File size: 97,034 Bytes
dba31cf | 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 | INFO:hf-to-gguf:Loading model: hf
INFO:hf-to-gguf:Model architecture: Qwen3_5MoeForConditionalGeneration
INFO:hf-to-gguf:gguf: loading model weight map from 'model.safetensors.index.json'
INFO:hf-to-gguf:gguf: indexing model part 'model-00001-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00002-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00003-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00004-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00005-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00006-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00007-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00008-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00009-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00010-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00011-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00012-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00013-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00014-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00015-of-00016.safetensors'
INFO:hf-to-gguf:gguf: indexing model part 'model-00016-of-00016.safetensors'
INFO:gguf.gguf_writer:gguf: This GGUF file is for Little Endian only
INFO:hf-to-gguf:Exporting model...
INFO:hf-to-gguf:token_embd.weight, torch.bfloat16 --> BF16, shape = {2048, 248320}
INFO:hf-to-gguf:blk.0.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.0.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.0.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.0.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.0.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.0.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.0.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.0.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.0.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.0.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.0.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.0.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.0.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.0.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.0.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.0.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.0.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.0.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.0.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.1.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.1.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.1.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.1.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.1.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.1.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.1.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.1.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.1.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.1.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.1.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.1.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.1.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.1.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.1.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.1.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.1.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.2.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.2.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.2.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.2.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.2.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.2.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.2.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.2.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.2.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.2.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.2.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.2.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.2.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.2.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.2.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.2.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.2.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.3.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.3.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.3.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.3.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.3.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.3.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.3.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.3.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.3.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.3.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.3.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.4.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.4.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.4.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.4.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.4.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.4.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.4.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.4.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.4.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.4.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.4.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.4.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.4.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.4.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.4.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.4.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.4.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.5.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.5.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.5.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.5.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.5.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.5.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.5.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.5.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.5.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.5.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.5.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.5.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.5.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.5.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.5.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.5.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.5.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.6.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.6.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.6.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.6.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.6.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.6.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.6.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.6.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.6.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.6.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.6.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.6.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.6.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.6.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.6.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.6.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.6.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.7.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.7.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.7.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.7.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.7.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.7.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.7.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.7.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.7.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.7.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.7.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.8.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.8.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.8.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.8.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.8.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.8.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.8.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.8.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.8.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.8.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.8.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.8.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.8.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.8.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.8.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.8.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.8.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.8.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.8.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.9.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.9.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.9.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.9.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.9.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.9.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.9.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.9.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.9.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.9.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.9.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.9.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.9.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.9.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.9.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.9.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.9.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.10.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.10.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.10.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.10.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.10.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.10.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.10.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.10.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.10.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.10.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.10.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.10.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.10.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.10.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.10.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.10.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.10.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.10.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.10.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.11.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.11.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.11.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.11.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.11.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.11.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.11.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.11.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.11.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.11.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.11.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.11.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.11.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.11.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.12.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.12.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.12.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.12.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.12.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.12.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.12.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.12.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.12.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.12.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.12.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.12.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.12.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.9.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.9.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.12.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.12.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.12.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.12.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.13.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.13.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.13.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.13.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.13.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.13.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.13.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.13.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.13.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.13.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.13.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.13.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.13.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.13.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.13.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.13.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.13.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.13.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.13.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.14.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.14.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.14.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.14.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.14.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.14.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.14.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.14.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.14.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.14.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.14.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.14.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.14.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.14.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.14.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.14.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.14.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.14.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.14.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.15.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.15.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.15.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.15.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.15.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.15.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.15.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.15.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.15.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.15.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.15.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.15.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.15.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.15.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.16.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.16.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.16.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.16.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.16.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.16.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.16.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.16.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.16.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.16.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.16.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.16.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.16.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.16.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.16.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.16.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.16.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.17.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.17.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.17.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.17.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.17.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.17.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.17.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.17.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.17.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.17.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.17.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.17.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.17.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.17.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.17.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.17.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.17.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.17.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.18.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.18.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.18.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.18.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.18.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.18.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.18.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.18.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.18.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.18.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.18.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.18.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.18.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.18.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.18.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.18.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.18.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.18.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.18.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.19.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.19.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.19.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.19.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.19.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.19.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.19.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.19.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.19.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.19.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.19.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.19.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.19.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.19.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.20.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.20.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.20.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.20.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.20.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.20.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.20.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.20.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.20.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.20.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.20.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.20.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.20.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.20.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.20.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.20.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.20.