Upload AriaForConditionalGeneration
Browse files- README.md +1 -1
- config.json +9 -8
- generation_config.json +1 -1
- model-00001-of-00012.safetensors +2 -2
- model.safetensors.index.json +444 -442
README.md
CHANGED
|
@@ -1,8 +1,8 @@
|
|
| 1 |
---
|
| 2 |
-
license: apache-2.0
|
| 3 |
language:
|
| 4 |
- en
|
| 5 |
library_name: transformers
|
|
|
|
| 6 |
pipeline_tag: image-text-to-text
|
| 7 |
tags:
|
| 8 |
- multimodal
|
|
|
|
| 1 |
---
|
|
|
|
| 2 |
language:
|
| 3 |
- en
|
| 4 |
library_name: transformers
|
| 5 |
+
license: apache-2.0
|
| 6 |
pipeline_tag: image-text-to-text
|
| 7 |
tags:
|
| 8 |
- multimodal
|
config.json
CHANGED
|
@@ -1,4 +1,5 @@
|
|
| 1 |
{
|
|
|
|
| 2 |
"architectures": [
|
| 3 |
"AriaForConditionalGeneration"
|
| 4 |
],
|
|
@@ -8,7 +9,9 @@
|
|
| 8 |
},
|
| 9 |
"ignore_index": -100,
|
| 10 |
"image_token_index": 9,
|
|
|
|
| 11 |
"model_type": "aria",
|
|
|
|
| 12 |
"projector_patch_to_query_dict": {
|
| 13 |
"1225": 128,
|
| 14 |
"4900": 256
|
|
@@ -17,7 +20,7 @@
|
|
| 17 |
"hidden_size": 2560,
|
| 18 |
"intermediate_size": 13568,
|
| 19 |
"max_position_embeddings": 65536,
|
| 20 |
-
"model_type": "
|
| 21 |
"moe_intermediate_size": 1664,
|
| 22 |
"moe_num_experts": 64,
|
| 23 |
"moe_topk": 6,
|
|
@@ -29,21 +32,19 @@
|
|
| 29 |
"vocab_size": 100352
|
| 30 |
},
|
| 31 |
"torch_dtype": "bfloat16",
|
| 32 |
-
"transformers_version": "4.
|
| 33 |
-
"_attn_implementation": "flash_attention_2",
|
| 34 |
"vision_config": {
|
| 35 |
"_flash_attn_2_enabled": true,
|
| 36 |
-
"_attn_implementation": "flash_attention_2",
|
| 37 |
"architectures": [
|
| 38 |
"AriaVisionModel"
|
| 39 |
],
|
| 40 |
-
"
|
| 41 |
"image_size": 980,
|
| 42 |
"intermediate_size": 4304,
|
| 43 |
-
"model_type": "
|
| 44 |
-
"num_attention_heads": 16,
|
| 45 |
"num_hidden_layers": 27,
|
| 46 |
"patch_size": 14,
|
| 47 |
"torch_dtype": "bfloat16"
|
| 48 |
-
}
|
|
|
|
| 49 |
}
|
|
|
|
| 1 |
{
|
| 2 |
+
"_name_or_path": "rhymes-ai/Aria",
|
| 3 |
"architectures": [
|
| 4 |
"AriaForConditionalGeneration"
|
| 5 |
],
|
|
|
|
| 9 |
},
|
| 10 |
"ignore_index": -100,
|
| 11 |
"image_token_index": 9,
|
| 12 |
+
"initializer_range": 0.02,
|
| 13 |
"model_type": "aria",
|
| 14 |
+
"pad_token_id": 2,
|
| 15 |
"projector_patch_to_query_dict": {
|
| 16 |
"1225": 128,
|
| 17 |
"4900": 256
|
|
|
|
| 20 |
"hidden_size": 2560,
|
| 21 |
"intermediate_size": 13568,
|
| 22 |
"max_position_embeddings": 65536,
|
| 23 |
+
"model_type": "aria_text",
|
| 24 |
"moe_intermediate_size": 1664,
|
| 25 |
"moe_num_experts": 64,
|
| 26 |
"moe_topk": 6,
|
|
|
|
| 32 |
"vocab_size": 100352
|
| 33 |
},
|
| 34 |
"torch_dtype": "bfloat16",
|
| 35 |
+
"transformers_version": "4.47.0.dev0",
|
|
|
|
| 36 |
"vision_config": {
|
| 37 |
"_flash_attn_2_enabled": true,
|
|
|
|
| 38 |
"architectures": [
|
| 39 |
"AriaVisionModel"
|
| 40 |
],
|
| 41 |
+
"attention_heads": 16,
|
| 42 |
"image_size": 980,
|
| 43 |
"intermediate_size": 4304,
|
| 44 |
+
"model_type": "idefics3_vision",
|
|
|
|
| 45 |
"num_hidden_layers": 27,
|
| 46 |
"patch_size": 14,
|
| 47 |
"torch_dtype": "bfloat16"
|
| 48 |
+
},
|
| 49 |
+
"vision_feature_layer": -1
|
| 50 |
}
|
generation_config.json
CHANGED
|
@@ -3,5 +3,5 @@
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 2,
|
| 6 |
-
"transformers_version": "4.
|
| 7 |
}
|
|
|
|
| 3 |
"bos_token_id": 1,
|
| 4 |
"eos_token_id": 2,
|
| 5 |
"pad_token_id": 2,
|
| 6 |
+
"transformers_version": "4.47.0.dev0"
|
| 7 |
}
|
model-00001-of-00012.safetensors
CHANGED
|
@@ -1,3 +1,3 @@
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
-
oid sha256:
|
| 3 |
-
size
|
|
|
|
| 1 |
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:07002e78de0e8d6f1142f46dd921929f00c2ff7b7f33558fb0b9142313268d1e
|
| 3 |
+
size 4922385168
|
model.safetensors.index.json
CHANGED
|
@@ -1,6 +1,6 @@
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
-
"total_size":
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.lm_head.weight": "model-00012-of-00012.safetensors",
|
|
@@ -345,455 +345,457 @@
|
|
| 345 |
"multi_modal_projector.cross_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 346 |
"multi_modal_projector.cross_attn.layer_norm.bias": "model-00001-of-00012.safetensors",
|
| 347 |
"multi_modal_projector.cross_attn.layer_norm.weight": "model-00001-of-00012.safetensors",
|
|
|
|
|
|
|
| 348 |
"multi_modal_projector.cross_attn.linear.bias": "model-00001-of-00012.safetensors",
|
| 349 |
"multi_modal_projector.cross_attn.linear.weight": "model-00001-of-00012.safetensors",
|
| 350 |
-
"multi_modal_projector.cross_attn.ln_kv.bias": "model-00001-of-00012.safetensors",
|
| 351 |
-
"multi_modal_projector.cross_attn.ln_kv.weight": "model-00001-of-00012.safetensors",
|
| 352 |
"multi_modal_projector.cross_attn.multihead_attn.in_proj_bias": "model-00001-of-00012.safetensors",
|
| 353 |
"multi_modal_projector.cross_attn.multihead_attn.in_proj_weight": "model-00001-of-00012.safetensors",
|
| 354 |
"multi_modal_projector.cross_attn.multihead_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 355 |
"multi_modal_projector.cross_attn.multihead_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 356 |
"multi_modal_projector.cross_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 357 |
"multi_modal_projector.cross_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 358 |
-
"multi_modal_projector.
