erfanzar commited on
Commit
7dc7fb0
·
verified ·
1 Parent(s): bb4f2cb

Add files using upload-large-folder tool

Browse files
This view is limited to 50 files because it contains too many changes.   See raw diff
Files changed (50) hide show
  1. .gitattributes +293 -0
  2. model/model/language_model/embed_tokens/embedding/0.0 +3 -0
  3. model/model/language_model/embed_tokens/embedding/1.0 +3 -0
  4. model/model/language_model/embed_tokens/embedding/2.0 +3 -0
  5. model/model/language_model/embed_tokens/embedding/3.0 +3 -0
  6. model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
  7. model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
  8. model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 +3 -0
  9. model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
  10. model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 +3 -0
  11. model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 +3 -0
  12. model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 +3 -0
  13. model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 +3 -0
  14. model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 +3 -0
  15. model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 +3 -0
  16. model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 +3 -0
  17. model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 +3 -0
  18. model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 +3 -0
  19. model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 +3 -0
  20. model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 +3 -0
  21. model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 +3 -0
  22. model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 +3 -0
  23. model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 +3 -0
  24. model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 +3 -0
  25. model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 +3 -0
  26. model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 +3 -0
  27. model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 +3 -0
  28. model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 +3 -0
  29. model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 +3 -0
  30. model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 +3 -0
  31. model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 +3 -0
  32. model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 +3 -0
  33. model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 +3 -0
  34. model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 +3 -0
  35. model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 +3 -0
  36. model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 +3 -0
  37. model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 +3 -0
  38. model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 +3 -0
  39. model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 +3 -0
  40. model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 +3 -0
  41. model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 +3 -0
  42. model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 +3 -0
  43. model/model/language_model/layers/11/mlp/down_proj/kernel/0.1 +3 -0
  44. model/model/language_model/layers/11/mlp/down_proj/kernel/0.2 +3 -0
  45. model/model/language_model/layers/11/self_attn/k_proj/kernel/3.0 +3 -0
  46. model/model/language_model/layers/11/self_attn/o_proj/kernel/0.2 +3 -0
  47. model/model/language_model/layers/11/self_attn/q_proj/kernel/0.0 +3 -0
  48. model/model/language_model/layers/11/self_attn/q_proj/kernel/1.0 +3 -0
  49. model/model/language_model/layers/11/self_attn/q_proj/kernel/2.0 +3 -0
  50. model/model/language_model/layers/11/self_attn/q_proj/kernel/3.0 +3 -0
.gitattributes CHANGED
@@ -550,3 +550,296 @@ model/model/language_model/layers/3/self_attn/o_proj/kernel/0.2 filter=lfs diff=
550
  model/model/language_model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
551
  model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
552
  model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
550
  model/model/language_model/layers/3/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
551
  model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
552
  model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
553
+ model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
554
+ model/model/language_model/layers/3/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
555
+ model/model/language_model/layers/3/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
556
+ model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
557
+ model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
558
+ model/model/language_model/layers/3/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
559
+ model/model/language_model/layers/4/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
560
+ model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
561
+ model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
562
+ model/model/language_model/layers/4/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
563
+ model/model/language_model/layers/4/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
564
+ model/model/language_model/layers/3/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
565
+ model/model/language_model/layers/4/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
566
+ model/model/language_model/layers/3/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
567
+ model/model/language_model/layers/4/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
568
+ model/model/language_model/layers/4/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
569
+ model/model/language_model/layers/4/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
570
+ model/model/language_model/embed_tokens/embedding/3.0 filter=lfs diff=lfs merge=lfs -text
571
+ model/model/language_model/layers/4/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
572
+ model/model/language_model/layers/5/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
573
+ model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
574
+ model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
575
+ model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
576
+ model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
577
