Hugging Face's logo

mjf-su
/
AutonomousVehiclePlanner

Safetensors
Model card Files
xet
 Community
mjf-su commited on
Commit
9229a22
·
verified ·
1 Parent(s): 68416b9

Upload folder using huggingface_hub

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 +202 -0
  2. ADEn-CFJ-KL0/README.md +68 -0
  3. ADEn-CFJ-KL0/added_tokens.json +28 -0
  4. ADEn-CFJ-KL0/chat_template.jinja +110 -0
  5. ADEn-CFJ-KL0/checkpoint-100/added_tokens.json +28 -0
  6. ADEn-CFJ-KL0/checkpoint-100/chat_template.jinja +110 -0
  7. ADEn-CFJ-KL0/checkpoint-100/config.json +68 -0
  8. ADEn-CFJ-KL0/checkpoint-100/generation_config.json +12 -0
  9. ADEn-CFJ-KL0/checkpoint-100/merges.txt +0 -0
  10. ADEn-CFJ-KL0/checkpoint-100/model-00001-of-00002.safetensors +3 -0
  11. ADEn-CFJ-KL0/checkpoint-100/model-00002-of-00002.safetensors +3 -0
  12. ADEn-CFJ-KL0/checkpoint-100/model.safetensors.index.json +721 -0
  13. ADEn-CFJ-KL0/checkpoint-100/optimizer.pt +3 -0
  14. ADEn-CFJ-KL0/checkpoint-100/rng_state_0.pth +3 -0
  15. ADEn-CFJ-KL0/checkpoint-100/rng_state_1.pth +3 -0
  16. ADEn-CFJ-KL0/checkpoint-100/scheduler.pt +3 -0
  17. ADEn-CFJ-KL0/checkpoint-100/special_tokens_map.json +31 -0
  18. ADEn-CFJ-KL0/checkpoint-100/tokenizer.json +3 -0
  19. ADEn-CFJ-KL0/checkpoint-100/tokenizer_config.json +244 -0
  20. ADEn-CFJ-KL0/checkpoint-100/trainer_state.json +353 -0
  21. ADEn-CFJ-KL0/checkpoint-100/training_args.bin +3 -0
  22. ADEn-CFJ-KL0/checkpoint-100/vocab.json +0 -0
  23. ADEn-CFJ-KL0/checkpoint-200/added_tokens.json +28 -0
  24. ADEn-CFJ-KL0/checkpoint-200/chat_template.jinja +110 -0
  25. ADEn-CFJ-KL0/checkpoint-200/config.json +68 -0
  26. ADEn-CFJ-KL0/checkpoint-200/generation_config.json +12 -0
  27. ADEn-CFJ-KL0/checkpoint-200/merges.txt +0 -0
  28. ADEn-CFJ-KL0/checkpoint-200/model-00001-of-00002.safetensors +3 -0
  29. ADEn-CFJ-KL0/checkpoint-200/model-00002-of-00002.safetensors +3 -0
  30. ADEn-CFJ-KL0/checkpoint-200/model.safetensors.index.json +721 -0
  31. ADEn-CFJ-KL0/checkpoint-200/optimizer.pt +3 -0
  32. ADEn-CFJ-KL0/checkpoint-200/rng_state_0.pth +3 -0
  33. ADEn-CFJ-KL0/checkpoint-200/rng_state_1.pth +3 -0
  34. ADEn-CFJ-KL0/checkpoint-200/scheduler.pt +3 -0
  35. ADEn-CFJ-KL0/checkpoint-200/special_tokens_map.json +31 -0
  36. ADEn-CFJ-KL0/checkpoint-200/tokenizer.json +3 -0
  37. ADEn-CFJ-KL0/checkpoint-200/tokenizer_config.json +244 -0
  38. ADEn-CFJ-KL0/checkpoint-200/trainer_state.json +672 -0
  39. ADEn-CFJ-KL0/checkpoint-200/training_args.bin +3 -0
  40. ADEn-CFJ-KL0/checkpoint-200/vocab.json +0 -0
  41. ADEn-CFJ-KL0/checkpoint-292/added_tokens.json +28 -0
  42. ADEn-CFJ-KL0/checkpoint-292/chat_template.jinja +110 -0
  43. ADEn-CFJ-KL0/checkpoint-292/config.json +68 -0
  44. ADEn-CFJ-KL0/checkpoint-292/generation_config.json +12 -0
  45. ADEn-CFJ-KL0/checkpoint-292/merges.txt +0 -0
  46. ADEn-CFJ-KL0/checkpoint-292/model-00001-of-00002.safetensors +3 -0
  47. ADEn-CFJ-KL0/checkpoint-292/model-00002-of-00002.safetensors +3 -0
  48. ADEn-CFJ-KL0/checkpoint-292/model.safetensors.index.json +721 -0
  49. ADEn-CFJ-KL0/checkpoint-292/optimizer.pt +3 -0
  50. ADEn-CFJ-KL0/checkpoint-292/rng_state_0.pth +3 -0
.gitattributes CHANGED
@@ -445,3 +445,205 @@ ADEn-RC-KL0/eval_image_cache/chunk_3084__76712ddc-0849-4345-89ce-2354c1e26612__1
445
  ADEn-RC-KL0/eval_image_cache/chunk_3084__9f5ff8ae-5e43-4116-94e1-202906ee17bd__8001827.png filter=lfs diff=lfs merge=lfs -text
446
  ADEn-RC-KL0/eval_image_cache/chunk_3087__c44bb8ad-a913-494d-88a1-987b6e8bfdf3__8000142.png filter=lfs diff=lfs merge=lfs -text
447
  ADEn-RC-KL0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
445
  ADEn-RC-KL0/eval_image_cache/chunk_3084__9f5ff8ae-5e43-4116-94e1-202906ee17bd__8001827.png filter=lfs diff=lfs merge=lfs -text
446
  ADEn-RC-KL0/eval_image_cache/chunk_3087__c44bb8ad-a913-494d-88a1-987b6e8bfdf3__8000142.png filter=lfs diff=lfs merge=lfs -text
447
  ADEn-RC-KL0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
448
+ ADEn-CFJ-KL0/checkpoint-100/tokenizer.json filter=lfs diff=lfs merge=lfs -text
449
+ ADEn-CFJ-KL0/checkpoint-200/tokenizer.json filter=lfs diff=lfs merge=lfs -text
450
+ ADEn-CFJ-KL0/checkpoint-292/tokenizer.json filter=lfs diff=lfs merge=lfs -text
451
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0108__07f9f468-02ac-4ec6-b83b-1755edc5cdce__1999996.png filter=lfs diff=lfs merge=lfs -text
452
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0109__bbb36725-1b40-419e-9432-699b5bd0d6dc__10000051.png filter=lfs diff=lfs merge=lfs -text
453
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0110__1a95715d-4ce6-47af-a95b-75fec0b326ee__6999997.png filter=lfs diff=lfs merge=lfs -text
454
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0111__3935487c-e145-43a3-b54d-a220130db33d__3999988.png filter=lfs diff=lfs merge=lfs -text
455
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0111__3935487c-e145-43a3-b54d-a220130db33d__5000041.png filter=lfs diff=lfs merge=lfs -text
456
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0111__3935487c-e145-43a3-b54d-a220130db33d__7999972.png filter=lfs diff=lfs merge=lfs -text
457
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0112__3e75f81b-748f-4ee5-aa74-3bc331df175b__2999908.png filter=lfs diff=lfs merge=lfs -text
458
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0114__30a70a85-3cdf-4c02-ac15-0c92d1224b82__12000124.png filter=lfs diff=lfs merge=lfs -text
459
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0114__30a70a85-3cdf-4c02-ac15-0c92d1224b82__2000001.png filter=lfs diff=lfs merge=lfs -text
460
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0114__b7cf7e0e-dba6-4551-9a13-596297df1bba__8000088.png filter=lfs diff=lfs merge=lfs -text
461
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0117__e785f4d9-8121-4ccb-a171-fb9c7277a316__9999629.png filter=lfs diff=lfs merge=lfs -text
462
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0118__0c1a7bec-2ff6-4e5a-bf0e-2d766231ca5d__12000067.png filter=lfs diff=lfs merge=lfs -text
463
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0118__1f23fc05-0eca-436d-b04e-fc6af9e10952__7999502.png filter=lfs diff=lfs merge=lfs -text
464
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0120__2ad625e0-db47-4837-ac85-5c7868750021__12000141.png filter=lfs diff=lfs merge=lfs -text
465
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0120__2ad625e0-db47-4837-ac85-5c7868750021__14000130.png filter=lfs diff=lfs merge=lfs -text
466
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0120__2ad625e0-db47-4837-ac85-5c7868750021__9000080.png filter=lfs diff=lfs merge=lfs -text
467
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0124__144495bb-8e60-4491-a587-869656f71b47__8999977.png filter=lfs diff=lfs merge=lfs -text
468
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0126__2cd6a7c7-646d-4104-91f7-fd4ae19a4d51__3999994.png filter=lfs diff=lfs merge=lfs -text
469
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0128__027a4871-e99c-4aae-be61-bce56cff84e6__7999983.png filter=lfs diff=lfs merge=lfs -text
470
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0129__514963ec-4e0b-43c8-b620-a7187a63c997__3000003.png filter=lfs diff=lfs merge=lfs -text
471
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0129__6c41ed3d-def2-4db3-95f2-325b80e97d41__5999994.png filter=lfs diff=lfs merge=lfs -text
472
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0129__a6af5b85-cd62-4062-89e1-c5fd114bbbff__3999992.png filter=lfs diff=lfs merge=lfs -text
473
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0129__a6af5b85-cd62-4062-89e1-c5fd114bbbff__5999990.png filter=lfs diff=lfs merge=lfs -text
474
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0131__11271cef-d09e-4e46-8356-b546e35f1d22__3999966.png filter=lfs diff=lfs merge=lfs -text
475
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0134__6759cd27-efbe-4835-a5f4-c0d8adf02243__11999986.png filter=lfs diff=lfs merge=lfs -text
476
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0134__b03cdc34-a47b-414e-872a-bab168d55ba0__7999996.png filter=lfs diff=lfs merge=lfs -text
477