|
| 359 |
-
"multi_modal_projector.
|
| 360 |
-
"multi_modal_projector.
|
| 361 |
-
"multi_modal_projector.
|
| 362 |
"multi_modal_projector.query": "model-00001-of-00012.safetensors",
|
| 363 |
-
"vision_tower.
|
| 364 |
-
"vision_tower.
|
| 365 |
-
"vision_tower.
|
| 366 |
-
"vision_tower.
|
| 367 |
-
"vision_tower.
|
| 368 |
-
"vision_tower.
|
| 369 |
-
"vision_tower.
|
| 370 |
-
"vision_tower.
|
| 371 |
-
"vision_tower.
|
| 372 |
-
"vision_tower.
|
| 373 |
-
"vision_tower.
|
| 374 |
-
"vision_tower.
|
| 375 |
-
"vision_tower.
|
| 376 |
-
"vision_tower.
|
| 377 |
-
"vision_tower.
|
| 378 |
-
"vision_tower.
|
| 379 |
-
"vision_tower.
|
| 380 |
-
"vision_tower.
|
| 381 |
-
"vision_tower.
|
| 382 |
-
"vision_tower.
|
| 383 |
-
"vision_tower.
|
| 384 |
-
"vision_tower.
|
| 385 |
-
"vision_tower.
|
| 386 |
-
"vision_tower.
|
| 387 |
-
"vision_tower.
|
| 388 |
-
"vision_tower.
|
| 389 |
-
"vision_tower.
|
| 390 |
-
"vision_tower.
|
| 391 |
-
"vision_tower.
|
| 392 |
-
"vision_tower.
|
| 393 |
-
"vision_tower.
|
| 394 |
-
"vision_tower.
|
| 395 |
-
"vision_tower.
|
| 396 |
-
"vision_tower.
|
| 397 |
-
"vision_tower.
|
| 398 |
-
"vision_tower.
|
| 399 |
-
"vision_tower.
|
| 400 |
-
"vision_tower.
|
| 401 |
-
"vision_tower.
|
| 402 |
-
"vision_tower.
|
| 403 |
-
"vision_tower.
|
| 404 |
-
"vision_tower.
|
| 405 |
-
"vision_tower.
|
| 406 |
-
"vision_tower.
|
| 407 |
-
"vision_tower.
|
| 408 |
-
"vision_tower.
|
| 409 |
-
"vision_tower.
|
| 410 |
-
"vision_tower.
|
| 411 |
-
"vision_tower.
|
| 412 |
-
"vision_tower.
|
| 413 |
-
"vision_tower.
|
| 414 |
-
"vision_tower.
|
| 415 |
-
"vision_tower.
|
| 416 |
-
"vision_tower.
|
| 417 |
-
"vision_tower.
|
| 418 |
-
"vision_tower.
|
| 419 |
-
"vision_tower.
|
| 420 |
-
"vision_tower.
|
| 421 |
-
"vision_tower.
|
| 422 |
-
"vision_tower.
|
| 423 |
-
"vision_tower.
|
| 424 |
-
"vision_tower.
|
| 425 |
-
"vision_tower.
|
| 426 |
-
"vision_tower.
|
| 427 |
-
"vision_tower.
|
| 428 |
-
"vision_tower.
|
| 429 |
-
"vision_tower.
|
| 430 |
-
"vision_tower.
|
| 431 |
-
"vision_tower.
|
| 432 |
-
"vision_tower.
|
| 433 |
-
"vision_tower.
|
| 434 |
-
"vision_tower.
|
| 435 |
-
"vision_tower.
|
| 436 |
-
"vision_tower.
|
| 437 |
-
"vision_tower.
|
| 438 |
-
"vision_tower.
|
| 439 |
-
"vision_tower.
|
| 440 |
-
"vision_tower.
|
| 441 |
-
"vision_tower.
|
| 442 |
-
"vision_tower.
|
| 443 |
-
"vision_tower.
|
| 444 |
-
"vision_tower.
|
| 445 |
-
"vision_tower.
|
| 446 |
-
"vision_tower.
|
| 447 |
-
"vision_tower.
|
| 448 |
-
"vision_tower.
|
| 449 |
-
"vision_tower.
|
| 450 |
-
"vision_tower.
|
| 451 |
-
"vision_tower.
|
| 452 |
-
"vision_tower.
|
| 453 |
-
"vision_tower.
|
| 454 |
-
"vision_tower.
|
| 455 |
-
"vision_tower.
|
| 456 |
-
"vision_tower.
|
| 457 |
-
"vision_tower.
|
| 458 |
-
"vision_tower.
|
| 459 |
-
"vision_tower.
|
| 460 |
-
"vision_tower.
|
| 461 |
-
"vision_tower.
|
| 462 |
-
"vision_tower.
|
| 463 |
-
"vision_tower.
|
| 464 |
-
"vision_tower.
|
| 465 |
-
"vision_tower.
|
| 466 |
-
"vision_tower.
|
| 467 |
-
"vision_tower.
|
| 468 |
-
"vision_tower.
|
| 469 |
-
"vision_tower.
|
| 470 |
-
"vision_tower.
|
| 471 |
-
"vision_tower.
|
| 472 |
-
"vision_tower.
|
| 473 |
-
"vision_tower.
|
| 474 |
-
"vision_tower.
|
| 475 |
-
"vision_tower.
|
| 476 |
-
"vision_tower.
|
| 477 |
-
"vision_tower.
|
| 478 |
-
"vision_tower.
|
| 479 |
-
"vision_tower.
|
| 480 |
-
"vision_tower.
|
| 481 |
-
"vision_tower.
|
| 482 |
-
"vision_tower.
|
| 483 |
-
"vision_tower.
|
| 484 |
-
"vision_tower.
|
| 485 |
-
"vision_tower.
|
| 486 |
-
"vision_tower.
|
| 487 |
-
"vision_tower.
|
| 488 |
-
"vision_tower.
|
| 489 |
-
"vision_tower.
|
| 490 |
-
"vision_tower.
|
| 491 |
-
"vision_tower.
|
| 492 |
-
"vision_tower.
|
| 493 |
-
"vision_tower.
|
| 494 |
-
"vision_tower.
|
| 495 |
-
"vision_tower.
|
| 496 |
-
"vision_tower.
|
| 497 |
-
"vision_tower.
|
| 498 |
-
"vision_tower.
|
| 499 |
-
"vision_tower.
|
| 500 |
-
"vision_tower.
|
| 501 |
-
"vision_tower.
|
| 502 |
-
"vision_tower.
|
| 503 |
-
"vision_tower.
|
| 504 |
-
"vision_tower.
|
| 505 |
-
"vision_tower.
|
| 506 |
-
"vision_tower.
|
| 507 |
-
"vision_tower.
|
| 508 |
-
"vision_tower.
|
| 509 |
-
"vision_tower.
|
| 510 |
-
"vision_tower.