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.20.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.20.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.21.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.21.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.21.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.21.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.21.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.21.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.21.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.21.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.21.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.21.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.21.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.21.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.21.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.21.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.21.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.21.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.21.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.21.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.21.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.22.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.22.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.22.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.22.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.22.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.22.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.22.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.22.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.22.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.22.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.22.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.22.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.22.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.22.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.22.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.22.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.22.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.22.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.22.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.23.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.23.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.23.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.23.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.23.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.23.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.23.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.23.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.23.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.23.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.23.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.23.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.23.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.23.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.24.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.24.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.24.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.24.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.24.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.24.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.24.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.24.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.24.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.24.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.24.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.24.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.24.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.24.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.24.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.24.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.24.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.24.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.24.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.25.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.25.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.25.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.25.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.25.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.25.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.25.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.25.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.25.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.25.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.25.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.25.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.25.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.25.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.25.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.25.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.25.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.25.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.25.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.26.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.26.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.26.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.26.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.26.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.26.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.26.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.26.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.26.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.26.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.26.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.26.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.26.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.26.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.26.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.26.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.26.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.26.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.26.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.27.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.27.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.27.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.27.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.27.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.27.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.27.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.27.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.27.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.27.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.27.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.27.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.27.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.27.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.27.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.27.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.28.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.28.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.28.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.28.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.28.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.28.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.28.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.28.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.28.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.28.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.28.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.28.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.28.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.28.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.28.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.28.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.28.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.28.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.28.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.29.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.29.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.29.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.29.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.29.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.29.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.29.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.29.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.29.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.29.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.29.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.29.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.29.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.29.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.29.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.29.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.29.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.29.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.29.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.30.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.30.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.30.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.30.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.30.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.30.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.30.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.30.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.30.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.30.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.30.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.30.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.30.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.30.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.30.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.30.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.30.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.30.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.30.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.31.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.31.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.31.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.31.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.31.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.31.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.31.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.31.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.31.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.31.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.31.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.31.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.31.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.31.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.31.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.31.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.32.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.32.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.32.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.32.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.32.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.32.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.32.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.32.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.32.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.32.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.32.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.32.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.32.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.32.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.32.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.32.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.32.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.32.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.32.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.33.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.33.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.33.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.33.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.33.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.33.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.33.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.33.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.33.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.33.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.33.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.33.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.33.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.33.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.33.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.33.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.33.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.33.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.33.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.34.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.34.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.34.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.34.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.34.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.34.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.34.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.34.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.34.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.34.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.34.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.34.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.34.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.34.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.34.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.34.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.34.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.34.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.34.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.35.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.35.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.35.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.35.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.35.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.35.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.35.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.35.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.35.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.35.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.35.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.35.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.35.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.35.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.35.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.35.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.36.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.36.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.36.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.36.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.36.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.36.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.36.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.36.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.36.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.36.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.36.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.36.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.36.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.36.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.36.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.36.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.36.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.36.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.36.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.37.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.37.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.37.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.37.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.37.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.37.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.37.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.37.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.37.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.37.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.37.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.37.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.37.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.37.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.37.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.37.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.37.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.37.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.37.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.38.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.38.ssm_a, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.38.ssm_conv1d.weight, torch.bfloat16 --> F32, shape = {4, 8192}
INFO:hf-to-gguf:blk.38.ssm_dt.bias, torch.bfloat16 --> F32, shape = {32}
INFO:hf-to-gguf:blk.38.ssm_alpha.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.38.ssm_beta.weight, torch.bfloat16 --> BF16, shape = {2048, 32}
INFO:hf-to-gguf:blk.38.attn_qkv.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.38.attn_gate.weight, torch.bfloat16 --> BF16, shape = {2048, 4096}
INFO:hf-to-gguf:blk.38.ssm_norm.weight, torch.bfloat16 --> F32, shape = {128}
INFO:hf-to-gguf:blk.38.ssm_out.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.38.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.38.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.38.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.38.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.38.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.38.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.38.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.38.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.38.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:output.weight, torch.bfloat16 --> BF16, shape = {2048, 248320}
INFO:hf-to-gguf:blk.39.attn_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.39.ffn_down_exps.weight, torch.bfloat16 --> BF16, shape = {512, 2048, 256}
INFO:hf-to-gguf:blk.39.ffn_gate_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.39.ffn_up_exps.weight, torch.bfloat16 --> BF16, shape = {2048, 512, 256}
INFO:hf-to-gguf:blk.39.ffn_gate_inp.weight, torch.bfloat16 --> F32, shape = {2048, 256}
INFO:hf-to-gguf:blk.39.ffn_down_shexp.weight, torch.bfloat16 --> BF16, shape = {512, 2048}
INFO:hf-to-gguf:blk.39.ffn_gate_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.39.ffn_up_shexp.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.39.ffn_gate_inp_shexp.weight, torch.bfloat16 --> F32, shape = {2048, 1}
INFO:hf-to-gguf:blk.39.post_attention_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:blk.39.attn_k_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.39.attn_k.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:blk.39.attn_output.weight, torch.bfloat16 --> BF16, shape = {4096, 2048}
INFO:hf-to-gguf:blk.39.attn_q_norm.weight, torch.bfloat16 --> F32, shape = {256}
INFO:hf-to-gguf:blk.39.attn_q.weight, torch.bfloat16 --> BF16, shape = {2048, 8192}
INFO:hf-to-gguf:blk.39.attn_v.weight, torch.bfloat16 --> BF16, shape = {2048, 512}
INFO:hf-to-gguf:output_norm.weight, torch.bfloat16 --> F32, shape = {2048}
INFO:hf-to-gguf:Set meta model
INFO:hf-to-gguf:Set model parameters
INFO:hf-to-gguf:gguf: context length = 262144
INFO:hf-to-gguf:gguf: embedding length = 2048
INFO:hf-to-gguf:gguf: head count = 16
INFO:hf-to-gguf:gguf: key-value head count = 2
WARNING:hf-to-gguf:Unknown RoPE type: default
INFO:hf-to-gguf:gguf: rope scaling type = NONE
INFO:hf-to-gguf:gguf: mrope sections: [11, 11, 10, 0]
INFO:hf-to-gguf:gguf: rope theta = 10000000
INFO:hf-to-gguf:gguf: rms norm epsilon = 1e-06
INFO:hf-to-gguf:gguf: expert count = 256
INFO:hf-to-gguf:gguf: experts used count = 8
INFO:hf-to-gguf:gguf: file type = 32
INFO:hf-to-gguf:gguf: expert feed forward length = 512
INFO:hf-to-gguf:gguf: expert shared feed forward length = 512
INFO:hf-to-gguf:Set model quantization version
INFO:hf-to-gguf:Set model tokenizer
INFO:gguf.vocab:Adding 247587 merge(s).