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0134__b16f483e-ee72-4608-abf2-5c8239b8c46d__6000016.png filter=lfs diff=lfs merge=lfs -text
478
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0135__82a0e604-bb05-41fb-8ad6-f24b3488494a__10000007.png filter=lfs diff=lfs merge=lfs -text
479
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0255__384ae427-068b-4608-8ad2-274b19e21c50__10000162.png filter=lfs diff=lfs merge=lfs -text
480
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0255__d964da47-9126-4a0d-81b5-447ff3d2f5ea__12000023.png filter=lfs diff=lfs merge=lfs -text
481
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0256__b5fb222f-994d-46ca-ba64-d58ab0d9e552__5000038.png filter=lfs diff=lfs merge=lfs -text
482
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0257__64672e20-c5cd-450f-af63-02e099a37ea0__8000105.png filter=lfs diff=lfs merge=lfs -text
483
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0257__91b8ec37-00f9-4cfe-84b2-393e5ff8761f__11000090.png filter=lfs diff=lfs merge=lfs -text
484
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0257__b019775a-94e7-485a-95d7-0aa1c631273a__13000080.png filter=lfs diff=lfs merge=lfs -text
485
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0257__d346d1f8-a675-4323-865d-90f0a376d47d__1999924.png filter=lfs diff=lfs merge=lfs -text
486
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0258__174f5269-71ad-4ff5-8c52-93fcd22bca08__12000160.png filter=lfs diff=lfs merge=lfs -text
487
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0260__31db2104-7783-46c1-b2d0-76c841af9b65__11999976.png filter=lfs diff=lfs merge=lfs -text
488
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0260__79262cc6-06dc-4f0f-a80a-7b85ba5d15ed__7000002.png filter=lfs diff=lfs merge=lfs -text
489
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0261__fe440ea7-4a09-4467-9994-2430d735f5a9__8999977.png filter=lfs diff=lfs merge=lfs -text
490
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0263__7a6fbf54-d533-428c-a182-557fef36cdcf__9999999.png filter=lfs diff=lfs merge=lfs -text
491
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0265__af94a1d4-4786-4013-84d2-ae4900b6fe31__10999970.png filter=lfs diff=lfs merge=lfs -text
492
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0347__174422ad-96a8-4808-9109-666a916d7db4__13000031.png filter=lfs diff=lfs merge=lfs -text
493
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0347__1db9bc8f-6771-4c39-b4bd-6e752c376ce0__4999994.png filter=lfs diff=lfs merge=lfs -text
494
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0347__6b7eb06a-3111-41ea-a93f-16b4b8aa38ff__6000009.png filter=lfs diff=lfs merge=lfs -text
495
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0351__089aac8c-d8a8-4f17-bc5d-2ce4771a62b4__12999959.png filter=lfs diff=lfs merge=lfs -text
496
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0352__80e59d8e-6543-4c24-bc11-34e50ef8dd5b__7999992.png filter=lfs diff=lfs merge=lfs -text
497
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0586__a7763237-2ae2-4e9c-96b2-6664243c76ff__10000122.png filter=lfs diff=lfs merge=lfs -text
498
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0587__51e2316b-30b9-4623-a177-2cd3b7999b6d__7999973.png filter=lfs diff=lfs merge=lfs -text
499
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0588__472e7533-ffa0-4828-bb98-b9e679e4ff4f__11000101.png filter=lfs diff=lfs merge=lfs -text
500
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0591__bcde195a-d402-4d71-90aa-84000183d3b4__5999999.png filter=lfs diff=lfs merge=lfs -text
501
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0591__c2184364-65bc-47a3-9f39-c4586a1776d7__8999995.png filter=lfs diff=lfs merge=lfs -text
502
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0592__f367b3f6-df4c-4084-b748-56dc21638a3f__11999996.png filter=lfs diff=lfs merge=lfs -text
503
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0592__f367b3f6-df4c-4084-b748-56dc21638a3f__4999994.png filter=lfs diff=lfs merge=lfs -text
504
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0593__a8425540-13aa-487c-8a4d-43df90e434f0__5999995.png filter=lfs diff=lfs merge=lfs -text
505
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0595__485567af-f9fd-4ebd-aae8-67d9d684db49__3999957.png filter=lfs diff=lfs merge=lfs -text
506
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0595__58828c5e-6104-4386-8aa2-3536c32894dc__6000002.png filter=lfs diff=lfs merge=lfs -text
507
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0596__2b7fa081-c8ec-4083-80e9-4afb629ac707__1999991.png filter=lfs diff=lfs merge=lfs -text
508
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0597__095856fb-112d-4d1c-bb53-5250a0f5cb76__11000014.png filter=lfs diff=lfs merge=lfs -text
509
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0597__ee260900-1c26-4841-821e-435aeac9cfd3__8999979.png filter=lfs diff=lfs merge=lfs -text
510
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0600__c0dfaa0c-58fb-4f6e-a806-3cced7170abc__8999956.png filter=lfs diff=lfs merge=lfs -text
511
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0601__64d0502c-8a63-4e20-93e7-90cd5aa700d8__8000021.png filter=lfs diff=lfs merge=lfs -text
512
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0601__b4754eda-96b8-4680-b980-c4dcaba7b43e__12000083.png filter=lfs diff=lfs merge=lfs -text
513
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0602__5008d1f9-2f19-429c-8fc8-6c8652312504__8999996.png filter=lfs diff=lfs merge=lfs -text
514
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0604__69fc21e8-6faf-487b-806f-1d24654805ce__4999984.png filter=lfs diff=lfs merge=lfs -text
515
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0604__c97f7dda-b4d5-4db3-887b-03c489fd2650__8999995.png filter=lfs diff=lfs merge=lfs -text
516
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0606__e3bf1780-f4eb-4f7f-99a6-e60f470ba734__2000007.png filter=lfs diff=lfs merge=lfs -text
517
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0606__e3bf1780-f4eb-4f7f-99a6-e60f470ba734__9000140.png filter=lfs diff=lfs merge=lfs -text
518
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0608__45731110-2cf7-46f3-bfc8-ca5f19c93537__6999993.png filter=lfs diff=lfs merge=lfs -text
519
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0608__82371c52-7bd3-490d-93c4-f92974349435__9000012.png filter=lfs diff=lfs merge=lfs -text
520
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0609__917f7182-f87f-428b-90ea-7c02153a2aa5__11000012.png filter=lfs diff=lfs merge=lfs -text
521
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0618__99c62f9c-fbd5-4a06-ab6c-ad966e18d6c5__13999985.png filter=lfs diff=lfs merge=lfs -text
522
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0618__b8516847-a9d3-45d6-81af-ac66942d9852__8999980.png filter=lfs diff=lfs merge=lfs -text
523
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0618__fb343576-5115-472e-9f6b-37444e63b893__2000002.png filter=lfs diff=lfs merge=lfs -text
524
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0621__459f0a6b-316e-4431-aefb-94277bb77a66__5000068.png filter=lfs diff=lfs merge=lfs -text
525
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0621__8729f8f9-2f76-472f-99b1-ca9cffb37bb7__11999994.png filter=lfs diff=lfs merge=lfs -text
526
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0622__178e7df8-9f8b-49a6-9cb4-35c26ebf0d78__2999989.png filter=lfs diff=lfs merge=lfs -text
527
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0623__b2604a77-65f2-4dd4-b753-8062da42a174__12000129.png filter=lfs diff=lfs merge=lfs -text
528
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0623__b2604a77-65f2-4dd4-b753-8062da42a174__8000113.png filter=lfs diff=lfs merge=lfs -text
529
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0623__eddf79af-0642-45e7-838e-0235b1789628__7999973.png filter=lfs diff=lfs merge=lfs -text
530
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0624__f8dfa81e-7c03-43a5-8380-291d8236958a__8999997.png filter=lfs diff=lfs merge=lfs -text
531
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0625__03e18e8c-c261-4d2e-88a8-c04d94f53d0e__4000038.png filter=lfs diff=lfs merge=lfs -text
532