|
| 511 |
-
"vision_tower.
|
| 512 |
-
"vision_tower.
|
| 513 |
-
"vision_tower.
|
| 514 |
-
"vision_tower.
|
| 515 |
-
"vision_tower.
|
| 516 |
-
"vision_tower.
|
| 517 |
-
"vision_tower.
|
| 518 |
-
"vision_tower.
|
| 519 |
-
"vision_tower.
|
| 520 |
-
"vision_tower.
|
| 521 |
-
"vision_tower.
|
| 522 |
-
"vision_tower.
|
| 523 |
-
"vision_tower.
|
| 524 |
-
"vision_tower.
|
| 525 |
-
"vision_tower.
|
| 526 |
-
"vision_tower.
|
| 527 |
-
"vision_tower.
|
| 528 |
-
"vision_tower.
|
| 529 |
-
"vision_tower.
|
| 530 |
-
"vision_tower.
|
| 531 |
-
"vision_tower.
|
| 532 |
-
"vision_tower.
|
| 533 |
-
"vision_tower.
|
| 534 |
-
"vision_tower.
|
| 535 |
-
"vision_tower.
|
| 536 |
-
"vision_tower.
|
| 537 |
-
"vision_tower.
|
| 538 |
-
"vision_tower.
|
| 539 |
-
"vision_tower.
|
| 540 |
-
"vision_tower.
|
| 541 |
-
"vision_tower.
|
| 542 |
-
"vision_tower.
|
| 543 |
-
"vision_tower.
|
| 544 |
-
"vision_tower.
|
| 545 |
-
"vision_tower.
|
| 546 |
-
"vision_tower.
|
| 547 |
-
"vision_tower.
|
| 548 |
-
"vision_tower.
|
| 549 |
-
"vision_tower.
|
| 550 |
-
"vision_tower.
|
| 551 |
-
"vision_tower.
|
| 552 |
-
"vision_tower.
|
| 553 |
-
"vision_tower.
|
| 554 |
-
"vision_tower.
|
| 555 |
-
"vision_tower.
|
| 556 |
-
"vision_tower.
|
| 557 |
-
"vision_tower.
|
| 558 |
-
"vision_tower.
|
| 559 |
-
"vision_tower.
|
| 560 |
-
"vision_tower.
|
| 561 |
-
"vision_tower.
|
| 562 |
-
"vision_tower.
|
| 563 |
-
"vision_tower.
|
| 564 |
-
"vision_tower.
|
| 565 |
-
"vision_tower.
|
| 566 |
-
"vision_tower.
|
| 567 |
-
"vision_tower.
|
| 568 |
-
"vision_tower.
|
| 569 |
-
"vision_tower.
|
| 570 |
-
"vision_tower.
|
| 571 |
-
"vision_tower.
|
| 572 |
-
"vision_tower.
|
| 573 |
-
"vision_tower.
|
| 574 |
-
"vision_tower.
|
| 575 |
-
"vision_tower.
|
| 576 |
-
"vision_tower.
|
| 577 |
-
"vision_tower.
|
| 578 |
-
"vision_tower.
|
| 579 |
-
"vision_tower.
|
| 580 |
-
"vision_tower.
|
| 581 |
-
"vision_tower.
|
| 582 |
-
"vision_tower.
|
| 583 |
-
"vision_tower.
|
| 584 |
-
"vision_tower.
|
| 585 |
-
"vision_tower.
|
| 586 |
-
"vision_tower.
|
| 587 |
-
"vision_tower.
|
| 588 |
-
"vision_tower.
|
| 589 |
-
"vision_tower.
|
| 590 |
-
"vision_tower.
|
| 591 |
-
"vision_tower.
|
| 592 |
-
"vision_tower.
|
| 593 |
-
"vision_tower.
|
| 594 |
-
"vision_tower.
|
| 595 |
-
"vision_tower.
|
| 596 |
-
"vision_tower.
|
| 597 |
-
"vision_tower.
|
| 598 |
-
"vision_tower.
|
| 599 |
-
"vision_tower.
|
| 600 |
-
"vision_tower.
|
| 601 |
-
"vision_tower.
|
| 602 |
-
"vision_tower.
|
| 603 |
-
"vision_tower.
|
| 604 |
-
"vision_tower.
|
| 605 |
-
"vision_tower.
|
| 606 |
-
"vision_tower.
|
| 607 |
-
"vision_tower.
|
| 608 |
-
"vision_tower.
|
| 609 |
-
"vision_tower.
|
| 610 |
-
"vision_tower.
|
| 611 |
-
"vision_tower.
|
| 612 |
-
"vision_tower.
|
| 613 |
-
"vision_tower.
|
| 614 |
-
"vision_tower.
|
| 615 |
-
"vision_tower.
|
| 616 |
-
"vision_tower.
|
| 617 |
-
"vision_tower.
|
| 618 |
-
"vision_tower.
|
| 619 |
-
"vision_tower.
|
| 620 |
-
"vision_tower.
|
| 621 |
-
"vision_tower.
|
| 622 |
-
"vision_tower.
|
| 623 |
-
"vision_tower.
|
| 624 |
-
"vision_tower.
|
| 625 |
-
"vision_tower.
|
| 626 |
-
"vision_tower.
|
| 627 |
-
"vision_tower.
|
| 628 |
-
"vision_tower.
|
| 629 |
-
"vision_tower.
|
| 630 |
-
"vision_tower.
|
| 631 |
-
"vision_tower.
|
| 632 |
-
"vision_tower.
|
| 633 |
-
"vision_tower.
|
| 634 |
-
"vision_tower.
|
| 635 |
-
"vision_tower.
|
| 636 |
-
"vision_tower.
|
| 637 |
-
"vision_tower.
|
| 638 |
-
"vision_tower.
|
| 639 |
-
"vision_tower.
|
| 640 |
-
"vision_tower.
|
| 641 |
-
"vision_tower.
|
| 642 |
-
"vision_tower.
|
| 643 |
-
"vision_tower.
|
| 644 |
-
"vision_tower.
|
| 645 |
-
"vision_tower.
|
| 646 |
-
"vision_tower.
|
| 647 |
-
"vision_tower.
|
| 648 |
-
"vision_tower.
|
| 649 |
-
"vision_tower.
|
| 650 |
-
"vision_tower.
|
| 651 |
-
"vision_tower.
|
| 652 |
-
"vision_tower.
|
| 653 |
-
"vision_tower.
|
| 654 |
-
"vision_tower.
|
| 655 |
-
"vision_tower.
|
| 656 |
-
"vision_tower.
|
| 657 |
-
"vision_tower.
|
| 658 |
-
"vision_tower.
|
| 659 |
-
"vision_tower.
|
| 660 |
-
"vision_tower.
|
| 661 |
-
"vision_tower.
|
| 662 |
-
"vision_tower.
|
| 663 |
-
"vision_tower.
|
| 664 |
-
"vision_tower.
|
| 665 |
-
"vision_tower.
|
| 666 |
-
"vision_tower.
|
| 667 |
-
"vision_tower.
|
| 668 |
-
"vision_tower.
|
| 669 |
-
"vision_tower.
