OpenTransformer commited on
Commit
b1e85b8
·
verified ·
1 Parent(s): 3ee08a1

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 +250 -0
  2. deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 +3 -0
  3. deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes +3 -0
  4. deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign +3 -0
  5. deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes +3 -0
  6. deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign +3 -0
  7. deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes +3 -0
  8. deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign +3 -0
  9. deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes +3 -0
  10. deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign +3 -0
  11. deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes +3 -0
  12. deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign +3 -0
  13. deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes +3 -0
  14. deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes +3 -0
  15. deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes +3 -0
  16. deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign +3 -0
  17. deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes +3 -0
  18. deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign +3 -0
  19. deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes +3 -0
  20. deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes +3 -0
  21. deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign +3 -0
  22. deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes +3 -0
  23. deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign +3 -0
  24. deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes +3 -0
  25. deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign +3 -0
  26. deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes +3 -0
  27. deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes +3 -0
  28. deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign +3 -0
  29. deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign +3 -0
  30. deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes +3 -0
  31. deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes +3 -0
  32. deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign +3 -0
  33. deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes +3 -0
  34. deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign +3 -0
  35. deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes +3 -0
  36. deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign +3 -0
  37. deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes +3 -0
  38. deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes +3 -0
  39. deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes +3 -0
  40. deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign +3 -0
  41. deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes +3 -0
  42. deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes +3 -0
  43. deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign +3 -0
  44. deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes +3 -0
  45. deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign +3 -0
  46. deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes +3 -0
  47. deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign +3 -0
  48. deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes +3 -0
  49. deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes +3 -0
  50. deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign +3 -0
.gitattributes CHANGED
@@ -387,3 +387,253 @@ deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.sign filter=lfs
387
  qwen3-4b-log-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
388
  deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
389
  deepseek-r1-1.5b-unary31/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
387
  qwen3-4b-log-unary/model_layers_27_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
388
  deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
389
  deepseek-r1-1.5b-unary31/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
390
+ deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
391
+ deepseek-r1-1.5b-unary31/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
392
+ deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
393
+ deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
394
+ deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
395
+ deepseek-r1-1.5b-unary31/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
396
+ deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
397
+ deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
398
+ deepseek-r1-1.5b-unary31/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
399
+ deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
400
+ deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
401
+ deepseek-r1-1.5b-unary31/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
402
+ deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
403
+ deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
404
+ deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
405
+ deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
406
+ deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 filter=lfs diff=lfs merge=lfs -text
407
+ deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
408
+ deepseek-r1-1.5b-unary31/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
409
+ deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
410
+ deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
411
+ deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
412
+ deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
413
+ deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
414
+ deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
415
+ deepseek-r1-1.5b-unary31/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
416
+ deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
417
+ deepseek-r1-1.5b-unary31/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
418
+ deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
419
+ deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
420
+ deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
421
+ deepseek-r1-1.5b-unary31/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
422
+ deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
423
+ deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
424
+ deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
425
+ deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
426
+ deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
427
+ deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
428
+ deepseek-r1-1.5b-unary31/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
429
+ deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
430
+ deepseek-r1-1.5b-unary31/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
431
+ deepseek-r1-1.5b-unary31/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
432
+ deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
433
+ deepseek-r1-1.5b-unary31/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
434
+ deepseek-r1-1.5b-unary31/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
435
+ deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
436
+ deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
437
+ deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
438
+ deepseek-r1-1.5b-unary31/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
439
+ deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
440
+ deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
441
+ deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
442
+ deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
443
+ deepseek-r1-1.5b-unary31/model_layers_7_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
444
+ deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
445
+ deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
446
+ deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
447
+ deepseek-r1-1.5b-unary31/model_layers_4_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
448
+ deepseek-r1-1.5b-unary31/model_layers_6_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
449
+ deepseek-r1-1.5b-unary31/model_layers_4_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
450
+ deepseek-r1-1.5b-unary31/model_layers_8_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
451
+ deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
452
+ deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
453
+ deepseek-r1-1.5b-unary31/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
454
+ deepseek-r1-1.5b-unary31/model_layers_9_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
455
+ deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
456
+ deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
457
+ deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
458
+ deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
459
+ deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
460
+ deepseek-r1-1.5b-unary31/model_layers_9_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
461
+ deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
462
+ deepseek-r1-1.5b-unary31/model_layers_6_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
463
+ deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
464
+ deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
465
+ deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
466
+ deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
467
+ deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
468
+ deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
469
+ deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
470
+ deepseek-r1-1.5b-unary31/model_layers_5_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
471
+ deepseek-r1-1.5b-unary31/model_layers_5_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
472
+ deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
473
+ deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
474
+ deepseek-r1-1.5b-unary31/model_layers_8_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
475
+ deepseek-r1-1.5b-unary31/model_layers_8_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
476
+ deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
477
+ deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
478
+ deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
479
+ deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
480
+ deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
481
+ deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
482
+ deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
483
+ deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
484
+ deepseek-r1-1.5b-unary31/model_layers_6_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
485
+ deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
486
+ deepseek-r1-1.5b-unary31/model_layers_9_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
487
+ deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
488
+ deepseek-r1-1.5b-unary31/model_layers_4_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
489
+ deepseek-r1-1.5b-unary31/model_layers_7_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
490
+ deepseek-r1-1.5b-unary31/model_layers_9_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
491
+ deepseek-r1-1.5b-unary31/model_layers_4_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
492
+ deepseek-r1-1.5b-unary31/model_layers_4_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
493
+ deepseek-r1-1.5b-unary31/model_layers_7_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
494
+ deepseek-r1-1.5b-unary31/model_layers_4_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
495
+ deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
496
+ deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
497
+ deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
498
+ deepseek-r1-1.5b-unary31/model_layers_6_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
499
+ deepseek-r1-1.5b-unary31/model_layers_5_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
500
+ deepseek-r1-1.5b-unary31/model_layers_5_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
501
+ deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
502
+ deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
503
+ deepseek-r1-1.5b-unary31/model_layers_8_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
504
+ deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
505
+ deepseek-r1-1.5b-unary31/model_layers_7_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
506
+ deepseek-r1-1.5b-unary31/model_layers_8_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
507
+ deepseek-r1-1.5b-unary4/model_layers_11_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
508
+ deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
509
+ deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
510
+ deepseek-r1-1.5b-unary4/model_layers_5_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
511
+ deepseek-r1-1.5b-unary4/model_layers_25_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
512
+ deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
513
+ deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
514
+ deepseek-r1-1.5b-unary4/model_layers_5_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
515
+ deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
516
+ deepseek-r1-1.5b-unary4/model_layers_17_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
517
+ deepseek-r1-1.5b-unary4/model_layers_18_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
518
+ deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
519
+ deepseek-r1-1.5b-unary4/model_layers_21_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
520
+ deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
521
+ deepseek-r1-1.5b-unary4/model_layers_6_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
522
+ deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
523
+ deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
524
+ deepseek-r1-1.5b-unary4/model_layers_4_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
525
+ deepseek-r1-1.5b-unary4/model_layers_0_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
526
+ deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
527
+ deepseek-r1-1.5b-unary4/model_layers_10_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
528
+ deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
529
+ deepseek-r1-1.5b-unary4/model_layers_24_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
530
+ deepseek-r1-1.5b-unary4/model_layers_14_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
531
+ deepseek-r1-1.5b-unary4/model_layers_22_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
532
+ deepseek-r1-1.5b-unary4/model_layers_20_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
533
+ deepseek-r1-1.5b-unary4/model_layers_4_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
534
+ deepseek-r1-1.5b-unary4/model_layers_6_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
535
+ deepseek-r1-1.5b-unary4/model_layers_3_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
536
+ deepseek-r1-1.5b-unary4/model_layers_11_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
537
+ deepseek-r1-1.5b-unary4/model_layers_7_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
538
+ deepseek-r1-1.5b-unary31/model_layers_5_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
539
+ deepseek-r1-1.5b-unary4/model_layers_8_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
540
+ deepseek-r1-1.5b-unary4/model_layers_16_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
541
+ deepseek-r1-1.5b-unary4/model_layers_7_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
542
+ deepseek-r1-1.5b-unary4/model_layers_7_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
543
+ deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
544
+ deepseek-r1-1.5b-unary4/model_layers_7_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
545
+ deepseek-r1-1.5b-unary4/model_layers_11_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
546
+ deepseek-r1-1.5b-unary4/model_layers_21_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
547
+ deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
548
+ deepseek-r1-1.5b-unary4/model_layers_19_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
549
+ deepseek-r1-1.5b-unary4/model_layers_19_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
550
+ deepseek-r1-1.5b-unary4/model_layers_17_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
551
+ deepseek-r1-1.5b-unary4/model_layers_18_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
552
+ deepseek-r1-1.5b-unary4/model_layers_4_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
553
+ deepseek-r1-1.5b-unary4/model_layers_9_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
554
+ deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
555
+ deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
556
+ deepseek-r1-1.5b-unary4/model_layers_8_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
557
+ deepseek-r1-1.5b-unary4/model_layers_21_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
558
+ deepseek-r1-1.5b-unary4/model_layers_13_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
559
+ deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
560
+ deepseek-r1-1.5b-unary4/model_layers_13_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
561
+ deepseek-r1-1.5b-unary4/model_layers_14_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
562
+ deepseek-r1-1.5b-unary4/model_layers_10_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
563
+ deepseek-r1-1.5b-unary4/model_layers_24_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
564
+ deepseek-r1-1.5b-unary4/model_layers_1_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
565
+ deepseek-r1-1.5b-unary4/model_layers_25_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
566
+ deepseek-r1-1.5b-unary4/model_layers_17_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
567
+ deepseek-r1-1.5b-unary4/model_layers_24_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
568
+ deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
569
+ deepseek-r1-1.5b-unary4/model_layers_9_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
570
+ deepseek-r1-1.5b-unary4/model_layers_12_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
571
+ deepseek-r1-1.5b-unary4/model_layers_3_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
572
+ deepseek-r1-1.5b-unary4/model_layers_23_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
573
+ deepseek-r1-1.5b-unary4/model_layers_26_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
574
+ deepseek-r1-1.5b-unary4/model_layers_23_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
575
+ deepseek-r1-1.5b-unary4/model_layers_12_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
576
+ deepseek-r1-1.5b-unary4/model_layers_14_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
577
+ deepseek-r1-1.5b-unary4/model_layers_23_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
578
+ deepseek-r1-1.5b-unary4/model_layers_13_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
579
+ deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
580
+ deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
581
+ deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
582
+ deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
583
+ deepseek-r1-1.5b-unary4/model_layers_1_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
584
+ deepseek-r1-1.5b-unary4/model_layers_6_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
585
+ deepseek-r1-1.5b-unary4/model_layers_23_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