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0625__03e18e8c-c261-4d2e-88a8-c04d94f53d0e__9000015.png filter=lfs diff=lfs merge=lfs -text
533
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0627__184c1a92-7b7f-43b0-bca5-2282a7b757f6__12000012.png filter=lfs diff=lfs merge=lfs -text
534
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0630__366299fa-20ac-4833-bce3-b8bc4e4d582f__2999985.png filter=lfs diff=lfs merge=lfs -text
535
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0630__ac7fdf05-cfdb-4a6f-af3c-309ccef3b4f5__10999967.png filter=lfs diff=lfs merge=lfs -text
536
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0630__d2a93ea6-012c-4b4e-a6f6-0ec5b419d28a__2999978.png filter=lfs diff=lfs merge=lfs -text
537
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0632__438c37a2-6b39-400d-97de-06b5d5ae2995__6000003.png filter=lfs diff=lfs merge=lfs -text
538
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0633__dfbbf996-f5d2-40e2-89f6-86566020d958__3999999.png filter=lfs diff=lfs merge=lfs -text
539
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0635__9ee5b39a-a131-4160-9bf4-6439968d43a9__7000011.png filter=lfs diff=lfs merge=lfs -text
540
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0635__e3153da1-65be-4eba-aa0a-ed28eb39493d__2000039.png filter=lfs diff=lfs merge=lfs -text
541
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0637__98a1a789-378d-4cd1-964c-10e862268bd4__12000009.png filter=lfs diff=lfs merge=lfs -text
542
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0638__25df96c1-62d4-46c6-b161-2ccef138945f__13999990.png filter=lfs diff=lfs merge=lfs -text
543
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0640__0c210498-a149-4f4b-b372-e27227d2d5a1__7999994.png filter=lfs diff=lfs merge=lfs -text
544
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0640__3725a28e-aefd-4efc-8507-8a23707e0aa7__13000039.png filter=lfs diff=lfs merge=lfs -text
545
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0642__42c04a80-f888-4ae3-8dab-2e144a5ae305__13000023.png filter=lfs diff=lfs merge=lfs -text
546
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0642__afe297e4-e866-46e9-804b-1bf3c41a2ff0__12999985.png filter=lfs diff=lfs merge=lfs -text
547
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0642__be26ec39-4f58-478c-80a8-b9a709f80881__13000024.png filter=lfs diff=lfs merge=lfs -text
548
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0643__cd62fa76-6efe-49d8-99a0-379e2782a6ad__2000016.png filter=lfs diff=lfs merge=lfs -text
549
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0643__d25f9074-ee0b-4424-a4f5-dff6d6fc8890__7000001.png filter=lfs diff=lfs merge=lfs -text
550
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0644__686912e3-8629-4589-a1ae-729d4714eea3__9999986.png filter=lfs diff=lfs merge=lfs -text
551
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0648__0341e45a-e60a-4831-9976-23e113c0839c__9999972.png filter=lfs diff=lfs merge=lfs -text
552
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0648__cfe53f5b-f0f1-4c70-b0d3-b722473f1d72__3000011.png filter=lfs diff=lfs merge=lfs -text
553
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0649__73761faa-8f5e-4f41-b1f1-978b35429983__12000014.png filter=lfs diff=lfs merge=lfs -text
554
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0652__2ef367e1-448e-45d1-8958-f94a7f3765dc__6000000.png filter=lfs diff=lfs merge=lfs -text
555
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0652__c7a18f3e-e919-4c3c-99d2-adf63e396339__2999994.png filter=lfs diff=lfs merge=lfs -text
556
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0652__d2909b0b-dac0-48dd-9cd1-4976b41a0ffd__10000029.png filter=lfs diff=lfs merge=lfs -text
557
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0653__16a0ea82-dcea-4802-9f36-d335e4d47a93__10999994.png filter=lfs diff=lfs merge=lfs -text
558
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0654__184727ec-0fc0-44df-8ba6-c821f2651363__13999997.png filter=lfs diff=lfs merge=lfs -text
559
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0654__184727ec-0fc0-44df-8ba6-c821f2651363__4000010.png filter=lfs diff=lfs merge=lfs -text
560
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0655__bd31d697-1c77-41ab-b740-dc6d46b55139__8999992.png filter=lfs diff=lfs merge=lfs -text
561
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0655__d7e22e4f-9937-47cf-a3e2-cba399f9e436__5000021.png filter=lfs diff=lfs merge=lfs -text
562
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0656__e62ae5fa-fcc2-4e43-bf74-81f6efe95fea__9000015.png filter=lfs diff=lfs merge=lfs -text
563
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0657__2136a539-0e22-4382-8406-b9c646344aea__10999999.png filter=lfs diff=lfs merge=lfs -text
564
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0657__4de6cb20-de4e-4006-8a75-e29153ac5abf__4999959.png filter=lfs diff=lfs merge=lfs -text
565
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0661__7602813e-ff78-422b-b999-099cf222835c__9000026.png filter=lfs diff=lfs merge=lfs -text
566
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0664__c0f0a4d4-98a7-411a-8697-765f3bf8a572__5000006.png filter=lfs diff=lfs merge=lfs -text
567
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0664__e570c983-50f7-4544-85da-52b5176592b8__9000009.png filter=lfs diff=lfs merge=lfs -text
568
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0666__10eddfef-8346-48cd-8f59-cab3df04f950__13999779.png filter=lfs diff=lfs merge=lfs -text
569
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0666__4596da55-0671-46d4-b843-2c8299fd87aa__4000016.png filter=lfs diff=lfs merge=lfs -text
570
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0668__38c69311-d520-41e3-befe-98ef3932f6ef__6999988.png filter=lfs diff=lfs merge=lfs -text
571
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0668__38c69311-d520-41e3-befe-98ef3932f6ef__8999991.png filter=lfs diff=lfs merge=lfs -text
572
+ ADEn-CFJ-KL0/eval_image_cache/chunk_0671__a09199fa-a1d4-4eb0-a950-4ab55b4196a6__3999998.png filter=lfs diff=lfs merge=lfs -text
573
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1057__43ad0fe8-9f11-4c34-bb2f-607fc5452c0a__7000007.png filter=lfs diff=lfs merge=lfs -text
574
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1057__c99feaf4-1f8c-4fd7-b89e-06d63a935996__13000005.png filter=lfs diff=lfs merge=lfs -text
575
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1059__06a68a48-2bfb-4673-a9d3-039fd62ff13d__2999986.png filter=lfs diff=lfs merge=lfs -text
576
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1059__cb060b90-369f-40ce-85da-11f94dcb0b59__3999992.png filter=lfs diff=lfs merge=lfs -text
577
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1059__f53afcd9-5f33-4b98-a40a-7e14ba667969__10999988.png filter=lfs diff=lfs merge=lfs -text
578
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1063__7fc0c615-6e87-4efc-8000-98a59904c2c7__10999983.png filter=lfs diff=lfs merge=lfs -text
579
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1064__00f79de8-de3f-4153-bc0d-490e0d8633a9__9999979.png filter=lfs diff=lfs merge=lfs -text
580
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1064__952a3c9b-54e8-427a-87b8-486d8b76e4bd__10999984.png filter=lfs diff=lfs merge=lfs -text
581
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1066__1af5e4de-606c-4759-b516-f383f1962f48__6000012.png filter=lfs diff=lfs merge=lfs -text
582
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1066__76a36af4-0486-4ca5-b4a6-4dca980f627b__7999987.png filter=lfs diff=lfs merge=lfs -text
583
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1066__9ece6473-5520-4b5f-9a15-13ac9576e005__7999945.png filter=lfs diff=lfs merge=lfs -text
584
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1066__e3efea50-1cda-45ce-a23a-1fd7e21b96f7__13999996.png filter=lfs diff=lfs merge=lfs -text
585
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1067__2e72746e-12f3-4d1c-acae-0fa677567b48__8999988.png filter=lfs diff=lfs merge=lfs -text
586
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1067__e6838c21-2c66-4569-97eb-374be6418db2__4999981.png filter=lfs diff=lfs merge=lfs -text