INFO:gguf.vocab:Setting special token type eos to 248046
INFO:gguf.vocab:Setting special token type pad to 248044
INFO:gguf.vocab:Setting chat_template to {%- set image_count = namespace(value=0) %}
{%- set video_count = namespace(value=0) %}
{%- macro render_content(content, do_vision_count, is_system_content=false) %}
{%- if content is string %}
{{- content }}
{%- elif content is iterable and content is not mapping %}
{%- for item in content %}
{%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain images.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set image_count.value = image_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Picture ' ~ image_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|image_pad|><|vision_end|>' }}
{%- elif 'video' in item or item.type == 'video' %}
{%- if is_system_content %}
{{- raise_exception('System message cannot contain videos.') }}
{%- endif %}
{%- if do_vision_count %}
{%- set video_count.value = video_count.value + 1 %}
{%- endif %}
{%- if add_vision_id %}
{{- 'Video ' ~ video_count.value ~ ': ' }}
{%- endif %}
{{- '<|vision_start|><|video_pad|><|vision_end|>' }}
{%- elif 'text' in item %}
{{- item.text }}
{%- else %}
{{- raise_exception('Unexpected item type in content.') }}
{%- endif %}
{%- endfor %}
{%- elif content is none or content is undefined %}
{{- '' }}
{%- else %}
{{- raise_exception('Unexpected content type.') }}
{%- endif %}
{%- endmacro %}
{%- if not messages %}
{{- raise_exception('No messages provided.') }}
{%- endif %}
{%- if tools and tools is iterable and tools is not mapping %}
{{- '<|im_start|>system\n' }}
{{- "# Tools\n\nYou have access to the following functions:\n\n<tools>" }}
{%- for tool in tools %}
{{- "\n" }}
{{- tool | tojson }}
{%- endfor %}
{{- "\n</tools>" }}
{{- '\n\nIf you choose to call a function ONLY reply in the following format with NO suffix:\n\n<tool_call>\n<function=example_function_name>\n<parameter=example_parameter_1>\nvalue_1\n</parameter>\n<parameter=example_parameter_2>\nThis is the value for the second parameter\nthat can span\nmultiple lines\n</parameter>\n</function>\n</tool_call>\n\n<IMPORTANT>\nReminder:\n- Function calls MUST follow the specified format: an inner <function=...></function> block must be nested within <tool_call></tool_call> XML tags\n- Required parameters MUST be specified\n- You may provide optional reasoning for your function call in natural language BEFORE the function call, but NOT after\n- If there is no function call available, answer the question like normal with your current knowledge and do not tell the user about function calls\n</IMPORTANT>' }}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{%- if content %}
{{- '\n\n' + content }}
{%- endif %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- else %}
{%- if messages[0].role == 'system' %}
{%- set content = render_content(messages[0].content, false, true)|trim %}
{{- '<|im_start|>system\n' + content + '<|im_end|>\n' }}
{%- endif %}
{%- endif %}
