File size: 110,569 Bytes
0b9e523 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 314 315 316 317 318 319 320 321 322 323 324 325 326 327 328 329 330 331 332 333 334 335 336 337 338 339 340 341 342 343 344 345 346 347 348 349 350 351 352 353 354 355 356 357 358 359 360 361 362 363 364 365 366 367 368 369 370 371 372 373 374 375 376 377 378 379 380 381 382 383 384 385 386 387 388 389 390 391 392 393 394 395 396 397 398 399 400 401 402 403 404 405 406 407 408 409 410 411 412 413 414 415 416 417 418 419 420 421 422 423 424 425 426 427 428 429 430 431 432 433 434 435 436 437 438 439 440 441 442 443 444 445 446 447 448 449 450 451 452 453 454 455 456 457 458 459 460 461 462 463 464 465 466 467 468 469 470 471 472 473 474 475 476 477 478 479 480 481 482 483 484 485 486 487 488 489 490 491 492 493 494 495 496 497 498 499 500 501 502 503 504 505 506 507 508 509 510 511 512 513 514 515 516 517 518 519 520 521 522 523 524 525 526 527 528 529 530 531 532 533 534 535 536 537 538 539 540 541 542 543 544 545 546 547 548 549 550 551 552 553 554 555 556 557 558 559 560 561 562 563 564 565 566 567 568 569 570 571 572 573 574 575 576 577 578 579 580 581 582 583 584 585 586 587 588 589 590 591 592 593 594 595 596 597 598 599 600 601 602 603 604 605 606 607 608 609 610 611 612 613 614 615 616 617 618 619 620 621 622 623 624 625 626 627 628 629 630 631 632 633 634 635 636 637 638 639 640 641 642 643 644 645 646 647 648 649 650 651 652 653 654 655 656 657 658 659 660 661 662 663 664 665 666 667 668 669 670 671 672 673 674 675 676 677 678 679 680 681 682 683 684 685 686 687 688 689 690 691 692 693 694 695 696 697 698 699 700 701 702 703 704 705 706 707 708 709 710 711 712 713 714 715 716 717 718 719 720 721 722 723 724 725 726 727 728 729 730 731 732 733 734 735 736 737 738 739 740 741 742 743 744 745 746 747 748 749 750 751 752 753 754 755 756 757 758 759 760 761 762 763 764 765 766 767 768 769 770 771 772 773 774 775 776 777 778 779 780 781 782 783 784 785 786 787 788 789 790 791 792 793 794 795 796 797 798 799 800 801 802 803 804 805 806 807 808 809 810 811 812 813 814 815 816 817 818 819 820 821 822 823 824 825 826 827 828 829 830 831 832 833 834 835 836 837 838 839 840 841 842 843 844 845 846 847 848 849 850 851 852 853 854 855 856 857 858 859 860 861 862 863 864 865 866 867 868 869 870 871 872 873 874 875 876 877 878 879 880 881 882 883 884 885 886 887 888 889 890 891 892 893 894 895 896 897 898 899 900 901 902 903 904 905 906 907 908 909 910 911 912 913 914 915 916 917 918 919 920 921 922 923 924 925 926 927 928 929 930 931 932 933 934 935 936 937 938 939 940 941 942 943 944 945 946 947 948 949 950 951 952 953 954 955 956 957 958 959 960 961 962 963 964 965 966 967 968 969 970 971 972 973 974 975 976 977 978 979 980 981 982 983 984 985 986 987 988 989 990 991 992 993 994 995 996 997 998 999 1000 1001 1002 1003 1004 1005 1006 1007 1008 1009 1010 1011 1012 1013 1014 1015 1016 1017 1018 1019 1020 1021 1022 1023 1024 1025 1026 1027 1028 1029 1030 1031 1032 1033 1034 1035 1036 1037 1038 1039 1040 1041 1042 1043 1044 1045 1046 1047 1048 1049 1050 1051 1052 1053 1054 1055 1056 1057 1058 1059 1060 1061 1062 1063 1064 1065 1066 1067 1068 1069 1070 1071 1072 1073 1074 1075 1076 1077 1078 1079 1080 1081 1082 1083 1084 1085 1086 1087 1088 1089 1090 1091 1092 1093 |
{
"metadata": {
"total_size": 16163330176
},
"weight_map": {
"language_model.model.layers.0.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.0.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.1.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.10.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.10.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.11.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.12.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.13.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.14.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.15.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.16.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.17.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.18.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.19.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.19.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.2.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.2.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.20.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.20.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.21.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.22.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.23.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.24.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.25.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.26.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.27.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.28.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.attention_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.feed_forward.w2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.29.ffn_norm.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.3.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.3.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.30.attention.gating_phantom_1.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.gating_phantom_1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.gating_phantom_2.bias": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.gating_phantom_2.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.wo.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.wqkv.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_key_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_key_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_key_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_key_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_query_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_query_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_query_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_query_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_value_phantom.linear_k.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_value_phantom.linear_o.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_value_phantom.linear_q.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention.xattn_value_phantom.linear_v.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.attention_norm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.feed_forward.w1.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.30.feed_forward.w3.weight": "model-00003-of-00004.safetensors",