+ model/model/language_model/layers/4/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
578
+ model/model/language_model/layers/4/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
579
+ model/model/language_model/layers/4/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
580
+ model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
581
+ model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
582
+ model/model/language_model/layers/5/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
583
+ model/model/language_model/layers/4/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
584
+ model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
585
+ model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
586
+ model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
587
+ model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
588
+ model/model/language_model/layers/4/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
589
+ model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
590
+ model/model/language_model/layers/4/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
591
+ model/model/language_model/layers/5/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
592
+ model/model/language_model/layers/5/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
593
+ model/model/language_model/layers/5/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
594
+ model/model/language_model/layers/5/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
595
+ model/model/language_model/layers/5/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
596
+ model/model/language_model/layers/5/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
597
+ model/model/language_model/layers/6/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
598
+ model/model/language_model/layers/4/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
599
+ model/model/language_model/layers/5/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
600
+ model/model/language_model/layers/5/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
601
+ model/model/language_model/layers/5/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
602
+ model/model/language_model/layers/5/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
603
+ model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
604
+ model/model/language_model/layers/6/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
605
+ model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
606
+ model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
607
+ model/model/language_model/layers/7/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
608
+ model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
609
+ model/model/language_model/layers/5/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
610
+ model/model/language_model/layers/6/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
611
+ model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
612
+ model/model/language_model/layers/7/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
613
+ model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
614
+ model/model/language_model/layers/5/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
615
+ model/model/language_model/layers/6/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
616
+ model/model/language_model/layers/7/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
617
+ model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
618
+ model/model/language_model/layers/6/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
619
+ model/model/language_model/layers/6/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
620
+ model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
621
+ model/model/language_model/layers/6/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
622
+ model/model/language_model/layers/7/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
623
+ model/model/language_model/layers/7/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
624
+ model/model/language_model/layers/6/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
625
+ model/model/language_model/layers/7/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
626
+ model/model/language_model/layers/7/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
627
+ model/model/language_model/layers/6/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
628
+ model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
629
+ model/model/language_model/layers/7/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
630
+ model/model/language_model/layers/7/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
631
+ model/model/language_model/layers/5/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
632
+ model/model/language_model/layers/6/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
633
+ model/model/language_model/layers/7/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
634
+ model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
635
+ model/model/language_model/layers/7/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
636
+ model/model/language_model/layers/7/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
637
+ model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
638
+ model/model/language_model/layers/7/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
639
+ model/model/language_model/layers/7/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
640
+ model/model/language_model/layers/6/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
641
+ model/model/language_model/layers/6/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
642
+ model/model/language_model/layers/7/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
643
+ model/model/language_model/layers/7/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
644
+ model/model/language_model/layers/7/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
645
+ model/model/language_model/layers/7/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
646
+ model/model/language_model/layers/6/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
647
+ model/model/language_model/layers/7/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
648
+ model/model/language_model/layers/7/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
649