|
| 670 |
-
"vision_tower.
|
| 671 |
-
"vision_tower.
|
| 672 |
-
"vision_tower.
|
| 673 |
-
"vision_tower.
|
| 674 |
-
"vision_tower.
|
| 675 |
-
"vision_tower.
|
| 676 |
-
"vision_tower.
|
| 677 |
-
"vision_tower.
|
| 678 |
-
"vision_tower.
|
| 679 |
-
"vision_tower.
|
| 680 |
-
"vision_tower.
|
| 681 |
-
"vision_tower.
|
| 682 |
-
"vision_tower.
|
| 683 |
-
"vision_tower.
|
| 684 |
-
"vision_tower.
|
| 685 |
-
"vision_tower.
|
| 686 |
-
"vision_tower.
|
| 687 |
-
"vision_tower.
|
| 688 |
-
"vision_tower.
|
| 689 |
-
"vision_tower.
|
| 690 |
-
"vision_tower.
|
| 691 |
-
"vision_tower.
|
| 692 |
-
"vision_tower.
|
| 693 |
-
"vision_tower.
|
| 694 |
-
"vision_tower.
|
| 695 |
-
"vision_tower.
|
| 696 |
-
"vision_tower.
|
| 697 |
-
"vision_tower.
|
| 698 |
-
"vision_tower.
|
| 699 |
-
"vision_tower.
|
| 700 |
-
"vision_tower.
|
| 701 |
-
"vision_tower.
|
| 702 |
-
"vision_tower.
|
| 703 |
-
"vision_tower.
|
| 704 |
-
"vision_tower.
|
| 705 |
-
"vision_tower.
|
| 706 |
-
"vision_tower.
|
| 707 |
-
"vision_tower.
|
| 708 |
-
"vision_tower.
|
| 709 |
-
"vision_tower.
|
| 710 |
-
"vision_tower.
|
| 711 |
-
"vision_tower.
|
| 712 |
-
"vision_tower.
|
| 713 |
-
"vision_tower.
|
| 714 |
-
"vision_tower.
|
| 715 |
-
"vision_tower.
|
| 716 |
-
"vision_tower.
|
| 717 |
-
"vision_tower.
|
| 718 |
-
"vision_tower.
|
| 719 |
-
"vision_tower.
|
| 720 |
-
"vision_tower.
|
| 721 |
-
"vision_tower.
|
| 722 |
-
"vision_tower.
|
| 723 |
-
"vision_tower.
|
| 724 |
-
"vision_tower.
|
| 725 |
-
"vision_tower.
|
| 726 |
-
"vision_tower.
|
| 727 |
-
"vision_tower.
|
| 728 |
-
"vision_tower.
|
| 729 |
-
"vision_tower.
|
| 730 |
-
"vision_tower.
|
| 731 |
-
"vision_tower.
|
| 732 |
-
"vision_tower.
|
| 733 |
-
"vision_tower.
|
| 734 |
-
"vision_tower.
|
| 735 |
-
"vision_tower.
|
| 736 |
-
"vision_tower.
|
| 737 |
-
"vision_tower.
|
| 738 |
-
"vision_tower.
|
| 739 |
-
"vision_tower.
|
| 740 |
-
"vision_tower.
|
| 741 |
-
"vision_tower.
|
| 742 |
-
"vision_tower.
|
| 743 |
-
"vision_tower.
|
| 744 |
-
"vision_tower.
|
| 745 |
-
"vision_tower.
|
| 746 |
-
"vision_tower.
|
| 747 |
-
"vision_tower.
|
| 748 |
-
"vision_tower.
|
| 749 |
-
"vision_tower.
|
| 750 |
-
"vision_tower.
|
| 751 |
-
"vision_tower.
|
| 752 |
-
"vision_tower.
|
| 753 |
-
"vision_tower.
|
| 754 |
-
"vision_tower.
|
| 755 |
-
"vision_tower.
|
| 756 |
-
"vision_tower.
|
| 757 |
-
"vision_tower.
|
| 758 |
-
"vision_tower.
|
| 759 |
-
"vision_tower.
|
| 760 |
-
"vision_tower.
|
| 761 |
-
"vision_tower.
|
| 762 |
-
"vision_tower.
|
| 763 |
-
"vision_tower.
|
| 764 |
-
"vision_tower.
|
| 765 |
-
"vision_tower.
|
| 766 |
-
"vision_tower.
|
| 767 |
-
"vision_tower.
|
| 768 |
-
"vision_tower.
|
| 769 |
-
"vision_tower.
|
| 770 |
-
"vision_tower.
|
| 771 |
-
"vision_tower.
|
| 772 |
-
"vision_tower.
|
| 773 |
-
"vision_tower.
|
| 774 |
-
"vision_tower.
|
| 775 |
-
"vision_tower.
|
| 776 |
-
"vision_tower.
|
| 777 |
-
"vision_tower.
|
| 778 |
-
"vision_tower.
|
| 779 |
-
"vision_tower.
|
| 780 |
-
"vision_tower.
|
| 781 |
-
"vision_tower.
|
| 782 |
-
"vision_tower.
|
| 783 |
-
"vision_tower.
|
| 784 |
-
"vision_tower.
|
| 785 |
-
"vision_tower.
|
| 786 |
-
"vision_tower.
|
| 787 |
-
"vision_tower.
|
| 788 |
-
"vision_tower.
|
| 789 |
-
"vision_tower.
|
| 790 |
-
"vision_tower.
|
| 791 |
-
"vision_tower.
|
| 792 |
-
"vision_tower.
|
| 793 |
-
"vision_tower.
|
| 794 |
-
"vision_tower.
|
| 795 |
-
"vision_tower.
|
| 796 |
-
"vision_tower.
|
| 797 |
-
"vision_tower.