586
+ deepseek-r1-1.5b-unary4/model_layers_9_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
587
+ deepseek-r1-1.5b-unary4/model_layers_23_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
588
+ deepseek-r1-1.5b-unary4/model_layers_23_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
589
+ deepseek-r1-1.5b-unary4/model_layers_2_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
590
+ deepseek-r1-1.5b-unary4/model_layers_21_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
591
+ deepseek-r1-1.5b-unary4/model_layers_8_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
592
+ deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
593
+ deepseek-r1-1.5b-unary4/model_layers_22_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
594
+ deepseek-r1-1.5b-unary4/model_layers_21_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
595
+ deepseek-r1-1.5b-unary4/model_layers_20_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
596
+ deepseek-r1-1.5b-unary4/model_layers_25_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
597
+ deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
598
+ deepseek-r1-1.5b-unary4/model_layers_19_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
599
+ deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
600
+ deepseek-r1-1.5b-unary4/model_layers_1_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
601
+ deepseek-r1-1.5b-unary4/model_layers_18_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
602
+ deepseek-r1-1.5b-unary4/model_layers_1_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
603
+ deepseek-r1-1.5b-unary4/model_layers_14_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
604
+ deepseek-r1-1.5b-unary4/model_layers_7_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
605
+ deepseek-r1-1.5b-unary4/model_layers_6_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
606
+ deepseek-r1-1.5b-unary4/model_layers_11_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
607
+ deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
608
+ deepseek-r1-1.5b-unary4/model_layers_26_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
609
+ deepseek-r1-1.5b-unary4/model_layers_0_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
610
+ deepseek-r1-1.5b-unary4/model_layers_9_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
611
+ deepseek-r1-1.5b-unary4/model_layers_5_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
612
+ deepseek-r1-1.5b-unary4/model_layers_16_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
613
+ deepseek-r1-1.5b-unary4/model_layers_10_mlp_up_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
614
+ deepseek-r1-1.5b-unary4/model_layers_19_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
615
+ deepseek-r1-1.5b-unary4/model_layers_10_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
616
+ deepseek-r1-1.5b-unary4/model_layers_26_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
617
+ deepseek-r1-1.5b-unary4/model_layers_18_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
618
+ deepseek-r1-1.5b-unary4/model_layers_12_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
619
+ deepseek-r1-1.5b-unary4/model_layers_7_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
620
+ deepseek-r1-1.5b-unary4/model_layers_8_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
621
+ deepseek-r1-1.5b-unary4/model_layers_6_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
622
+ deepseek-r1-1.5b-unary4/model_layers_0_mlp_down_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
623
+ deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
624
+ deepseek-r1-1.5b-unary4/model_layers_25_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
625
+ deepseek-r1-1.5b-unary4/model_layers_15_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
626
+ deepseek-r1-1.5b-unary4/model_layers_24_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
627
+ deepseek-r1-1.5b-unary4/model_layers_3_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
628
+ deepseek-r1-1.5b-unary4/model_layers_20_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
629
+ deepseek-r1-1.5b-unary4/model_layers_3_mlp_down_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
630
+ deepseek-r1-1.5b-unary4/model_layers_22_mlp_up_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
631
+ deepseek-r1-1.5b-unary4/model_layers_2_self_attn_o_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
632
+ deepseek-r1-1.5b-unary4/model_layers_9_self_attn_k_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
633
+ deepseek-r1-1.5b-unary4/model_layers_14_mlp_gate_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
634
+ deepseek-r1-1.5b-unary4/model_layers_16_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
635
+ deepseek-r1-1.5b-unary4/model_layers_3_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
636
+ deepseek-r1-1.5b-unary4/model_layers_22_self_attn_v_proj_weight.planes filter=lfs diff=lfs merge=lfs -text
637
+ deepseek-r1-1.5b-unary4/model_layers_26_mlp_gate_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
638
+ deepseek-r1-1.5b-unary4/model_layers_1_self_attn_q_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
639
+ deepseek-r1-1.5b-unary4/model_layers_22_self_attn_o_proj_weight.sign filter=lfs diff=lfs merge=lfs -text
deepseek-r1-1.5b-packed/model_embed_tokens_weight.fp16 ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e55610c68685326d482c594ff3bb16141e71a0d219fe729211562ab630953c6e
3
+ size 466747392
deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e4398ac44e6d827abd4f5fb1dc689354f9f29bedff598be1c639fa56dcd51b7e
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_0_mlp_down_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:b49338069c9db0f188c0b6e9b2a9bbb1c3ee94d02d186706f7d297872e2711a7
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4f0f2bcb11c6fe3733574382a611d2f52a56645d46d6442c2cd65f217adacd9c
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_0_mlp_gate_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2cf601ab6062858b266017e3ccc33f77bb1a6560510ddb28d0bddd9822adbd0b
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:8b6994e4d41a48ae9764063df8498511c756d2de9be45716628a746e679883a2
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_0_mlp_up_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:43b1f543227944a1af2750e991457b30cb7188988bc96d74d0a5dd89facf6877
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5e104c032c4c68245888a5ca8d0e472f195a8c5739111acb0bcf374d02b225db