+ model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
650
+ model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
651
+ model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
652
+ model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
653
+ model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
654
+ model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
655
+ model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
656
+ model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
657
+ model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
658
+ model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
659
+ model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
660
+ model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
661
+ model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
662
+ model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
663
+ model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
664
+ model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
665
+ model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
666
+ model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
667
+ model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
668
+ model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
669
+ model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
670
+ model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
671
+ model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
672
+ model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
673
+ model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
674
+ model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
675
+ model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
676
+ model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
677
+ model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
678
+ model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
679
+ model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
680
+ model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
681
+ tokenizer.json filter=lfs diff=lfs merge=lfs -text
682
+ model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
683
+ model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
684
+ model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
685
+ model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
686
+ model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
687
+ model/model/language_model/layers/7/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
688
+ model/model/language_model/layers/7/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
689
+ model/model/language_model/layers/7/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
690
+ model/model/language_model/layers/6/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
691
+ model/model/language_model/layers/7/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
692
+ model/model/language_model/layers/7/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
693
+ model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
694
+ model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
695
+ model/model/language_model/layers/7/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
696
+ model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
697
+ model/model/language_model/layers/6/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
698
+ model/model/language_model/layers/8/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
699
+ model/model/language_model/layers/8/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
700
+ model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
701
+ model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
702
+ model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
703
+ model/model/language_model/layers/7/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
704
+ model/model/language_model/layers/8/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
705
+ model/model/language_model/layers/8/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
706
+ model/model/language_model/layers/9/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
707
+ model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
708
+ model/model/language_model/layers/8/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
709
+ model/model/language_model/layers/8/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
710
+ model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
711
+ model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
712
+ model/model/language_model/layers/8/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
713
+ model/model/language_model/layers/9/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
714
+ model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
715
+ model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
716
+ model/model/language_model/layers/8/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
717
+ model/model/language_model/layers/9/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
718
+ model/model/language_model/layers/8/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
719
+ model/model/language_model/layers/8/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
720
+ model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
721
+ model/model/language_model/layers/7/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
722
+ model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
723
+ model/model/language_model/layers/9/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
724
+ model/model/language_model/layers/9/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
725
+ model/model/language_model/layers/8/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
726
+ model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
727
+ model/model/language_model/layers/8/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
728
+ model/model/visual/blocks/0/attn/proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
729
+ model/model/visual/blocks/0/attn/proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
730
+ model/model/language_model/layers/8/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
731
+ model/model/language_model/layers/9/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
732