587
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1070__38fd4fd1-16d0-445d-bb26-850f3c395ae0__11000005.png filter=lfs diff=lfs merge=lfs -text
588
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1070__38fd4fd1-16d0-445d-bb26-850f3c395ae0__7999992.png filter=lfs diff=lfs merge=lfs -text
589
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1070__6ad73485-5c49-4b7d-8d77-f5da88d21b9c__6999990.png filter=lfs diff=lfs merge=lfs -text
590
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1071__79a7d106-aaec-4b13-ae27-62db2abf274f__7999989.png filter=lfs diff=lfs merge=lfs -text
591
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1071__f96e2317-e91f-4d02-8c56-e4d53d67dc8e__6999988.png filter=lfs diff=lfs merge=lfs -text
592
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1073__63f4b7d2-ac47-4c8a-8e63-bcfaa4fb0c0e__9999978.png filter=lfs diff=lfs merge=lfs -text
593
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1076__423b597a-90cf-4c16-984f-7c245aceed8e__2999998.png filter=lfs diff=lfs merge=lfs -text
594
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1079__fce10c54-03a8-4b3f-964d-52060bd354ee__5999999.png filter=lfs diff=lfs merge=lfs -text
595
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1080__e7f947ae-8c90-49a5-a5e3-04e32476a3ea__5999971.png filter=lfs diff=lfs merge=lfs -text
596
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1081__c0e4f144-eef3-4be4-855d-672062369aa9__7000013.png filter=lfs diff=lfs merge=lfs -text
597
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1082__f9eb98a0-5d14-44f1-ac97-f585ac2a39b3__13000028.png filter=lfs diff=lfs merge=lfs -text
598
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1085__7ca38136-485f-44e9-804f-5f3936350402__9999988.png filter=lfs diff=lfs merge=lfs -text
599
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1085__dd6c9afd-7fdb-4499-b724-122cbf402eb8__10999985.png filter=lfs diff=lfs merge=lfs -text
600
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1086__4e8cbffd-f20d-43ee-af9e-14abb0c172ad__10000000.png filter=lfs diff=lfs merge=lfs -text
601
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1087__8268bbad-94e1-4dd7-ad8b-f0023c4ad558__9999991.png filter=lfs diff=lfs merge=lfs -text
602
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1089__d78d5e65-f00e-4dc4-8365-8ce810ac06dc__6999973.png filter=lfs diff=lfs merge=lfs -text
603
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1091__166b1e4e-1c73-4835-b0be-c7781a103c86__11000003.png filter=lfs diff=lfs merge=lfs -text
604
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1091__ccb5acd0-778a-4fc5-92ce-3ea86e31caf1__13999987.png filter=lfs diff=lfs merge=lfs -text
605
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1091__fd994f87-3c39-4ff4-a1f8-0f1e5f4c6575__2000018.png filter=lfs diff=lfs merge=lfs -text
606
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1092__265e9592-5b24-4f96-9b6f-38ce95a75d1d__12999968.png filter=lfs diff=lfs merge=lfs -text
607
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1092__265e9592-5b24-4f96-9b6f-38ce95a75d1d__3999990.png filter=lfs diff=lfs merge=lfs -text
608
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1094__49225bce-c30c-48b3-82a9-82b50b682997__8999994.png filter=lfs diff=lfs merge=lfs -text
609
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1094__bb9354fd-394d-45a4-b980-00a3b2bf12d1__7999777.png filter=lfs diff=lfs merge=lfs -text
610
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1095__130ffa81-5524-4ea6-a434-50a1e100c7b4__12999963.png filter=lfs diff=lfs merge=lfs -text
611
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1095__130ffa81-5524-4ea6-a434-50a1e100c7b4__9999976.png filter=lfs diff=lfs merge=lfs -text
612
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1098__d38a8e3a-175e-4042-a609-467459cb0a76__11000013.png filter=lfs diff=lfs merge=lfs -text
613
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1102__a8eb19ea-88eb-43a3-a916-4d500dc205e7__13000013.png filter=lfs diff=lfs merge=lfs -text
614
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1103__583582a6-c323-4bfb-b461-53f175805dc3__13999981.png filter=lfs diff=lfs merge=lfs -text
615
+ ADEn-CFJ-KL0/eval_image_cache/chunk_1103__f3dd9de0-ddfe-4052-9fc5-862f549ee9ab__14000347.png filter=lfs diff=lfs merge=lfs -text
616
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2771__59f384c5-8a39-47ca-a922-13a1f348ea4c__12000038.png filter=lfs diff=lfs merge=lfs -text
617
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2772__7b468eaf-05aa-4a34-820f-74a82e94d24a__12999975.png filter=lfs diff=lfs merge=lfs -text
618
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2773__7de88e93-719b-4afd-a647-6477bb12932d__8999987.png filter=lfs diff=lfs merge=lfs -text
619
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2774__4c4403a0-bca1-4dbb-8862-9feb046f9cb8__3000011.png filter=lfs diff=lfs merge=lfs -text
620
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2776__35582a89-49cf-4ed7-8c7f-518f58eda4c9__13000006.png filter=lfs diff=lfs merge=lfs -text
621
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2777__52a1e79f-39bf-4ffd-bec7-d1bd9e6ea667__10999989.png filter=lfs diff=lfs merge=lfs -text
622
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2777__8847117c-066a-476c-889b-3940d6ca178b__8999975.png filter=lfs diff=lfs merge=lfs -text
623
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2778__66e38562-7434-42c8-b97c-210afbf97016__9000010.png filter=lfs diff=lfs merge=lfs -text
624
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2779__44df6d40-5f86-4ecc-8432-265e2beeac7e__10999850.png filter=lfs diff=lfs merge=lfs -text
625
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2779__81967a46-b230-45f6-a56f-730a70ddf7b5__10000000.png filter=lfs diff=lfs merge=lfs -text
626
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2780__d573ca03-a457-446a-8243-433a28d910d0__9000008.png filter=lfs diff=lfs merge=lfs -text
627
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2794__e8f8ed0b-abd0-40fc-9889-512f9eebfa2c__8000013.png filter=lfs diff=lfs merge=lfs -text
628
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2795__07233c4b-9fab-481c-847c-4867513586c0__9999997.png filter=lfs diff=lfs merge=lfs -text
629
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2796__eb87b038-404e-4f00-b638-98ff7b40ac00__2000001.png filter=lfs diff=lfs merge=lfs -text
630
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2797__365c37a2-94cd-40de-b94b-1674e0ef408c__13000090.png filter=lfs diff=lfs merge=lfs -text
631
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2798__39bd6901-3a99-47dc-992e-e364346247a0__1999997.png filter=lfs diff=lfs merge=lfs -text
632
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2799__29c4cd40-d260-488e-9d1d-f8a3cf952c2a__11000008.png filter=lfs diff=lfs merge=lfs -text
633
+ ADEn-CFJ-KL0/eval_image_cache/chunk_2799__29c4cd40-d260-488e-9d1d-f8a3cf952c2a__7000012.png filter=lfs diff=lfs merge=lfs -text
634
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3020__203421ee-e75c-41c4-9dbe-34f2f7adf79c__10999997.png filter=lfs diff=lfs merge=lfs -text
635
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3020__56f16fff-6c63-4511-a971-ca043d18a4aa__10999988.png filter=lfs diff=lfs merge=lfs -text
636
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3020__b4239ff9-aaac-4f0e-b307-fdbe53a94d11__6000006.png filter=lfs diff=lfs merge=lfs -text
637
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3021__a54f8f11-fab1-4add-94e6-4236ee63cee9__12000006.png filter=lfs diff=lfs merge=lfs -text
638
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3021__aea860ff-6b70-456d-beba-d0a83ecd0bd9__4999991.png filter=lfs diff=lfs merge=lfs -text
639
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3022__1df7dea7-061b-4edf-8fcd-48296dbb2287__12999975.png filter=lfs diff=lfs merge=lfs -text
640
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3080__62fe5e69-b0f8-446c-bd4b-1e5b19f1981e__3999996.png filter=lfs diff=lfs merge=lfs -text
641
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3080__d6b6653b-77cb-4bf2-a751-f82be313ff56__9999978.png filter=lfs diff=lfs merge=lfs -text