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_0_self_attn_o_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:afa7c60db5e54d8009750dd241125670907a01f6b0741fecf14e3983914efbbe
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fa2f56946b5325dd1b5897fc27129a7301445ff2cd4ca4242299ff8bb72f8496
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_0_self_attn_q_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:556096531abd03fc5e5f04c6d35b923f99fa220b279f136aea4b8d2af372d579
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_0_self_attn_v_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c5e8ef8cffc0641ec01e4c91e292c3ce67d088ffef871aa98265002f8fcdefab
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_10_self_attn_k_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:93aaf4a9cbb3a8889e30662df570f4e51ed997c4714864898d6ea5fe3d6544ea
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3cf02c8c10afce88344a2b0aa0b4d6069547ec9bfceb51355481a53eb2143c2f
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_10_self_attn_o_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1c8d38e33a29916b3a384d78f3154474f9b47aa396ce1f0b4ab1c44518164ce8
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6a7bc333a497612fb08e62ac8f382109a337cab927e09fc41c1fed906b50bf74
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_10_self_attn_q_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4fe42ad280bffdb73f427b1fcb4601b4c336923d9c34223edcbd271ce82dd90b
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_10_self_attn_v_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1572f5b6dbd9936dae84bbd687c2db2b319601d94df7923d90b67ef60d235029
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:14a02754c82eed6f3e2a557f4e0560ed0b241998e36a924d38ab03ed508a7166
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_1_mlp_down_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:431585ec6292217d6b8d7f6c56e402c3a5067273ae6f01ff773f6b546c295222
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:c68703a984d2d090b1cb0b157ddbf6a35984227a5576feef746a5f90bcaf1f94
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_1_mlp_gate_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:18d4f22d7a9844c265b8737f51512a8b9c3e83f8b3df30a048d2d1312bd89579
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:49fdaf2a9b2a0b40052fa7df86f91d6cf6c4fa7171af371f089846c1604c2ef3
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_1_mlp_up_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:7a161d226b750496245767146f576d75554387c2831fabca60a236b62c0c1e68
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_1_self_attn_k_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1028d183765318456b812c0444bb9fc73279aff341b0801f3a187b98cb0bc696
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:55ab407c506a305f0d56787b3ebc6cf8bffe2a31ed0382393286587fce50cfcc
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_1_self_attn_o_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:264d743b356d1c334878111aa6d1c1fbd184503bb3bc5e09618c4659ef84c4d6
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_1_self_attn_q_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:0bcf90e3fe150f12fb44938fb4e6d4837e2b673b6f2942a018af7d3c0ade3bd5
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_1_self_attn_v_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:084e761aa4eb0aaef88198bcde4e18ba8d418eccd6f996c06bd43991fcbf2de0
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:03f920edb44554298432d0e677d40ad1b19aad7a0bffe57ff9d42e42728842be
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_2_mlp_down_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4910406d2aff7bd205f58fcf484f9abd4b7efb7bb2a5740d5afc071e55cd2711
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71595b0eae522ae9bd300dbdfc19d2c65f64ed108ac63af9c80a13cd5ecd2742
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_2_mlp_gate_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:6acd236a009c2c646537035d07ed56d1f1a7e4bfd8e9b83a2e6c6ecf7c531bc8
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:3ef8b19b483e5c701cd841f100b08c04d092cec714b25a37697b3957213f7aac
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_2_mlp_up_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2959ca73da13885c8bd2b97eba55955a11c54af86f4ded2216013ef7283830ac
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_2_self_attn_k_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:dfcd69396e9bd01d0fab4f50cae4334ea575368c7da2251e78a5e09baf4b4a7b
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_2_self_attn_o_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:48f2b14390e677da26d5109be28c56e2d54e3a7ef09cb127f4efaca6d937d000
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1cb36cc621fe9d22dde6257003f4843334fdd596bca99ae80a0c87753b04f1d2
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_2_self_attn_q_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:816d513cdeac8dc0605a5808e97cfc152dddd76d3c3ac8451508ba3b140cbf6b
3
+ size 294912
deepseek-r1-1.5b-unary31/model_layers_2_self_attn_v_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:78088541f39243b167a6fb3fa2eb1deb46f833b7e568ae4f16b28369d721936d
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9d1f2ec7621ea4c2bfb6195d51c4c9f8f2d0b150d04f494f97871b61f726b603
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_3_mlp_down_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:9ff2e7d5e2d1eb45e4d6d632bfdd4f4b541720f921e8198927099700e4a6f91b
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d0ffe57e12e4d95f84bab1eda718068006f9158132e70ab107f8381bfaf3ff2f
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_3_mlp_gate_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:71f770399800a7dd1df24cc413f67013848e44dd3c181d48d80aaa11dc45202a
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd5de36c17c78bbf66ea3a227130880be06ea939f4bfc6480e8f44df2793ce0e
3
+ size 53329920
deepseek-r1-1.5b-unary31/model_layers_3_mlp_up_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd3b8fb93a12a2e9411ec693f5e761da80b09734ca758f2ddd06cb83365677bb
3
+ size 1720320
deepseek-r1-1.5b-unary31/model_layers_3_self_attn_k_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:d7a83b95bfb5bc107e9025d1d4bcda0b5f631e0e5263999bf1272080c7d46446
3
+ size 1523712
deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.planes ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:99e9229c23a396d0ab2850f7487af78390d7eb76faee82fc06f2293cab5e6318
3
+ size 9142272
deepseek-r1-1.5b-unary31/model_layers_3_self_attn_o_proj_weight.sign ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f794bbcdffd07b8719ce97780dab4eabc04d310bbe111dfba7f8205fb80b684
3
+ size 294912