{%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
{%- for message in messages[::-1] %}
{%- set index = (messages|length - 1) - loop.index0 %}
{%- if ns.multi_step_tool and message.role == "user" %}
{%- set content = render_content(message.content, false)|trim %}
{%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
{%- set ns.multi_step_tool = false %}
{%- set ns.last_query_index = index %}
{%- endif %}
{%- endif %}
{%- endfor %}
{%- if ns.multi_step_tool %}
{{- raise_exception('No user query found in messages.') }}
{%- endif %}
{%- for message in messages %}
{%- set content = render_content(message.content, true)|trim %}
{%- if message.role == "system" %}
{%- if not loop.first %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- endif %}
{%- elif message.role == "user" %}
{{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
{%- elif message.role == "assistant" %}
{%- set reasoning_content = '' %}
{%- if message.reasoning_content is string %}
{%- set reasoning_content = message.reasoning_content %}
{%- else %}
{%- if '</think>' in content %}
{%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
{%- set content = content.split('</think>')[-1].lstrip('\n') %}
{%- endif %}
{%- endif %}
{%- set reasoning_content = reasoning_content|trim %}
{{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content + '\n</think>\n\n' + content }}
{%- if message.tool_calls and message.tool_calls is iterable and message.tool_calls is not mapping %}
{%- for tool_call in message.tool_calls %}
{%- if tool_call.function is defined %}
{%- set tool_call = tool_call.function %}
{%- endif %}
{%- if loop.first %}
{%- if content|trim %}
{{- '\n\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- else %}
{{- '<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- else %}
{{- '\n<tool_call>\n<function=' + tool_call.name + '>\n' }}
{%- endif %}
{%- if tool_call.arguments is defined %}
{%- for args_name, args_value in tool_call.arguments|items %}
{{- '<parameter=' + args_name + '>\n' }}
{%- set args_value = args_value | tojson | safe if args_value is mapping or (args_value is sequence and args_value is not string) else args_value | string %}
{{- args_value }}
{{- '\n</parameter>\n' }}
{%- endfor %}
{%- endif %}
{{- '</function>\n</tool_call>' }}
{%- endfor %}
{%- endif %}
{{- '<|im_end|>\n' }}
{%- elif message.role == "tool" %}
{%- if loop.previtem and loop.previtem.role != "tool" %}
{{- '<|im_start|>user' }}
{%- endif %}
{{- '\n<tool_response>\n' }}
{{- content }}
{{- '\n</tool_response>' }}
{%- if not loop.last and loop.nextitem.role != "tool" %}
{{- '<|im_end|>\n' }}
{%- elif loop.last %}
{{- '<|im_end|>\n' }}
{%- endif %}
{%- else %}
{{- raise_exception('Unexpected message role.') }}
{%- endif %}
{%- endfor %}
{%- if add_generation_prompt %}
{{- '<|im_start|>assistant\n' }}
{%- if reasoning_effort is not defined or reasoning_effort is none %}
{{- '<think>' }}
{%- elif reasoning_effort == 'none' %}
{{- '<think>\n\n</think>\n\n' }}
{%- elif reasoning_effort == 'high' %}
{{- '<think>\n' }}