+ model/model/language_model/layers/9/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
733
+ model/model/language_model/layers/8/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
734
+ model/model/language_model/layers/9/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
735
+ model/model/language_model/layers/9/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
736
+ model/model/language_model/layers/11/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
737
+ model/model/language_model/layers/11/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
738
+ model/model/language_model/layers/11/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
739
+ model/model/language_model/layers/11/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
740
+ model/model/language_model/layers/11/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
741
+ model/model/language_model/layers/11/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
742
+ model/model/language_model/layers/11/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
743
+ model/model/language_model/layers/11/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
744
+ model/model/language_model/layers/11/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
745
+ model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
746
+ model/model/language_model/layers/11/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
747
+ model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
748
+ model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
749
+ model/model/language_model/layers/11/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
750
+ model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
751
+ model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
752
+ model/model/language_model/layers/12/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
753
+ model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
754
+ model/model/language_model/layers/12/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
755
+ model/model/language_model/layers/12/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
756
+ model/model/language_model/layers/12/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
757
+ model/model/language_model/layers/12/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
758
+ model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
759
+ model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
760
+ model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
761
+ model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
762
+ model/model/language_model/layers/12/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
763
+ model/model/language_model/layers/12/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
764
+ model/model/language_model/layers/12/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
765
+ model/model/language_model/layers/12/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
766
+ model/model/language_model/layers/12/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
767
+ model/model/language_model/layers/13/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
768
+ model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
769
+ model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
770
+ model/model/language_model/layers/12/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
771
+ model/model/language_model/layers/12/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
772
+ model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
773
+ model/model/language_model/layers/12/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
774
+ model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
775
+ model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
776
+ model/model/language_model/layers/13/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
777
+ model/model/language_model/layers/12/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
778
+ model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
779
+ model/model/language_model/layers/13/linear_attn/in_proj_z/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
780
+ model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
781
+ model/model/language_model/layers/13/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
782
+ model/model/language_model/layers/13/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
783
+ model/model/language_model/layers/13/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
784
+ model/model/language_model/layers/13/linear_attn/in_proj_qkv/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
785
+ model/model/language_model/layers/23/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
786
+ model/model/language_model/layers/22/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
787
+ model/model/language_model/layers/22/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
788
+ model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
789
+ model/model/language_model/embed_tokens/embedding/0.0 filter=lfs diff=lfs merge=lfs -text
790
+ model/model/language_model/layers/22/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
791
+ model/model/language_model/layers/22/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
792
+ model/model/language_model/layers/23/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
793
+ model/model/language_model/layers/22/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
794
+ model/model/language_model/layers/23/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
795
+ model/model/language_model/layers/23/self_attn/v_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
796
+ model/model/language_model/layers/23/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
797
+ model/model/language_model/layers/23/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
798
+ model/model/language_model/layers/22/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
799
+ model/model/language_model/layers/23/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
800
+ model/model/language_model/layers/22/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
801
+ model/model/language_model/layers/22/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
802
+ model/model/language_model/layers/22/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
803