"language_model.model.layers.30.ffn_norm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.gating_phantom_1.bias": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.gating_phantom_1.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.gating_phantom_2.bias": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.gating_phantom_2.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.wo.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.wqkv.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_key_phantom.linear_k.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_key_phantom.linear_o.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_key_phantom.linear_q.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_key_phantom.linear_v.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_query_phantom.linear_k.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_query_phantom.linear_o.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_query_phantom.linear_q.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_query_phantom.linear_v.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_value_phantom.linear_k.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_value_phantom.linear_o.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_value_phantom.linear_q.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention.xattn_value_phantom.linear_v.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.attention_norm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.feed_forward.w1.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.feed_forward.w2.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.feed_forward.w3.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.31.ffn_norm.weight": "model-00004-of-00004.safetensors",
"language_model.model.layers.4.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.4.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.5.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.6.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.attention_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.feed_forward.w1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.feed_forward.w2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.feed_forward.w3.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.7.ffn_norm.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.gating_phantom_1.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.gating_phantom_1.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.gating_phantom_2.bias": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.gating_phantom_2.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.wo.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.wqkv.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_key_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_key_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_key_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_key_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_query_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_query_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_query_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_query_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_value_phantom.linear_k.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_value_phantom.linear_o.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_value_phantom.linear_q.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention.xattn_value_phantom.linear_v.weight": "model-00001-of-00004.safetensors",
"language_model.model.layers.8.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.8.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.gating_phantom_1.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.gating_phantom_1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.gating_phantom_2.bias": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.gating_phantom_2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.wo.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.wqkv.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_key_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_key_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_key_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_key_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_query_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_query_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_query_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_query_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_value_phantom.linear_k.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_value_phantom.linear_o.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_value_phantom.linear_q.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention.xattn_value_phantom.linear_v.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.attention_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.feed_forward.w1.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.feed_forward.w2.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.feed_forward.w3.weight": "model-00002-of-00004.safetensors",
"language_model.model.layers.9.ffn_norm.weight": "model-00002-of-00004.safetensors",
"language_model.model.norm.weight": "model-00004-of-00004.safetensors",
"language_model.model.tok_embeddings.weight": "model-00001-of-00004.safetensors",
"language_model.output.weight": "model-00004-of-00004.safetensors",
"vision_model.embeddings.class_embedding": "model-00001-of-00004.safetensors",
"vision_model.embeddings.patch_embedding.bias": "model-00001-of-00004.safetensors",
"vision_model.embeddings.patch_embedding.weight": "model-00001-of-00004.safetensors",
"vision_model.embeddings.position_embedding": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.0.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.1.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.10.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.11.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.12.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.13.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.14.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.15.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.16.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.17.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.18.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.19.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.2.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.20.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.21.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.22.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.23.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.3.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.4.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.5.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.6.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.7.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.8.norm2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.attn.proj.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.attn.proj.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.attn.qkv.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.attn.qkv.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.ls1": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.ls2": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.norm1.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.norm1.weight": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.norm2.bias": "model-00001-of-00004.safetensors",
"vision_model.encoder.layers.9.norm2.weight": "model-00001-of-00004.safetensors",
"vision_proj.0.bias": "model-00004-of-00004.safetensors",
"vision_proj.0.weight": "model-00004-of-00004.safetensors",
"vision_proj.1.bias": "model-00004-of-00004.safetensors",
"vision_proj.1.weight": "model-00004-of-00004.safetensors",
"vision_proj.3.bias": "model-00004-of-00004.safetensors",
"vision_proj.3.weight": "model-00004-of-00004.safetensors"
}
}
|