{%- else %}
{{- '<think>' }}
{%- endif %}
{%- endif %}
INFO:gguf.gguf_writer:Writing the following files:
INFO:gguf.gguf_writer:gguf/Nex-N2.5-mini-BF16.gguf: n_tensors = 733, total_size = 69.4G
Writing: 0%| | 0.00/69.4G [00:00<?, ?byte/s]
Writing: 1%|▏ | 1.02G/69.4G [00:02<02:29, 457Mbyte/s]
Writing: 2%|▏ | 1.07G/69.4G [00:02<02:39, 428Mbyte/s]
Writing: 2%|▏ | 1.62G/69.4G [00:03<02:41, 419Mbyte/s]
Writing: 3%|▎ | 2.16G/69.4G [00:05<03:08, 356Mbyte/s]
Writing: 4%|▍ | 2.70G/69.4G [00:06<02:30, 443Mbyte/s]
Writing: 4%|▍ | 2.75G/69.4G [00:06<02:37, 423Mbyte/s]
Writing: 5%|▍ | 3.31G/69.4G [00:08<03:01, 365Mbyte/s]
Writing: 6%|▌ | 3.84G/69.4G [00:09<02:25, 452Mbyte/s]
Writing: 6%|▋ | 4.39G/69.4G [00:10<02:33, 423Mbyte/s]
Writing: 6%|▋ | 4.44G/69.4G [00:10<02:37, 413Mbyte/s]
Writing: 7%|▋ | 4.99G/69.4G [00:12<02:39, 403Mbyte/s]
Writing: 8%|▊ | 5.53G/69.4G [00:13<02:57, 359Mbyte/s]
Writing: 9%|▊ | 6.07G/69.4G [00:14<02:23, 441Mbyte/s]
Writing: 10%|▉ | 6.61G/69.4G [00:16<03:04, 340Mbyte/s]
Writing: 10%|█ | 7.15G/69.4G [00:20<04:24, 235Mbyte/s]
Writing: 11%|█ | 7.69G/69.4G [00:22<04:05, 252Mbyte/s]
Writing: 11%|█ | 7.75G/69.4G [00:22<04:07, 249Mbyte/s]
Writing: 11%|█ | 7.78G/69.4G [00:22<04:05, 250Mbyte/s]
Writing: 11%|█▏ | 7.82G/69.4G [00:23<04:04, 252Mbyte/s]
Writing: 12%|█▏ | 8.36G/69.4G [00:26<05:05, 199Mbyte/s]
Writing: 13%|█▎ | 8.90G/69.4G [00:29<05:32, 182Mbyte/s]
Writing: 14%|█▎ | 9.44G/69.4G [00:31<04:23, 228Mbyte/s]
Writing: 14%|█▎ | 9.47G/69.4G [00:31<04:26, 225Mbyte/s]
Writing: 14%|█▎ | 9.50G/69.4G [00:31<04:26, 225Mbyte/s]
Writing: 14%|█▍ | 10.0G/69.4G [00:34<04:37, 214Mbyte/s]
Writing: 15%|█▌ | 10.6G/69.4G [00:36<04:48, 204Mbyte/s]
Writing: 16%|█▌ | 11.1G/69.4G [00:38<04:13, 230Mbyte/s]
Writing: 16%|█▌ | 11.2G/69.4G [00:38<04:15, 228Mbyte/s]
Writing: 16%|█▌ | 11.2G/69.4G [00:38<04:12, 230Mbyte/s]
Writing: 17%|█▋ | 11.7G/69.4G [00:41<04:27, 216Mbyte/s]
Writing: 18%|█▊ | 12.3G/69.4G [00:44<04:39, 204Mbyte/s]
Writing: 18%|█▊ | 12.8G/69.4G [00:46<04:02, 233Mbyte/s]
Writing: 19%|█▉ | 13.3G/69.4G [00:48<04:13, 221Mbyte/s]
Writing: 20%|██ | 13.9G/69.4G [00:51<04:24, 210Mbyte/s]
Writing: 21%|██ | 14.4G/69.4G [00:53<03:53, 235Mbyte/s]
Writing: 21%|██ | 14.4G/69.4G [00:53<03:54, 234Mbyte/s]
Writing: 21%|██ | 14.5G/69.4G [00:53<03:53, 235Mbyte/s]
Writing: 21%|██ | 14.5G/69.4G [00:53<03:53, 235Mbyte/s]
Writing: 21%|██ | 14.6G/69.4G [00:53<03:52, 236Mbyte/s]
Writing: 22%|██▏ | 15.1G/69.4G [00:56<04:12, 215Mbyte/s]
Writing: 23%|██▎ | 15.6G/69.4G [00:59<04:24, 203Mbyte/s]
Writing: 23%|██▎ | 16.2G/69.4G [01:00<03:37, 245Mbyte/s]
Writing: 23%|██▎ | 16.2G/69.4G [01:01<03:39, 242Mbyte/s]
Writing: 23%|██▎ | 16.2G/69.4G [01:01<03:39, 242Mbyte/s]
Writing: 24%|██▍ | 16.8G/69.4G [01:04<04:05, 214Mbyte/s]
Writing: 25%|██▍ | 17.3G/69.4G [01:05<03:34, 242Mbyte/s]
Writing: 25%|██▌ | 17.4G/69.4G [01:06<03:38, 238Mbyte/s]
Writing: 25%|██▌ | 17.4G/69.4G [01:06<03:37, 238Mbyte/s]
Writing: 26%|██▌ | 17.9G/69.4G [01:08<03:41, 232Mbyte/s]
Writing: 27%|██▋ | 18.5G/69.4G [01:11<04:00, 212Mbyte/s]