642
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3081__4024607b-3590-4316-8c55-8e644c70b3a7__5999998.png filter=lfs diff=lfs merge=lfs -text
643
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3081__44f595a6-e638-456c-92ca-fd8b7e2a631b__8999936.png filter=lfs diff=lfs merge=lfs -text
644
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3082__29b1de86-ca2e-47e5-9f4b-846892485ec4__6000114.png filter=lfs diff=lfs merge=lfs -text
645
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3083__e0fd41f6-1e4b-4a1e-a1ea-7ac0d0b3e1a0__14000108.png filter=lfs diff=lfs merge=lfs -text
646
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3084__76712ddc-0849-4345-89ce-2354c1e26612__12000056.png filter=lfs diff=lfs merge=lfs -text
647
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3084__9f5ff8ae-5e43-4116-94e1-202906ee17bd__8001827.png filter=lfs diff=lfs merge=lfs -text
648
+ ADEn-CFJ-KL0/eval_image_cache/chunk_3087__c44bb8ad-a913-494d-88a1-987b6e8bfdf3__8000142.png filter=lfs diff=lfs merge=lfs -text
649
+ ADEn-CFJ-KL0/tokenizer.json filter=lfs diff=lfs merge=lfs -text
ADEn-CFJ-KL0/README.md ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ ---
2
+ base_model: mjf-su/PhysicalAI-reason-VLA-MetaAction-1e
3
+ library_name: transformers
4
+ model_name: ADEn-CFJ-KL0
5
+ tags:
6
+ - generated_from_trainer
7
+ - trl
8
+ - grpo
9
+ licence: license
10
+ ---
11
+
12
+ # Model Card for ADEn-CFJ-KL0
13
+
14
+ This model is a fine-tuned version of [mjf-su/PhysicalAI-reason-VLA-MetaAction-1e](https://huggingface.co/mjf-su/PhysicalAI-reason-VLA-MetaAction-1e).
15
+ It has been trained using [TRL](https://github.com/huggingface/trl).
16
+
17
+ ## Quick start
18
+
19
+ ```python
20
+ from transformers import pipeline
21
+
22
+ question = "If you had a time machine, but could only go to the past or the future once and never return, which would you choose and why?"
23
+ generator = pipeline("text-generation", model="None", device="cuda")
24
+ output = generator([{"role": "user", "content": question}], max_new_tokens=128, return_full_text=False)[0]
25
+ print(output["generated_text"])
26
+ ```
27
+
28
+ ## Training procedure
29
+
30
+ [<img src="https://raw.githubusercontent.com/wandb/assets/main/wandb-github-badge-28.svg" alt="Visualize in Weights & Biases" width="150" height="24"/>](https://wandb.ai/mjf-su-stanford-university/GRPO-faithfulness/runs/40aidksk)
31
+
32
+
33
+ This model was trained with GRPO, a method introduced in [DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models](https://huggingface.co/papers/2402.03300).
34
+
35
+ ### Framework versions
36
+
37
+ - TRL: 0.26.1
38
+ - Transformers: 4.57.6
39
+ - Pytorch: 2.10.0
40
+ - Datasets: 4.4.1
41
+ - Tokenizers: 0.22.1
42
+
43
+ ## Citations
44
+
45
+ Cite GRPO as:
46
+
47
+ ```bibtex
48
+ @article{shao2024deepseekmath,
49
+ title = {{DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models}},
50
+ author = {Zhihong Shao and Peiyi Wang and Qihao Zhu and Runxin Xu and Junxiao Song and Mingchuan Zhang and Y. K. Li and Y. Wu and Daya Guo},
51
+ year = 2024,
52
+ eprint = {arXiv:2402.03300},
53
+ }
54
+
55
+ ```
56
+
57
+ Cite TRL as:
58
+
59
+ ```bibtex
60
+ @misc{vonwerra2022trl,
61
+ title = {{TRL: Transformer Reinforcement Learning}},
62
+ author = {Leandro von Werra and Younes Belkada and Lewis Tunstall and Edward Beeching and Tristan Thrush and Nathan Lambert and Shengyi Huang and Kashif Rasul and Quentin Gallou{\'e}dec},
63
+ year = 2020,
64
+ journal = {GitHub repository},
65
+ publisher = {GitHub},
66
+ howpublished = {\url{https://github.com/huggingface/trl}}
67
+ }
68
+ ```
ADEn-CFJ-KL0/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
ADEn-CFJ-KL0/chat_template.jinja ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- else %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if do_vision_count %}
10
+ {%- set image_count.value = image_count.value + 1 %}
11
+ {%- endif %}
12
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
13
+ <|vision_start|><|image_pad|><|vision_end|>
14
+ {%- elif 'video' in item or item.type == 'video' %}
15
+ {%- if do_vision_count %}
16
+ {%- set video_count.value = video_count.value + 1 %}
17
+ {%- endif %}
18
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
19
+ <|vision_start|><|video_pad|><|vision_end|>
20
+ {%- elif 'text' in item %}
21
+ {{- item.text }}
22
+ {%- endif %}
23
+ {%- endfor %}
24
+ {%- endif %}
25
+ {%- endmacro %}
26
+ {%- if tools %}
27
+ {{- '<|im_start|>system\n' }}
28
+ {%- if messages[0].role == 'system' %}
29
+ {{- render_content(messages[0].content, false) + '\n\n' }}
30
+ {%- endif %}
31
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
32
+ {%- for tool in tools %}
33
+ {{- "\n" }}
34
+ {{- tool | tojson }}
35
+ {%- endfor %}
36
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
37
+ {%- else %}
38
+ {%- if messages[0].role == 'system' %}
39
+ {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
40
+ {%- endif %}
41
+ {%- endif %}
42
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
43
+ {%- for message in messages[::-1] %}
44
+ {%- set index = (messages|length - 1) - loop.index0 %}
45
+ {%- if ns.multi_step_tool and message.role == "user" %}
46
+ {%- set content = render_content(message.content, false) %}
47
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
48
+ {%- set ns.multi_step_tool = false %}
49
+ {%- set ns.last_query_index = index %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- endfor %}
53
+ {%- for message in messages %}
54
+ {%- set content = render_content(message.content, True) %}
55
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
57
+ {%- elif message.role == "assistant" %}
58
+ {%- set reasoning_content = '' %}
59
+ {%- if message.reasoning_content is string %}
60
+ {%- set reasoning_content = message.reasoning_content %}
61
+ {%- else %}
62
+ {%- if '</think>' in content %}
63
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
64
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- if loop.index0 > ns.last_query_index %}
68
+ {%- if loop.last or (not loop.last and reasoning_content) %}
69
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
70
+ {%- else %}
71
+ {{- '<|im_start|>' + message.role + '\n' + content }}
72
+ {%- endif %}
73
+ {%- else %}
74
+ {{- '<|im_start|>' + message.role + '\n' + content }}
75
+ {%- endif %}
76
+ {%- if message.tool_calls %}
77
+ {%- for tool_call in message.tool_calls %}
78
+ {%- if (loop.first and content) or (not loop.first) %}
79
+ {{- '\n' }}
80
+ {%- endif %}
81
+ {%- if tool_call.function %}
82
+ {%- set tool_call = tool_call.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>\n{"name": "' }}
85
+ {{- tool_call.name }}
86
+ {{- '", "arguments": ' }}
87
+ {%- if tool_call.arguments is string %}
88
+ {{- tool_call.arguments }}
89
+ {%- else %}
90
+ {{- tool_call.arguments | tojson }}
91
+ {%- endif %}
92
+ {{- '}\n</tool_call>' }}
93
+ {%- endfor %}
94
+ {%- endif %}
95
+ {{- '<|im_end|>\n' }}
96
+ {%- elif message.role == "tool" %}
97
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
98
+ {{- '<|im_start|>user' }}
99
+ {%- endif %}
100
+ {{- '\n<tool_response>\n' }}
101
+ {{- content }}
102
+ {{- '\n</tool_response>' }}
103
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
104
+ {{- '<|im_end|>\n' }}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- endfor %}
108
+ {%- if add_generation_prompt %}
109
+ {{- '<|im_start|>assistant\n' }}
110
+ {%- endif %}
ADEn-CFJ-KL0/checkpoint-100/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
ADEn-CFJ-KL0/checkpoint-100/chat_template.jinja ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- else %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if do_vision_count %}
10
+ {%- set image_count.value = image_count.value + 1 %}
11
+ {%- endif %}
12
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
13
+ <|vision_start|><|image_pad|><|vision_end|>
14
+ {%- elif 'video' in item or item.type == 'video' %}
15
+ {%- if do_vision_count %}
16
+ {%- set video_count.value = video_count.value + 1 %}
17
+ {%- endif %}
18
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