|
|
|
|
|
|
|
| 798 |
}
|
| 799 |
}
|
|
|
|
| 1 |
{
|
| 2 |
"metadata": {
|
| 3 |
+
"total_size": 50614622432
|
| 4 |
},
|
| 5 |
"weight_map": {
|
| 6 |
"language_model.lm_head.weight": "model-00012-of-00012.safetensors",
|
|
|
|
| 345 |
"multi_modal_projector.cross_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 346 |
"multi_modal_projector.cross_attn.layer_norm.bias": "model-00001-of-00012.safetensors",
|
| 347 |
"multi_modal_projector.cross_attn.layer_norm.weight": "model-00001-of-00012.safetensors",
|
| 348 |
+
"multi_modal_projector.cross_attn.layer_norm_kv.bias": "model-00001-of-00012.safetensors",
|
| 349 |
+
"multi_modal_projector.cross_attn.layer_norm_kv.weight": "model-00001-of-00012.safetensors",
|
| 350 |
"multi_modal_projector.cross_attn.linear.bias": "model-00001-of-00012.safetensors",
|
| 351 |
"multi_modal_projector.cross_attn.linear.weight": "model-00001-of-00012.safetensors",
|
|
|
|
|
|
|
| 352 |
"multi_modal_projector.cross_attn.multihead_attn.in_proj_bias": "model-00001-of-00012.safetensors",
|
| 353 |
"multi_modal_projector.cross_attn.multihead_attn.in_proj_weight": "model-00001-of-00012.safetensors",
|
| 354 |
"multi_modal_projector.cross_attn.multihead_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 355 |
"multi_modal_projector.cross_attn.multihead_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 356 |
"multi_modal_projector.cross_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 357 |
"multi_modal_projector.cross_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 358 |
+
"multi_modal_projector.feed_forward.linear_in.weight": "model-00001-of-00012.safetensors",
|
| 359 |
+
"multi_modal_projector.feed_forward.linear_out.weight": "model-00001-of-00012.safetensors",
|
| 360 |
+
"multi_modal_projector.layer_norm.bias": "model-00001-of-00012.safetensors",
|
| 361 |
+
"multi_modal_projector.layer_norm.weight": "model-00001-of-00012.safetensors",
|
| 362 |
"multi_modal_projector.query": "model-00001-of-00012.safetensors",
|
| 363 |
+
"vision_tower.embeddings.patch_embedding.bias": "model-00001-of-00012.safetensors",
|
| 364 |
+
"vision_tower.embeddings.patch_embedding.weight": "model-00001-of-00012.safetensors",
|
| 365 |
+
"vision_tower.embeddings.position_embedding.weight": "model-00001-of-00012.safetensors",
|
| 366 |
+
"vision_tower.encoder.layers.0.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 367 |
+
"vision_tower.encoder.layers.0.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 368 |
+
"vision_tower.encoder.layers.0.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 369 |
+
"vision_tower.encoder.layers.0.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 370 |
+
"vision_tower.encoder.layers.0.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 371 |
+
"vision_tower.encoder.layers.0.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 372 |
+
"vision_tower.encoder.layers.0.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 373 |
+
"vision_tower.encoder.layers.0.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 374 |
+
"vision_tower.encoder.layers.0.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 375 |
+
"vision_tower.encoder.layers.0.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 376 |
+
"vision_tower.encoder.layers.0.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 377 |
+
"vision_tower.encoder.layers.0.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 378 |
+
"vision_tower.encoder.layers.0.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 379 |
+
"vision_tower.encoder.layers.0.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 380 |
+
"vision_tower.encoder.layers.0.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 381 |
+
"vision_tower.encoder.layers.0.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 382 |
+
"vision_tower.encoder.layers.1.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 383 |
+
"vision_tower.encoder.layers.1.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 384 |
+
"vision_tower.encoder.layers.1.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 385 |
+
"vision_tower.encoder.layers.1.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 386 |
+
"vision_tower.encoder.layers.1.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 387 |
+
"vision_tower.encoder.layers.1.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 388 |
+
"vision_tower.encoder.layers.1.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 389 |
+
"vision_tower.encoder.layers.1.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 390 |
+
"vision_tower.encoder.layers.1.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 391 |
+
"vision_tower.encoder.layers.1.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 392 |
+
"vision_tower.encoder.layers.1.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 393 |
+
"vision_tower.encoder.layers.1.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 394 |
+
"vision_tower.encoder.layers.1.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 395 |
+
"vision_tower.encoder.layers.1.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 396 |
+
"vision_tower.encoder.layers.1.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 397 |
+
"vision_tower.encoder.layers.1.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 398 |
+
"vision_tower.encoder.layers.10.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 399 |
+
"vision_tower.encoder.layers.10.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 400 |
+
"vision_tower.encoder.layers.10.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 401 |
+
"vision_tower.encoder.layers.10.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 402 |
+
"vision_tower.encoder.layers.10.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 403 |
+
"vision_tower.encoder.layers.10.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 404 |
+
"vision_tower.encoder.layers.10.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 405 |
+
"vision_tower.encoder.layers.10.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 406 |
+
"vision_tower.encoder.layers.10.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 407 |
+
"vision_tower.encoder.layers.10.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 408 |
+
"vision_tower.encoder.layers.10.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 409 |
+
"vision_tower.encoder.layers.10.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 410 |
+
"vision_tower.encoder.layers.10.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 411 |
+
"vision_tower.encoder.layers.10.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 412 |
+
"vision_tower.encoder.layers.10.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 413 |
+
"vision_tower.encoder.layers.10.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 414 |
+
"vision_tower.encoder.layers.11.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 415 |
+
"vision_tower.encoder.layers.11.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 416 |
+
"vision_tower.encoder.layers.11.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 417 |
+
"vision_tower.encoder.layers.11.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 418 |
+
"vision_tower.encoder.layers.11.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 419 |
+
"vision_tower.encoder.layers.11.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 420 |
+
"vision_tower.encoder.layers.11.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 421 |
+
"vision_tower.encoder.layers.11.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 422 |
+
"vision_tower.encoder.layers.11.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 423 |
+
"vision_tower.encoder.layers.11.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 424 |
+
"vision_tower.encoder.layers.11.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 425 |
+
"vision_tower.encoder.layers.11.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 426 |
+
"vision_tower.encoder.layers.11.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 427 |
+
"vision_tower.encoder.layers.11.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 428 |
+
"vision_tower.encoder.layers.11.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 429 |
+
"vision_tower.encoder.layers.11.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 430 |
+
"vision_tower.encoder.layers.12.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 431 |
+
"vision_tower.encoder.layers.12.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 432 |
+
"vision_tower.encoder.layers.12.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 433 |
+
"vision_tower.encoder.layers.12.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 434 |
+
"vision_tower.encoder.layers.12.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 435 |
+
"vision_tower.encoder.layers.12.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 436 |
+
"vision_tower.encoder.layers.12.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 437 |
+
"vision_tower.encoder.layers.12.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 438 |
+
"vision_tower.encoder.layers.12.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 439 |
+
"vision_tower.encoder.layers.12.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 440 |
+
"vision_tower.encoder.layers.12.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 441 |
+
"vision_tower.encoder.layers.12.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 442 |
+
"vision_tower.encoder.layers.12.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 443 |
+
"vision_tower.encoder.layers.12.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 444 |
+
"vision_tower.encoder.layers.12.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 445 |
+
"vision_tower.encoder.layers.12.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 446 |
+
"vision_tower.encoder.layers.13.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 447 |
+
"vision_tower.encoder.layers.13.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 448 |
+
"vision_tower.encoder.layers.13.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 449 |
+
"vision_tower.encoder.layers.13.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 450 |
+
"vision_tower.encoder.layers.13.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 451 |
+
"vision_tower.encoder.layers.13.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 452 |
+
"vision_tower.encoder.layers.13.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 453 |
+
"vision_tower.encoder.layers.13.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 454 |
+
"vision_tower.encoder.layers.13.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 455 |
+
"vision_tower.encoder.layers.13.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 456 |
+