Writing: 27%|██▋ | 19.0G/69.4G [01:13<03:31, 238Mbyte/s]
Writing: 28%|██▊ | 19.5G/69.4G [01:15<03:35, 232Mbyte/s]
Writing: 29%|██▉ | 20.1G/69.4G [01:18<03:47, 217Mbyte/s]
Writing: 30%|██▉ | 20.6G/69.4G [01:20<03:26, 237Mbyte/s]
Writing: 30%|██▉ | 20.6G/69.4G [01:20<03:27, 234Mbyte/s]
Writing: 30%|██▉ | 20.7G/69.4G [01:20<03:27, 235Mbyte/s]
Writing: 30%|██▉ | 20.7G/69.4G [01:20<03:28, 234Mbyte/s]
Writing: 30%|██▉ | 20.7G/69.4G [01:20<03:27, 234Mbyte/s]
Writing: 31%|███ | 21.3G/69.4G [01:23<03:26, 233Mbyte/s]
Writing: 31%|███▏ | 21.8G/69.4G [01:26<03:42, 214Mbyte/s]
Writing: 32%|███▏ | 22.4G/69.4G [01:28<03:48, 205Mbyte/s]
Writing: 33%|███▎ | 22.9G/69.4G [01:30<03:12, 242Mbyte/s]
Writing: 33%|███▎ | 22.9G/69.4G [01:30<03:14, 238Mbyte/s]
Writing: 33%|███▎ | 23.0G/69.4G [01:30<03:14, 239Mbyte/s]
Writing: 34%|███▍ | 23.5G/69.4G [01:33<03:29, 219Mbyte/s]
Writing: 35%|███▍ | 24.0G/69.4G [01:36<03:35, 211Mbyte/s]
Writing: 35%|███▌ | 24.6G/69.4G [01:37<03:02, 246Mbyte/s]
Writing: 35%|███▌ | 24.6G/69.4G [01:37<03:04, 242Mbyte/s]
Writing: 36%|███▌ | 24.7G/69.4G [01:38<03:04, 242Mbyte/s]
Writing: 36%|███▋ | 25.2G/69.4G [01:40<03:20, 221Mbyte/s]
Writing: 37%|███▋ | 25.7G/69.4G [01:43<03:28, 209Mbyte/s]
Writing: 38%|███▊ | 26.3G/69.4G [01:45<02:56, 244Mbyte/s]
Writing: 39%|███▊ | 26.8G/69.4G [01:47<03:08, 226Mbyte/s]
Writing: 39%|███▉ | 27.3G/69.4G [01:50<03:15, 215Mbyte/s]
Writing: 40%|████ | 27.9G/69.4G [01:52<02:50, 244Mbyte/s]
Writing: 40%|████ | 27.9G/69.4G [01:52<02:52, 240Mbyte/s]
Writing: 40%|████ | 27.9G/69.4G [01:52<02:52, 241Mbyte/s]
Writing: 40%|████ | 28.0G/69.4G [01:52<02:52, 239Mbyte/s]
Writing: 40%|████ | 28.0G/69.4G [01:52<02:52, 240Mbyte/s]
Writing: 41%|████ | 28.6G/69.4G [01:55<03:08, 217Mbyte/s]
Writing: 42%|████▏ | 29.1G/69.4G [01:58<03:17, 204Mbyte/s]
Writing: 43%|████▎ | 29.6G/69.4G [01:59<02:45, 239Mbyte/s]
Writing: 43%|████▎ | 29.7G/69.4G [02:00<02:48, 236Mbyte/s]
Writing: 43%|████▎ | 29.7G/69.4G [02:00<02:47, 237Mbyte/s]
Writing: 44%|████▎ | 30.2G/69.4G [02:02<03:03, 213Mbyte/s]
Writing: 44%|████▍ | 30.8G/69.4G [02:04<02:40, 241Mbyte/s]
Writing: 45%|████▌ | 31.3G/69.4G [02:07<02:45, 230Mbyte/s]
Writing: 45%|████▌ | 31.4G/69.4G [02:07<02:47, 227Mbyte/s]
Writing: 45%|████▌ | 31.4G/69.4G [02:07<02:47, 227Mbyte/s]
Writing: 46%|████▌ | 31.9G/69.4G [02:10<02:55, 213Mbyte/s]
Writing: 47%|████▋ | 32.5G/69.4G [02:12<02:54, 212Mbyte/s]
Writing: 48%|████▊ | 33.0G/69.4G [02:14<02:33, 236Mbyte/s]
Writing: 48%|████▊ | 33.5G/69.4G [02:17<02:41, 222Mbyte/s]
Writing: 49%|████▉ | 34.1G/69.4G [02:20<02:42, 217Mbyte/s]
Writing: 50%|████▉ | 34.6G/69.4G [02:21<02:26, 238Mbyte/s]
Writing: 50%|████▉ | 34.6G/69.4G [02:21<02:27, 235Mbyte/s]
Writing: 50%|████▉ | 34.7G/69.4G [02:22<02:26, 236Mbyte/s]
Writing: 50%|█████ | 34.7G/69.4G [02:22<02:26, 237Mbyte/s]
Writing: 50%|█████ | 34.8G/69.4G [02:22<02:25, 238Mbyte/s]
Writing: 51%|█████ | 35.3G/69.4G [02:25<02:38, 214Mbyte/s]
Writing: 52%|█████▏ | 35.8G/69.4G [02:27<02:36, 214Mbyte/s]
Writing: 52%|█████▏ | 36.4G/69.4G [02:29<02:17, 239Mbyte/s]