+ model/model/language_model/layers/23/self_attn/o_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
804
+ model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
805
+ model/model/language_model/layers/22/linear_attn/out_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
806
+ model/model/language_model/layers/23/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
807
+ model/model/language_model/layers/3/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
808
+ model/model/language_model/layers/23/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
809
+ model/model/language_model/layers/23/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
810
+ model/model/language_model/layers/3/mlp/down_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
811
+ model/model/language_model/layers/3/self_attn/k_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
812
+ model/model/language_model/embed_tokens/embedding/2.0 filter=lfs diff=lfs merge=lfs -text
813
+ model/model/language_model/layers/23/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
814
+ model/model/language_model/layers/23/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
815
+ model/model/language_model/layers/23/self_attn/o_proj/kernel/0.2 filter=lfs diff=lfs merge=lfs -text
816
+ model/model/language_model/layers/3/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
817
+ model/model/language_model/layers/23/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
818
+ model/model/language_model/layers/3/mlp/up_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
819
+ model/model/language_model/layers/23/mlp/up_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
820
+ model/model/language_model/embed_tokens/embedding/1.0 filter=lfs diff=lfs merge=lfs -text
821
+ model/model/language_model/layers/23/mlp/down_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
822
+ model/model/language_model/layers/3/self_attn/k_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
823
+ model/model/language_model/layers/22/linear_attn/in_proj_qkv/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
824
+ model/model/language_model/layers/3/self_attn/k_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
825
+ model/model/language_model/layers/3/mlp/up_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
826
+ model/model/language_model/layers/3/self_attn/q_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
827
+ model/model/language_model/layers/23/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
828
+ model/model/language_model/layers/3/self_attn/v_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
829
+ model/model/language_model/layers/23/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
830
+ model/model/language_model/layers/23/self_attn/v_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
831
+ model/model/language_model/layers/3/mlp/down_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
832
+ model/model/language_model/layers/23/mlp/gate_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
833
+ model/model/language_model/layers/3/mlp/gate_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
834
+ model/model/language_model/layers/3/mlp/down_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
835
+ model/model/language_model/layers/3/self_attn/o_proj/kernel/0.1 filter=lfs diff=lfs merge=lfs -text
836
+ model/model/language_model/layers/3/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
837
+ model/model/language_model/layers/3/self_attn/q_proj/kernel/1.0 filter=lfs diff=lfs merge=lfs -text
838
+ model/model/language_model/layers/3/mlp/gate_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
839
+ model/model/language_model/layers/23/self_attn/q_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
840
+ model/model/language_model/layers/23/self_attn/o_proj/kernel/0.3 filter=lfs diff=lfs merge=lfs -text
841
+ model/model/language_model/layers/23/self_attn/v_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
842
+ model/model/language_model/layers/3/self_attn/q_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
843
+ model/model/language_model/layers/3/mlp/gate_proj/kernel/3.0 filter=lfs diff=lfs merge=lfs -text
844
+ model/model/language_model/layers/3/self_attn/k_proj/kernel/2.0 filter=lfs diff=lfs merge=lfs -text
845
+ model/model/language_model/layers/3/mlp/up_proj/kernel/0.0 filter=lfs diff=lfs merge=lfs -text
model/model/language_model/embed_tokens/embedding/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:072d34387fc3fbb1208da99dd018d1fe280c7791d000dfe71a98dc3a1bd1b845
3
+ size 99142870
model/model/language_model/embed_tokens/embedding/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b3ad8515dc378258ea535631d11abad7eb47f10e5a2f99345bab0152a878021c
3
+ size 99186872
model/model/language_model/embed_tokens/embedding/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d5f28c9326a62c9a94235bc3b9f41284ca825bd573e0728997a7e98afbd842f8
3
+ size 99226026
model/model/language_model/embed_tokens/embedding/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:029c17be082efc71db7a9238fca23787e7db22031ff17ad04d17266853ecf7f0
3
+ size 98810022
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5efd5b200a4cbe5fbf4c723896d23b8ab5c5686fe015c6852003f81811a6768e
3
+ size 2464012
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:30a2b7b0ba8b9539127969b80e902bea262b0174f5616c4b30d340cd67d2f67b
3
+ size 2461728
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6f0ade81791424a07fa85b7c3e87adfeeeae38330ad13715429a06c6b881b8ef
3
+ size 2459761
model/model/language_model/layers/0/linear_attn/in_proj_qkv/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:317cf74bd08bcfac029234b969163028d46b9387cf3c9f4d046c60dc11bcf82c
3
+ size 2459769
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f02a7ea377200bd3c5285c3b883da66039815b1fd6245a953f4c9d357d680b10
3
+ size 820844
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:751f9c21d643c5bfaf92446109023d6df38b32a97bf25bf52f029323d91953ed
3
+ size 820570
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:598eeddfaa9757d527f5cc8f15bf3ec982d95b1266d65ebc7d0ada7a2e8ae4ac
3
+ size 820244
model/model/language_model/layers/0/linear_attn/in_proj_z/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:904fd92edc1d647b2d0029eee40acd9274e5bc22d6b9cc8cafe3e48e6aa7558d
3
+ size 819865