"vision_tower.encoder.layers.13.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 457 |
+
"vision_tower.encoder.layers.13.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 458 |
+
"vision_tower.encoder.layers.13.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 459 |
+
"vision_tower.encoder.layers.13.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 460 |
+
"vision_tower.encoder.layers.13.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 461 |
+
"vision_tower.encoder.layers.13.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 462 |
+
"vision_tower.encoder.layers.14.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 463 |
+
"vision_tower.encoder.layers.14.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 464 |
+
"vision_tower.encoder.layers.14.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 465 |
+
"vision_tower.encoder.layers.14.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 466 |
+
"vision_tower.encoder.layers.14.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 467 |
+
"vision_tower.encoder.layers.14.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 468 |
+
"vision_tower.encoder.layers.14.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 469 |
+
"vision_tower.encoder.layers.14.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 470 |
+
"vision_tower.encoder.layers.14.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 471 |
+
"vision_tower.encoder.layers.14.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 472 |
+
"vision_tower.encoder.layers.14.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 473 |
+
"vision_tower.encoder.layers.14.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 474 |
+
"vision_tower.encoder.layers.14.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 475 |
+
"vision_tower.encoder.layers.14.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 476 |
+
"vision_tower.encoder.layers.14.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 477 |
+
"vision_tower.encoder.layers.14.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 478 |
+
"vision_tower.encoder.layers.15.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 479 |
+
"vision_tower.encoder.layers.15.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 480 |
+
"vision_tower.encoder.layers.15.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 481 |
+
"vision_tower.encoder.layers.15.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 482 |
+
"vision_tower.encoder.layers.15.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 483 |
+
"vision_tower.encoder.layers.15.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 484 |
+
"vision_tower.encoder.layers.15.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 485 |
+
"vision_tower.encoder.layers.15.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 486 |
+
"vision_tower.encoder.layers.15.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 487 |
+
"vision_tower.encoder.layers.15.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 488 |
+
"vision_tower.encoder.layers.15.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 489 |
+
"vision_tower.encoder.layers.15.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 490 |
+
"vision_tower.encoder.layers.15.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 491 |
+
"vision_tower.encoder.layers.15.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 492 |
+
"vision_tower.encoder.layers.15.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 493 |
+
"vision_tower.encoder.layers.15.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 494 |
+
"vision_tower.encoder.layers.16.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 495 |
+
"vision_tower.encoder.layers.16.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 496 |
+
"vision_tower.encoder.layers.16.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 497 |
+
"vision_tower.encoder.layers.16.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 498 |
+
"vision_tower.encoder.layers.16.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 499 |
+
"vision_tower.encoder.layers.16.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 500 |
+
"vision_tower.encoder.layers.16.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 501 |
+
"vision_tower.encoder.layers.16.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 502 |
+
"vision_tower.encoder.layers.16.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 503 |
+
"vision_tower.encoder.layers.16.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 504 |
+
"vision_tower.encoder.layers.16.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 505 |
+
"vision_tower.encoder.layers.16.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 506 |
+
"vision_tower.encoder.layers.16.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 507 |
+
"vision_tower.encoder.layers.16.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 508 |
+
"vision_tower.encoder.layers.16.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 509 |
+
"vision_tower.encoder.layers.16.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 510 |
+
"vision_tower.encoder.layers.17.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 511 |
+
"vision_tower.encoder.layers.17.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 512 |
+
"vision_tower.encoder.layers.17.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 513 |
+
"vision_tower.encoder.layers.17.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 514 |
+
"vision_tower.encoder.layers.17.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 515 |
+
"vision_tower.encoder.layers.17.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 516 |
+
"vision_tower.encoder.layers.17.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 517 |
+
"vision_tower.encoder.layers.17.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 518 |
+
"vision_tower.encoder.layers.17.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 519 |
+
"vision_tower.encoder.layers.17.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 520 |
+
"vision_tower.encoder.layers.17.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 521 |
+
"vision_tower.encoder.layers.17.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 522 |
+
"vision_tower.encoder.layers.17.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 523 |
+
"vision_tower.encoder.layers.17.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 524 |
+
"vision_tower.encoder.layers.17.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 525 |
+
"vision_tower.encoder.layers.17.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 526 |
+
"vision_tower.encoder.layers.18.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 527 |
+
"vision_tower.encoder.layers.18.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 528 |
+
"vision_tower.encoder.layers.18.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 529 |
+
"vision_tower.encoder.layers.18.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 530 |
+
"vision_tower.encoder.layers.18.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 531 |
+
"vision_tower.encoder.layers.18.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 532 |
+
"vision_tower.encoder.layers.18.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 533 |
+
"vision_tower.encoder.layers.18.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 534 |
+
"vision_tower.encoder.layers.18.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 535 |
+
"vision_tower.encoder.layers.18.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 536 |
+
"vision_tower.encoder.layers.18.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 537 |
+
"vision_tower.encoder.layers.18.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 538 |
+
"vision_tower.encoder.layers.18.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 539 |
+
"vision_tower.encoder.layers.18.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 540 |
+
"vision_tower.encoder.layers.18.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 541 |
+
"vision_tower.encoder.layers.18.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 542 |
+
"vision_tower.encoder.layers.19.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 543 |
+
"vision_tower.encoder.layers.19.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 544 |
+
"vision_tower.encoder.layers.19.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 545 |
+
"vision_tower.encoder.layers.19.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 546 |
+
"vision_tower.encoder.layers.19.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 547 |
+
"vision_tower.encoder.layers.19.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 548 |
+
"vision_tower.encoder.layers.19.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 549 |
+
"vision_tower.encoder.layers.19.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 550 |
+
"vision_tower.encoder.layers.19.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 551 |
+
"vision_tower.encoder.layers.19.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 552 |
+
"vision_tower.encoder.layers.19.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 553 |
+
"vision_tower.encoder.layers.19.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 554 |
+
"vision_tower.encoder.layers.19.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 555 |
+
"vision_tower.encoder.layers.19.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 556 |
+
"vision_tower.encoder.layers.19.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 557 |
+
"vision_tower.encoder.layers.19.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 558 |
+
"vision_tower.encoder.layers.2.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 559 |
+
"vision_tower.encoder.layers.2.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 560 |
+
"vision_tower.encoder.layers.2.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 561 |
+
"vision_tower.encoder.layers.2.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 562 |
+
"vision_tower.encoder.layers.2.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 563 |
+
"vision_tower.encoder.layers.2.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 564 |
+
"vision_tower.encoder.layers.2.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 565 |
+
"vision_tower.encoder.layers.2.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 566 |
+
"vision_tower.encoder.layers.2.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 567 |
+
"vision_tower.encoder.layers.2.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 568 |
+
"vision_tower.encoder.layers.2.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 569 |
+
"vision_tower.encoder.layers.2.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 570 |
+
"vision_tower.encoder.layers.2.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 571 |
+