Writing: 52%|█████▏ | 36.4G/69.4G [02:29<02:19, 236Mbyte/s]
Writing: 53%|█████▎ | 36.4G/69.4G [02:29<02:19, 236Mbyte/s]
Writing: 53%|█████▎ | 37.0G/69.4G [02:32<02:28, 218Mbyte/s]
Writing: 54%|█████▍ | 37.5G/69.4G [02:34<02:28, 215Mbyte/s]
Writing: 55%|█████▍ | 38.0G/69.4G [02:36<02:11, 238Mbyte/s]
Writing: 55%|█████▍ | 38.1G/69.4G [02:37<02:13, 235Mbyte/s]
Writing: 55%|█████▍ | 38.1G/69.4G [02:37<02:13, 234Mbyte/s]
Writing: 56%|█████▌ | 38.7G/69.4G [02:39<02:21, 217Mbyte/s]
Writing: 57%|█████▋ | 39.2G/69.4G [02:42<02:19, 217Mbyte/s]
Writing: 57%|█████▋ | 39.7G/69.4G [02:44<02:03, 240Mbyte/s]
Writing: 58%|█████▊ | 40.3G/69.4G [02:46<02:09, 224Mbyte/s]
Writing: 59%|█████▉ | 40.8G/69.4G [02:49<02:09, 220Mbyte/s]
Writing: 60%|█████▉ | 41.4G/69.4G [02:51<01:56, 240Mbyte/s]
Writing: 60%|█████▉ | 41.4G/69.4G [02:51<01:57, 237Mbyte/s]
Writing: 60%|█████▉ | 41.4G/69.4G [02:51<01:57, 237Mbyte/s]
Writing: 60%|█████▉ | 41.4G/69.4G [02:51<01:57, 237Mbyte/s]
Writing: 60%|█████▉ | 41.5G/69.4G [02:51<01:57, 238Mbyte/s]
Writing: 61%|██████ | 42.0G/69.4G [02:54<02:06, 215Mbyte/s]
Writing: 61%|██████▏ | 42.6G/69.4G [02:56<02:04, 216Mbyte/s]
Writing: 62%|██████▏ | 43.1G/69.4G [02:58<01:49, 240Mbyte/s]
Writing: 62%|██████▏ | 43.1G/69.4G [02:59<01:51, 235Mbyte/s]
Writing: 62%|██████▏ | 43.2G/69.4G [02:59<01:51, 235Mbyte/s]
Writing: 63%|██████▎ | 43.7G/69.4G [03:01<02:00, 213Mbyte/s]
Writing: 64%|██████▍ | 44.2G/69.4G [03:03<01:38, 255Mbyte/s]
Writing: 65%|██████▍ | 44.8G/69.4G [03:06<01:47, 229Mbyte/s]
Writing: 65%|██████▍ | 44.8G/69.4G [03:06<01:49, 224Mbyte/s]
Writing: 65%|██████▍ | 44.9G/69.4G [03:06<01:49, 224Mbyte/s]
Writing: 65%|██████▌ | 45.4G/69.4G [03:09<01:52, 213Mbyte/s]
Writing: 66%|██████▌ | 45.9G/69.4G [03:12<01:54, 205Mbyte/s]
Writing: 67%|██████▋ | 46.5G/69.4G [03:13<01:39, 230Mbyte/s]
Writing: 68%|██████▊ | 47.0G/69.4G [03:16<01:42, 219Mbyte/s]
Writing: 69%|██████▊ | 47.5G/69.4G [03:19<01:44, 210Mbyte/s]
Writing: 69%|██████▉ | 48.1G/69.4G [03:21<01:32, 230Mbyte/s]
Writing: 69%|██████▉ | 48.1G/69.4G [03:21<01:33, 228Mbyte/s]
Writing: 69%|██████▉ | 48.1G/69.4G [03:21<01:32, 229Mbyte/s]
Writing: 69%|██████▉ | 48.2G/69.4G [03:21<01:32, 229Mbyte/s]
Writing: 70%|██████▉ | 48.2G/69.4G [03:21<01:31, 231Mbyte/s]
Writing: 70%|███████ | 48.8G/69.4G [03:24<01:36, 214Mbyte/s]
Writing: 71%|███████ | 49.3G/69.4G [03:27<01:38, 203Mbyte/s]
Writing: 72%|███████▏ | 49.8G/69.4G [03:29<01:23, 233Mbyte/s]
Writing: 72%|███████▏ | 49.9G/69.4G [03:29<01:24, 229Mbyte/s]
Writing: 72%|███████▏ | 49.9G/69.4G [03:29<01:24, 230Mbyte/s]
Writing: 73%|███████▎ | 50.4G/69.4G [03:31<01:25, 222Mbyte/s]
Writing: 73%|███████▎ | 51.0G/69.4G [03:34<01:27, 209Mbyte/s]
Writing: 74%|███████▍ | 51.5G/69.4G [03:36<01:16, 234Mbyte/s]
Writing: 74%|███████▍ | 51.6G/69.4G [03:36<01:17, 231Mbyte/s]
Writing: 74%|███████▍ | 51.6G/69.4G [03:36<01:16, 232Mbyte/s]
Writing: 75%|███████▌ | 52.1G/69.4G [03:39<01:15, 228Mbyte/s]
Writing: 76%|███████▌ | 52.7G/69.4G [03:42<01:19, 211Mbyte/s]