19
+ <|vision_start|><|video_pad|><|vision_end|>
20
+ {%- elif 'text' in item %}
21
+ {{- item.text }}
22
+ {%- endif %}
23
+ {%- endfor %}
24
+ {%- endif %}
25
+ {%- endmacro %}
26
+ {%- if tools %}
27
+ {{- '<|im_start|>system\n' }}
28
+ {%- if messages[0].role == 'system' %}
29
+ {{- render_content(messages[0].content, false) + '\n\n' }}
30
+ {%- endif %}
31
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
32
+ {%- for tool in tools %}
33
+ {{- "\n" }}
34
+ {{- tool | tojson }}
35
+ {%- endfor %}
36
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
37
+ {%- else %}
38
+ {%- if messages[0].role == 'system' %}
39
+ {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
40
+ {%- endif %}
41
+ {%- endif %}
42
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
43
+ {%- for message in messages[::-1] %}
44
+ {%- set index = (messages|length - 1) - loop.index0 %}
45
+ {%- if ns.multi_step_tool and message.role == "user" %}
46
+ {%- set content = render_content(message.content, false) %}
47
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
48
+ {%- set ns.multi_step_tool = false %}
49
+ {%- set ns.last_query_index = index %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- endfor %}
53
+ {%- for message in messages %}
54
+ {%- set content = render_content(message.content, True) %}
55
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
57
+ {%- elif message.role == "assistant" %}
58
+ {%- set reasoning_content = '' %}
59
+ {%- if message.reasoning_content is string %}
60
+ {%- set reasoning_content = message.reasoning_content %}
61
+ {%- else %}
62
+ {%- if '</think>' in content %}
63
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
64
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- if loop.index0 > ns.last_query_index %}
68
+ {%- if loop.last or (not loop.last and reasoning_content) %}
69
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
70
+ {%- else %}
71
+ {{- '<|im_start|>' + message.role + '\n' + content }}
72
+ {%- endif %}
73
+ {%- else %}
74
+ {{- '<|im_start|>' + message.role + '\n' + content }}
75
+ {%- endif %}
76
+ {%- if message.tool_calls %}
77
+ {%- for tool_call in message.tool_calls %}
78
+ {%- if (loop.first and content) or (not loop.first) %}
79
+ {{- '\n' }}
80
+ {%- endif %}
81
+ {%- if tool_call.function %}
82
+ {%- set tool_call = tool_call.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>\n{"name": "' }}
85
+ {{- tool_call.name }}
86
+ {{- '", "arguments": ' }}
87
+ {%- if tool_call.arguments is string %}
88
+ {{- tool_call.arguments }}
89
+ {%- else %}
90
+ {{- tool_call.arguments | tojson }}
91
+ {%- endif %}
92
+ {{- '}\n</tool_call>' }}
93
+ {%- endfor %}
94
+ {%- endif %}
95
+ {{- '<|im_end|>\n' }}
96
+ {%- elif message.role == "tool" %}
97
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
98
+ {{- '<|im_start|>user' }}
99
+ {%- endif %}
100
+ {{- '\n<tool_response>\n' }}
101
+ {{- content }}
102
+ {{- '\n</tool_response>' }}
103
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
104
+ {{- '<|im_end|>\n' }}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- endfor %}
108
+ {%- if add_generation_prompt %}
109
+ {{- '<|im_start|>assistant\n' }}
110
+ {%- endif %}
ADEn-CFJ-KL0/checkpoint-100/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "image_token_id": 151655,
8
+ "model_type": "qwen3_vl",
9
+ "pad_token_id": 151643,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 151643,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 151645,
16
+ "head_dim": 128,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2560,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 9728,
21
+ "max_position_embeddings": 262144,
22
+ "model_type": "qwen3_vl_text",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 36,
25
+ "num_key_value_heads": 8,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_scaling": {
28
+ "mrope_interleaved": true,
29
+ "mrope_section": [
30
+ 24,
31
+ 20,
32
+ 20
33
+ ],
34
+ "rope_type": "default"
35
+ },
36
+ "rope_theta": 5000000,
37
+ "tie_word_embeddings": true,
38
+ "use_cache": true,
39
+ "vocab_size": 151936
40
+ },
41
+ "tie_word_embeddings": true,
42
+ "transformers_version": "4.57.6",
43
+ "use_cache": false,
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 5,
48
+ 11,
49
+ 17
50
+ ],
51
+ "depth": 24,
52
+ "dtype": "bfloat16",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1024,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 2560,
62
+ "patch_size": 16,
63
+ "spatial_merge_size": 2,
64
+ "temporal_patch_size": 2
65
+ },
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652
68
+ }
ADEn-CFJ-KL0/checkpoint-100/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.57.6"
12
+ }
ADEn-CFJ-KL0/checkpoint-100/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
ADEn-CFJ-KL0/checkpoint-100/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:265d738988bcb376780f3f68251aeb449dc2dcac58af6ec19f7e131b8b5f7eaf
3
+ size 4990497880
ADEn-CFJ-KL0/checkpoint-100/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:537445401f6b04c9eb451579b1b77f989df9e6fa38eea9587a355030d9b2886c
3
+ size 3885221448
ADEn-CFJ-KL0/checkpoint-100/model.safetensors.index.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4437815808,
4
+ "total_size": 8875631616
5
+ },
6
+ "weight_map": {
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
97
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
405
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
406
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
408
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
409
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
410
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
411
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
412
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
413
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
414
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
415
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
416
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
417
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
418
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
420
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
421
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
422
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
423
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
424
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
425
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
426
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
427
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
428
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
429
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
432
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
433
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
438
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
439
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
440
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
441
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
444
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
445
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
446
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
447
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
448
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
449
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
450
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
451
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
452
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
453
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
456
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
457
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
458
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
459
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
460
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
461
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
462
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
463
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
464
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