"vision_tower.encoder.layers.2.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 572 |
+
"vision_tower.encoder.layers.2.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 573 |
+
"vision_tower.encoder.layers.2.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 574 |
+
"vision_tower.encoder.layers.20.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 575 |
+
"vision_tower.encoder.layers.20.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 576 |
+
"vision_tower.encoder.layers.20.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 577 |
+
"vision_tower.encoder.layers.20.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 578 |
+
"vision_tower.encoder.layers.20.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 579 |
+
"vision_tower.encoder.layers.20.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 580 |
+
"vision_tower.encoder.layers.20.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 581 |
+
"vision_tower.encoder.layers.20.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 582 |
+
"vision_tower.encoder.layers.20.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 583 |
+
"vision_tower.encoder.layers.20.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 584 |
+
"vision_tower.encoder.layers.20.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 585 |
+
"vision_tower.encoder.layers.20.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 586 |
+
"vision_tower.encoder.layers.20.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 587 |
+
"vision_tower.encoder.layers.20.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 588 |
+
"vision_tower.encoder.layers.20.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 589 |
+
"vision_tower.encoder.layers.20.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 590 |
+
"vision_tower.encoder.layers.21.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 591 |
+
"vision_tower.encoder.layers.21.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 592 |
+
"vision_tower.encoder.layers.21.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 593 |
+
"vision_tower.encoder.layers.21.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 594 |
+
"vision_tower.encoder.layers.21.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 595 |
+
"vision_tower.encoder.layers.21.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 596 |
+
"vision_tower.encoder.layers.21.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 597 |
+
"vision_tower.encoder.layers.21.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 598 |
+
"vision_tower.encoder.layers.21.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 599 |
+
"vision_tower.encoder.layers.21.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 600 |
+
"vision_tower.encoder.layers.21.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 601 |
+
"vision_tower.encoder.layers.21.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 602 |
+
"vision_tower.encoder.layers.21.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 603 |
+
"vision_tower.encoder.layers.21.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 604 |
+
"vision_tower.encoder.layers.21.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 605 |
+
"vision_tower.encoder.layers.21.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 606 |
+
"vision_tower.encoder.layers.22.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 607 |
+
"vision_tower.encoder.layers.22.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 608 |
+
"vision_tower.encoder.layers.22.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 609 |
+
"vision_tower.encoder.layers.22.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 610 |
+
"vision_tower.encoder.layers.22.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 611 |
+
"vision_tower.encoder.layers.22.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 612 |
+
"vision_tower.encoder.layers.22.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 613 |
+
"vision_tower.encoder.layers.22.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 614 |
+
"vision_tower.encoder.layers.22.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 615 |
+
"vision_tower.encoder.layers.22.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 616 |
+
"vision_tower.encoder.layers.22.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 617 |
+
"vision_tower.encoder.layers.22.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 618 |
+
"vision_tower.encoder.layers.22.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 619 |
+
"vision_tower.encoder.layers.22.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 620 |
+
"vision_tower.encoder.layers.22.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 621 |
+
"vision_tower.encoder.layers.22.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 622 |
+
"vision_tower.encoder.layers.23.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 623 |
+
"vision_tower.encoder.layers.23.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 624 |
+
"vision_tower.encoder.layers.23.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 625 |
+
"vision_tower.encoder.layers.23.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 626 |
+
"vision_tower.encoder.layers.23.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 627 |
+
"vision_tower.encoder.layers.23.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 628 |
+
"vision_tower.encoder.layers.23.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 629 |
+
"vision_tower.encoder.layers.23.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 630 |
+
"vision_tower.encoder.layers.23.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 631 |
+
"vision_tower.encoder.layers.23.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 632 |
+
"vision_tower.encoder.layers.23.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 633 |
+
"vision_tower.encoder.layers.23.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 634 |
+
"vision_tower.encoder.layers.23.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 635 |
+
"vision_tower.encoder.layers.23.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 636 |
+
"vision_tower.encoder.layers.23.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 637 |
+
"vision_tower.encoder.layers.23.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 638 |
+
"vision_tower.encoder.layers.24.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 639 |
+
"vision_tower.encoder.layers.24.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 640 |
+
"vision_tower.encoder.layers.24.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 641 |
+
"vision_tower.encoder.layers.24.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 642 |
+
"vision_tower.encoder.layers.24.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 643 |
+
"vision_tower.encoder.layers.24.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 644 |
+
"vision_tower.encoder.layers.24.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 645 |
+
"vision_tower.encoder.layers.24.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 646 |
+
"vision_tower.encoder.layers.24.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 647 |
+
"vision_tower.encoder.layers.24.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 648 |
+
"vision_tower.encoder.layers.24.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 649 |
+
"vision_tower.encoder.layers.24.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 650 |
+
"vision_tower.encoder.layers.24.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 651 |
+
"vision_tower.encoder.layers.24.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 652 |
+
"vision_tower.encoder.layers.24.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 653 |
+
"vision_tower.encoder.layers.24.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 654 |
+
"vision_tower.encoder.layers.25.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 655 |
+
"vision_tower.encoder.layers.25.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 656 |
+
"vision_tower.encoder.layers.25.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 657 |
+
"vision_tower.encoder.layers.25.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 658 |
+
"vision_tower.encoder.layers.25.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 659 |
+
"vision_tower.encoder.layers.25.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 660 |
+
"vision_tower.encoder.layers.25.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 661 |
+
"vision_tower.encoder.layers.25.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 662 |
+
"vision_tower.encoder.layers.25.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 663 |
+
"vision_tower.encoder.layers.25.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 664 |
+
"vision_tower.encoder.layers.25.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 665 |
+
"vision_tower.encoder.layers.25.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 666 |
+
"vision_tower.encoder.layers.25.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 667 |
+
"vision_tower.encoder.layers.25.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 668 |
+
"vision_tower.encoder.layers.25.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 669 |
+
"vision_tower.encoder.layers.25.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 670 |
+
"vision_tower.encoder.layers.26.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 671 |
+
"vision_tower.encoder.layers.26.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 672 |
+
"vision_tower.encoder.layers.26.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 673 |
+
"vision_tower.encoder.layers.26.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 674 |
+
"vision_tower.encoder.layers.26.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 675 |
+
"vision_tower.encoder.layers.26.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 676 |
+
"vision_tower.encoder.layers.26.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 677 |
+
"vision_tower.encoder.layers.26.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 678 |
+
"vision_tower.encoder.layers.26.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 679 |
+
"vision_tower.encoder.layers.26.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 680 |
+
"vision_tower.encoder.layers.26.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 681 |
+
"vision_tower.encoder.layers.26.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 682 |
+
"vision_tower.encoder.layers.26.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 683 |
+
"vision_tower.encoder.layers.26.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 684 |
+
"vision_tower.encoder.layers.26.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 685 |
+
"vision_tower.encoder.layers.26.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 686 |