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:68e09eff388e0b3cac66e2d60fce45653aba04f6d7637ac15ed33061e34afdea
3
+ size 821260
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2838bf5c99bdb6e853071d869806e0ec3f7ec36e83c687ad5de1d9e100948a2e
3
+ size 822354
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2d0a76fb432730a3d78d4ef6edb28ae14d0bffe511f179162a7bd1573b55382e
3
+ size 821794
model/model/language_model/layers/0/linear_attn/out_proj/kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ce828d749fa4ca3563abe8126919d89c58de9bf76a0ae061aaa826168c871a57
3
+ size 818798
model/model/language_model/layers/0/mlp/down_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f7537accaf09e51e3bf0b657c6d8c1a7dbf869f990132f094c048642ba1c236e
3
+ size 1438823
model/model/language_model/layers/0/mlp/down_proj/kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa66a0316360bd7a698b2e9ece53942e75999fd5182b98a58cce03c641fbd636
3
+ size 1438577
model/model/language_model/layers/0/mlp/down_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f1054b831eb5c7e123274d352eca23182fc6bf16f1d70fdabf983ac086eff04
3
+ size 1438326
model/model/language_model/layers/0/mlp/down_proj/kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:db515c1ef4f32bce078566d4475ce928e2d17fc7f76f669fec27373b30f1279d
3
+ size 1434758
model/model/language_model/layers/0/mlp/gate_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:17e79de915588ffc0e208847385deca354687d5c16f0a7685dd17d0b6b468670
3
+ size 1429897
model/model/language_model/layers/0/mlp/gate_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9fd2c6633d12ec915dc6fc61c9d4afc525ceb769c0ab62315abf1521b9736fd9
3
+ size 1429133
model/model/language_model/layers/0/mlp/gate_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3a0277cbc02bd31198067d25ff5c669a7aa91b519402fe6c90ed442f288b3056
3
+ size 1428836
model/model/language_model/layers/0/mlp/gate_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a7427085c60395db5a2b9465d09a8911f243afd07dd6591c2ffc55a8f4bdfffa
3
+ size 1427580
model/model/language_model/layers/0/mlp/up_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e913a8963677d93def1e477e1ce8a09bc50144420d870a61b32b798cf61a17cb
3
+ size 1437491
model/model/language_model/layers/0/mlp/up_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f28ed3204661ad2df363be964f3d832255c7b77ccd688aedd74ffa36a2fbb14a
3
+ size 1437005
model/model/language_model/layers/0/mlp/up_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:40a2924cbc4e923989fdc29527d3b3a67881468c652541bad50a3fe6ef03cea1
3
+ size 1436445
model/model/language_model/layers/0/mlp/up_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:a924d0ba08dde3c73ffbb36155ad256d7810835b8202189023701b6430e85278
3
+ size 1435173
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2ed50e9225a1b969b48ee9963e227952469692dc53cf3a7ee2d81d89add79716
3
+ size 2461231
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:993912c7d821204758a99842034b6c151065e31668bab750405156a5cc24ffc6
3
+ size 2456497
model/model/language_model/layers/1/linear_attn/in_proj_qkv/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0fe04cbf86c21c029119695fd4a1c7db5a28bb999c3c36da26e50ef21670e3ba
3
+ size 2455959
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:aa0ae7ab308542c10d964c2a0f5fca40c5750a7d3760b2a8570235af7f17e55e
3
+ size 822067
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1ec4c8a7a0b411f705341b8033d93b12dd1e432d8008187e5d7c879edb454515
3
+ size 822339
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:da111b0ff64a6c2a40cf3b139bef7d27a92ce7af5179fa77ef19d120ec89cb5a
3
+ size 822313
model/model/language_model/layers/1/linear_attn/in_proj_z/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:922903432bd3db6a09fd4a70dd0f1f6a7d624a2104517fd19ec760b7c4d06135
3
+ size 822159
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3f34542232beb00ac535da0a27d8cd18421ef0b14fa24720c8c5c9b2fbd9a3be
3
+ size 820298
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1b2bffd0abe6be380f6cba40179915c375350a5e01829315d8fd035c0b87787a
3
+ size 822414
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0ca3077c7df66b4fdd13f905962bb15726d651805a0f852e598b431684dfdfe9
3
+ size 821587
model/model/language_model/layers/1/linear_attn/out_proj/kernel/0.3 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:16a3a956bbe24a58dcf5e90e73ec85b187c252f69681734285a92e5ee9699676
3
+ size 817754
model/model/language_model/layers/1/mlp/down_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4add7d8eeb7143b72472ff890b81bb979d414f45988e30907f2d58327399eb87
3
+ size 1439797
model/model/language_model/layers/1/mlp/gate_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:cea7477ad1dc9e9ff7f55e0438b4f82006be91061f52523206895c2b5cd96d09
3
+ size 1428980
model/model/language_model/layers/11/mlp/down_proj/kernel/0.1 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:baaf043cd1d6cde7e17a847a6e1dace55cd6e2aac06afaf41b2aa908c838fb44
3
+ size 1446283
model/model/language_model/layers/11/mlp/down_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3955332f4a5ebc599127663e30232ac32bb34478c894b6668937e84e22374664
3
+ size 1446656
model/model/language_model/layers/11/self_attn/k_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:45c3fc7df87384e922dd8c05393629ec7398faa526d6bdacd6aed9a8a46c9139
3
+ size 205726
model/model/language_model/layers/11/self_attn/o_proj/kernel/0.2 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:139642658efea94b9dcaab5aea718d4dae44fb639273abf842315e769278736a
3
+ size 827707
model/model/language_model/layers/11/self_attn/q_proj/kernel/0.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f2d4f2c750172093578d7853fc07203e3babf2120ce5deba96e985bcb4cceb1d
3
+ size 1648505
model/model/language_model/layers/11/self_attn/q_proj/kernel/1.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:f099cbde5bde3abb3beb4f6994e9b51fdb7c4ab774e2443f833e1faaa863f04c
3
+ size 1645064
model/model/language_model/layers/11/self_attn/q_proj/kernel/2.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1386717396deb3aa072e033ea059ee46242a2fa3aaa86ac1b7cef6833f96512c
3
+ size 1642697
model/model/language_model/layers/11/self_attn/q_proj/kernel/3.0 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:678f194d793bfed43bd53fe0148055e4dc50eb2815f278f6c76723e78c89d45a
3
+ size 1638800