+
size 1073336288
|
model-00017-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:842cc47f334a628adb02e84632ce3d39e101b8d1cf7810ad3b40c1fa5c8b279e
|
| 3 |
+
size 1071992744
|
model-00018-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:927efbcf7ee17310ed9d21343be919d7ea98c4305f9875524ce8119a75478325
|
| 3 |
+
size 1073337344
|
model-00019-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d2844ad4318355ef38d45983e5b3ea650712da970a854af7c03e4e5af75280f9
|
| 3 |
+
size 1071993368
|
model-00020-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fc955199d6dc8d81930c3ee2c1d393d6f499ede78894085634902dceb101572
|
| 3 |
+
size 1073337024
|
model-00021-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:15c16795083a4eacb847f0641df693022ba62ec40ae4052cff040b2f1af425ed
|
| 3 |
+
size 1073368408
|
model-00022-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:1853c82edc9ea3b4d67458824709b6270d84a4520a1a0c633891910399cdb02c
|
| 3 |
+
size 1073336712
|
model-00023-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b1b1d948868d78b113d8c986617aa506c3431462a93030bedb8f6dcca84eef75
|
| 3 |
+
size 1073337464
|
model-00024-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:80c2a39a8bdc0eab75e78fb6c34476c46c79b780afa8a272a8b1b8bfb2d6b2a1
|
| 3 |
+
size 1071992928
|
model-00025-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3d03ed40879d45a30ea7636672e60f632a233c2116e8286f53ca261ce23b8e37
|
| 3 |
+
size 1073337464
|
model-00026-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9b025761327bd03f09653ff32e45b276683e146986d0a4f9d3f2dff8ff0a4529
|
| 3 |
+
size 1071993160
|
model-00027-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a88f9c95a27a198a1bc872456f7079137efde4b660d29fa8e23cc774ecea21ce
|
| 3 |
+
size 1073337232
|
model-00028-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:3f7e3d00f1195536076970bf423933925251b54e669d62b9f03b90b974f37789
|
| 3 |
+
size 1071993488
|
model-00029-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:95fb0e10dae4fef1d06c889656bee93478840611317c1c5dfc81925fe8dcce4e
|
| 3 |
+
size 1073336904
|
model-00030-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f0e214f8db24f856b6acefeb3e5702e1d43c1a3441e4899f1ab74bd63c6a4a2c
|
| 3 |
+
size 1073368584
|
model-00031-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ad910c3e810da44b5ad96ae6c4e62cdf9dd6bea2762c23aa02b878786dcd18ee
|
| 3 |
+
size 1073336528
|
model-00032-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:0296c5d2aea0e42f0e97e90b5d08cdb9a869b7f19247852e96cb861f667ce6e4
|
| 3 |
+
size 1073337464
|
model-00033-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:d5b4e03a0cc9ef15d690944e9f1b0cc744df8fe69ac94091505774dbfdeb9d05
|
| 3 |
+
size 1071992944
|
model-00034-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f749c75f37b54154c7a431db43b568d54ce8690aebbd5f904ce3215133a6d045
|
| 3 |
+
size 1073337448
|
model-00035-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a001022c9b949acd5fb3c4fd855b3a5eab3a4def493a66f5f5267ea9fbf8a704
|
| 3 |
+
size 1071993272
|
model-00036-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:c945b19aa2e8a68bf09894477561a6566a13d4314841d2e7f4a132821d7c091a
|
| 3 |
+
size 1073337112
|
model-00037-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:18caada793c593e3816344a4e2844ecd7fb77bd91a1db2293808df7902af6c2d
|
| 3 |
+
size 1071993608
|
model-00038-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:073733f2f953e0c3d9e72896a8b7acbf57cade556e299d428b8930f262f72e87
|
| 3 |
+
size 1073336792
|
model-00039-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:a1c25cea900d9a42bbe1b6e925524e2ed12d66c6a9acb6a1e0c3a5ac5a17b685
|
| 3 |
+
size 1073337464
|
model-00040-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:7c05f8cc5682e490c106db6f33fb31f7d1eb6e3a4529349d8a0ebca6a063b183
|
| 3 |
+
size 1073367648
|
model-00041-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:aa9dae1871ecd0f73720a6e476c31559cee8641917cb0525c47fdb069822c9eb
|
| 3 |
+
size 1073337464
|
model-00042-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:b8fce519bf5e99eb154062b45f23a7c9a770f62b7e8b4eaf1939773e206cd2c8
|
| 3 |
+
size 1071993064
|
model-00043-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:6046d69ae0fbaefc598f430bb3276c1f1501570f0de6b1dcbb4bdffa9ffe4f93
|
| 3 |
+
size 1073337336
|
model-00044-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:9a513538bbf993d4178a525997148f587de910a17c1b42da192321faa6851638
|
| 3 |
+
size 1071993392
|
model-00045-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:f5615d42dba5cc5c393cc7fa4fff20fd989aa5c9cbd0ece491909c3cc5230381
|
| 3 |
+
size 1073337000
|
model-00046-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:fb7163f8322b264d70bf4266f2122dd5248ac1323edb3fc089e01224b260bb3a
|
| 3 |
+
size 1071993720
|
model-00047-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:5ca914a72228d4ca16b83bc5031ad50bc254855528bb930ea19adaeec0425d93
|
| 3 |
+
size 1073336672
|
model-00048-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:ea2379d554931fb82986208ffc99e72bba401a50845765ad4852c95dad8de659
|
| 3 |
+
size 1073337464
|
model-00049-of-00098.safetensors
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:4fd56e1a51e96e2e4d004f82061860fbee586821a92a451e728d3fc5a49201d1
|
| 3 |
+
size 1073367648
|