+
"vision_tower.encoder.layers.3.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 687 |
+
"vision_tower.encoder.layers.3.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 688 |
+
"vision_tower.encoder.layers.3.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 689 |
+
"vision_tower.encoder.layers.3.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 690 |
+
"vision_tower.encoder.layers.3.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 691 |
+
"vision_tower.encoder.layers.3.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 692 |
+
"vision_tower.encoder.layers.3.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 693 |
+
"vision_tower.encoder.layers.3.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 694 |
+
"vision_tower.encoder.layers.3.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 695 |
+
"vision_tower.encoder.layers.3.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 696 |
+
"vision_tower.encoder.layers.3.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 697 |
+
"vision_tower.encoder.layers.3.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 698 |
+
"vision_tower.encoder.layers.3.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 699 |
+
"vision_tower.encoder.layers.3.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 700 |
+
"vision_tower.encoder.layers.3.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 701 |
+
"vision_tower.encoder.layers.3.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 702 |
+
"vision_tower.encoder.layers.4.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 703 |
+
"vision_tower.encoder.layers.4.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 704 |
+
"vision_tower.encoder.layers.4.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 705 |
+
"vision_tower.encoder.layers.4.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 706 |
+
"vision_tower.encoder.layers.4.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 707 |
+
"vision_tower.encoder.layers.4.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 708 |
+
"vision_tower.encoder.layers.4.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 709 |
+
"vision_tower.encoder.layers.4.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 710 |
+
"vision_tower.encoder.layers.4.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 711 |
+
"vision_tower.encoder.layers.4.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 712 |
+
"vision_tower.encoder.layers.4.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 713 |
+
"vision_tower.encoder.layers.4.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 714 |
+
"vision_tower.encoder.layers.4.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 715 |
+
"vision_tower.encoder.layers.4.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 716 |
+
"vision_tower.encoder.layers.4.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 717 |
+
"vision_tower.encoder.layers.4.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 718 |
+
"vision_tower.encoder.layers.5.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 719 |
+
"vision_tower.encoder.layers.5.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 720 |
+
"vision_tower.encoder.layers.5.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 721 |
+
"vision_tower.encoder.layers.5.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 722 |
+
"vision_tower.encoder.layers.5.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 723 |
+
"vision_tower.encoder.layers.5.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 724 |
+
"vision_tower.encoder.layers.5.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 725 |
+
"vision_tower.encoder.layers.5.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 726 |
+
"vision_tower.encoder.layers.5.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 727 |
+
"vision_tower.encoder.layers.5.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 728 |
+
"vision_tower.encoder.layers.5.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 729 |
+
"vision_tower.encoder.layers.5.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 730 |
+
"vision_tower.encoder.layers.5.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 731 |
+
"vision_tower.encoder.layers.5.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 732 |
+
"vision_tower.encoder.layers.5.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 733 |
+
"vision_tower.encoder.layers.5.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 734 |
+
"vision_tower.encoder.layers.6.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 735 |
+
"vision_tower.encoder.layers.6.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 736 |
+
"vision_tower.encoder.layers.6.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 737 |
+
"vision_tower.encoder.layers.6.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 738 |
+
"vision_tower.encoder.layers.6.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 739 |
+
"vision_tower.encoder.layers.6.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 740 |
+
"vision_tower.encoder.layers.6.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 741 |
+
"vision_tower.encoder.layers.6.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 742 |
+
"vision_tower.encoder.layers.6.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 743 |
+
"vision_tower.encoder.layers.6.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 744 |
+
"vision_tower.encoder.layers.6.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 745 |
+
"vision_tower.encoder.layers.6.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 746 |
+
"vision_tower.encoder.layers.6.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 747 |
+
"vision_tower.encoder.layers.6.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 748 |
+
"vision_tower.encoder.layers.6.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 749 |
+
"vision_tower.encoder.layers.6.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 750 |
+
"vision_tower.encoder.layers.7.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 751 |
+
"vision_tower.encoder.layers.7.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 752 |
+
"vision_tower.encoder.layers.7.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 753 |
+
"vision_tower.encoder.layers.7.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 754 |
+
"vision_tower.encoder.layers.7.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 755 |
+
"vision_tower.encoder.layers.7.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 756 |
+
"vision_tower.encoder.layers.7.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 757 |
+
"vision_tower.encoder.layers.7.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 758 |
+
"vision_tower.encoder.layers.7.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 759 |
+
"vision_tower.encoder.layers.7.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 760 |
+
"vision_tower.encoder.layers.7.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 761 |
+
"vision_tower.encoder.layers.7.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 762 |
+
"vision_tower.encoder.layers.7.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 763 |
+
"vision_tower.encoder.layers.7.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 764 |
+
"vision_tower.encoder.layers.7.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 765 |
+
"vision_tower.encoder.layers.7.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 766 |
+
"vision_tower.encoder.layers.8.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 767 |
+
"vision_tower.encoder.layers.8.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 768 |
+
"vision_tower.encoder.layers.8.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 769 |
+
"vision_tower.encoder.layers.8.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 770 |
+
"vision_tower.encoder.layers.8.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 771 |
+
"vision_tower.encoder.layers.8.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 772 |
+
"vision_tower.encoder.layers.8.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 773 |
+
"vision_tower.encoder.layers.8.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 774 |
+
"vision_tower.encoder.layers.8.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 775 |
+
"vision_tower.encoder.layers.8.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 776 |
+
"vision_tower.encoder.layers.8.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 777 |
+
"vision_tower.encoder.layers.8.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 778 |
+
"vision_tower.encoder.layers.8.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 779 |
+
"vision_tower.encoder.layers.8.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 780 |
+
"vision_tower.encoder.layers.8.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 781 |
+
"vision_tower.encoder.layers.8.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 782 |
+
"vision_tower.encoder.layers.9.layer_norm1.bias": "model-00001-of-00012.safetensors",
|
| 783 |
+
"vision_tower.encoder.layers.9.layer_norm1.weight": "model-00001-of-00012.safetensors",
|
| 784 |
+
"vision_tower.encoder.layers.9.layer_norm2.bias": "model-00001-of-00012.safetensors",
|
| 785 |
+
"vision_tower.encoder.layers.9.layer_norm2.weight": "model-00001-of-00012.safetensors",
|
| 786 |
+
"vision_tower.encoder.layers.9.mlp.fc1.bias": "model-00001-of-00012.safetensors",
|
| 787 |
+
"vision_tower.encoder.layers.9.mlp.fc1.weight": "model-00001-of-00012.safetensors",
|
| 788 |
+
"vision_tower.encoder.layers.9.mlp.fc2.bias": "model-00001-of-00012.safetensors",
|
| 789 |
+
"vision_tower.encoder.layers.9.mlp.fc2.weight": "model-00001-of-00012.safetensors",
|
| 790 |
+
"vision_tower.encoder.layers.9.self_attn.k_proj.bias": "model-00001-of-00012.safetensors",
|
| 791 |
+
"vision_tower.encoder.layers.9.self_attn.k_proj.weight": "model-00001-of-00012.safetensors",
|
| 792 |
+
"vision_tower.encoder.layers.9.self_attn.out_proj.bias": "model-00001-of-00012.safetensors",
|
| 793 |
+
"vision_tower.encoder.layers.9.self_attn.out_proj.weight": "model-00001-of-00012.safetensors",
|
| 794 |
+
"vision_tower.encoder.layers.9.self_attn.q_proj.bias": "model-00001-of-00012.safetensors",
|
| 795 |
+
"vision_tower.encoder.layers.9.self_attn.q_proj.weight": "model-00001-of-00012.safetensors",
|
| 796 |
+
"vision_tower.encoder.layers.9.self_attn.v_proj.bias": "model-00001-of-00012.safetensors",
|
| 797 |
+
"vision_tower.encoder.layers.9.self_attn.v_proj.weight": "model-00001-of-00012.safetensors",
|
| 798 |
+
"vision_tower.post_layernorm.bias": "model-00001-of-00012.safetensors",
|
| 799 |
+
"vision_tower.post_layernorm.weight": "model-00001-of-00012.safetensors"
|
| 800 |
}
|
| 801 |
}
|