465
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
466
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
468
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
469
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
470
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
471
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
472
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
473
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
474
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
475
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
476
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
482
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
483
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
484
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
485
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
486
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
487
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
488
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
489
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
490
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
492
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
493
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
494
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
495
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
496
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
497
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
498
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
499
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
500
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
501
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
502
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
504
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
505
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
506
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
507
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
508
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
509
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
510
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
511
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
512
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
513
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
514
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
515
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
516
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
517
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
518
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
519
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
520
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
521
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
522
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
523
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
524
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
525
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
526
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
527
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
528
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
529
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
530
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
531
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
532
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
533
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
534
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
535
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
536
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
537
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
538
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
539
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
540
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
541
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
542
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
543
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
544
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
545
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
546
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
547
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
548
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
549
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
550
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
551
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
552
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
553
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
554
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
555
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
556
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
557
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
558
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
559
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
560
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
561
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
562
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
563
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
564
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
565
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
566
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
567
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
568
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
569
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
570
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
571
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
572
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
573
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
574
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
575
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
576
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
577
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
578
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
579
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
580
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
581
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
582
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
583
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
584
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
585
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
586
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
587
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
588
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
589
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
590
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
591
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
592
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
593
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
594
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
595
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
596
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
597
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
598
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
599
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
600
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
601
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
602
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
603
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
604
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
605
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
606
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
607
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
608
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
609
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
610
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
611
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
612
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
613