Writing: 77%|███████▋ | 53.2G/69.4G [03:43<01:08, 238Mbyte/s]
Writing: 77%|███████▋ | 53.7G/69.4G [03:46<01:08, 229Mbyte/s]
Writing: 78%|███████▊ | 54.3G/69.4G [03:49<01:10, 215Mbyte/s]
Writing: 79%|███████▉ | 54.8G/69.4G [03:51<01:01, 236Mbyte/s]
Writing: 79%|███████▉ | 54.8G/69.4G [03:51<01:02, 234Mbyte/s]
Writing: 79%|███████▉ | 54.9G/69.4G [03:51<01:01, 234Mbyte/s]
Writing: 79%|███████▉ | 54.9G/69.4G [03:51<01:01, 234Mbyte/s]
Writing: 79%|███████▉ | 54.9G/69.4G [03:51<01:00, 237Mbyte/s]
Writing: 80%|███████▉ | 55.5G/69.4G [03:54<00:59, 231Mbyte/s]
Writing: 81%|████████ | 56.0G/69.4G [03:56<00:55, 239Mbyte/s]
Writing: 82%|████████▏ | 56.6G/69.4G [03:57<00:49, 260Mbyte/s]
Writing: 82%|████████▏ | 56.6G/69.4G [03:58<00:49, 258Mbyte/s]
Writing: 82%|████████▏ | 56.6G/69.4G [03:58<00:48, 260Mbyte/s]
Writing: 82%|████████▏ | 57.2G/69.4G [04:00<00:43, 281Mbyte/s]
Writing: 83%|████████▎ | 57.7G/69.4G [04:01<00:38, 306Mbyte/s]
Writing: 84%|████████▍ | 58.3G/69.4G [04:04<00:43, 255Mbyte/s]
Writing: 84%|████████▍ | 58.3G/69.4G [04:04<00:44, 250Mbyte/s]
Writing: 84%|████████▍ | 58.3G/69.4G [04:04<00:44, 250Mbyte/s]
Writing: 85%|████████▍ | 58.9G/69.4G [04:07<00:47, 222Mbyte/s]
Writing: 86%|████████▌ | 59.4G/69.4G [04:10<00:47, 209Mbyte/s]
Writing: 86%|████████▋ | 59.9G/69.4G [04:11<00:40, 235Mbyte/s]
Writing: 87%|████████▋ | 60.5G/69.4G [04:14<00:38, 230Mbyte/s]
Writing: 88%|████████▊ | 61.0G/69.4G [04:15<00:32, 261Mbyte/s]
Writing: 89%|████████▊ | 61.6G/69.4G [04:17<00:28, 272Mbyte/s]
Writing: 89%|████████▉ | 61.6G/69.4G [04:17<00:28, 272Mbyte/s]
Writing: 89%|████████▉ | 61.6G/69.4G [04:18<00:28, 272Mbyte/s]
Writing: 89%|████████▉ | 61.7G/69.4G [04:18<00:27, 275Mbyte/s]
Writing: 90%|████████▉ | 62.2G/69.4G [04:20<00:30, 232Mbyte/s]
Writing: 90%|█████████ | 62.8G/69.4G [04:23<00:29, 224Mbyte/s]
Writing: 91%|█████████▏| 63.3G/69.4G [04:25<00:24, 246Mbyte/s]
Writing: 91%|█████████▏| 63.3G/69.4G [04:25<00:24, 242Mbyte/s]
Writing: 91%|█████████▏| 63.4G/69.4G [04:25<00:24, 242Mbyte/s]
Writing: 92%|█████████▏| 63.9G/69.4G [04:27<00:22, 239Mbyte/s]
Writing: 93%|█████████▎| 64.4G/69.4G [04:29<00:18, 261Mbyte/s]
Writing: 94%|█████████▎| 65.0G/69.4G [04:31<00:15, 286Mbyte/s]
Writing: 94%|█████████▎| 65.0G/69.4G [04:31<00:15, 282Mbyte/s]
Writing: 94%|█████████▍| 65.1G/69.4G [04:31<00:15, 283Mbyte/s]
Writing: 95%|█████████▍| 65.6G/69.4G [04:33<00:14, 266Mbyte/s]
Writing: 95%|█████████▌| 66.1G/69.4G [04:35<00:11, 277Mbyte/s]
Writing: 96%|█████████▌| 66.7G/69.4G [04:37<00:09, 291Mbyte/s]
Writing: 98%|█████████▊| 67.7G/69.4G [04:41<00:06, 267Mbyte/s]
Writing: 98%|█████████▊| 68.2G/69.4G [04:43<00:04, 243Mbyte/s]
Writing: 99%|█████████▉| 68.8G/69.4G [04:45<00:02, 251Mbyte/s]
Writing: 100%|█████████▉| 69.3G/69.4G [04:47<00:00, 261Mbyte/s]
Writing: 100%|█████████▉| 69.3G/69.4G [04:47<00:00, 259Mbyte/s]
Writing: 100%|█████████▉| 69.4G/69.4G [04:48<00:00, 261Mbyte/s]
Writing: 100%|██████████| 69.4G/69.4G [04:48<00:00, 241Mbyte/s]
INFO:hf-to-gguf:Model successfully exported to gguf/Nex-N2.5-mini-BF16.gguf
|