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
614
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
615
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
616
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
617
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
618
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
619
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
620
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
621
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
622
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
623
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
624
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
625
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
626
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
627
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
628
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
629
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
630
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
631
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
632
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
633
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
634
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
635
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
636
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
637
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
638
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
639
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
640
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
641
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
642
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
643
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
644
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
645
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
646
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
647
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
648
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
649
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
650
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
651
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
652
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
653
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
654
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
655
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
656
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
657
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
658
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
659
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
660
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
661
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
662
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
663
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
664
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
665
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
666
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
667
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
668
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
669
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
670
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
671
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
672
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
673
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
674
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
675
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
676
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
677
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
678
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
679
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
680
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
681
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
682
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
683
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
684
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
685
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
686
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
687
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
688
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
689
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
690
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
691
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
692
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
693
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
694
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
695
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
696
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
697
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
698
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
699
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
700
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
701
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
702
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
703
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
704
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
705
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
706
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
707
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
708
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
709
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
710
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
711
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
712
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
713
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
714
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
715
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
716
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
717
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
718
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
719
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
720
+ }
721
+ }
ADEn-CFJ-KL0/checkpoint-100/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58cafafe6afcbb8d171d6296f655dff94e095b785ada23327bc512cd36723f31
3
+ size 16090226537
ADEn-CFJ-KL0/checkpoint-100/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:658dd286d40d96edc0640447b800b53e7abc000fdf2e8b8c3ff01c8e248806c5
3
+ size 14853
ADEn-CFJ-KL0/checkpoint-100/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:69926e1cb17276b386d13b54c3d385820686523929f3719f65e62603c014abbe
3
+ size 14917
ADEn-CFJ-KL0/checkpoint-100/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:2c64505c5b36da3be59e9e5daa60039a6fba9dc5c33f06140c82afef8dd3fe60
3
+ size 1465
ADEn-CFJ-KL0/checkpoint-100/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
ADEn-CFJ-KL0/checkpoint-100/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f6994642cfbd8473e43b4fae1d60d4a953aea1419dc28b4ae3f41778cd0924
3
+ size 11422922
ADEn-CFJ-KL0/checkpoint-100/tokenizer_config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "max_length": null,
235
+ "model_max_length": 262144,
236
+ "pad_to_multiple_of": null,
237
+ "pad_token": "<|endoftext|>",
238
+ "pad_token_type_id": 0,
239
+ "padding_side": "left",
240
+ "processor_class": "Qwen3VLProcessor",
241
+ "split_special_tokens": false,
242
+ "tokenizer_class": "Qwen2Tokenizer",
243
+ "unk_token": null
244
+ }
ADEn-CFJ-KL0/checkpoint-100/trainer_state.json ADDED
@@ -0,0 +1,353 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.021431633090441493,
6
+ "eval_steps": 72,
7
+ "global_step": 100,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.0,
19
+ "completions/max_length": 722.4,
20
+ "completions/max_terminated_length": 722.4,
21
+ "completions/mean_length": 687.3479309082031,
22
+ "completions/mean_terminated_length": 687.3479309082031,
23
+ "completions/min_length": 596.1,
24
+ "completions/min_terminated_length": 596.1,
25
+ "entropy": 0.5129013667503993,
26
+ "epoch": 0.0021431633090441492,
27
+ "frac_reward_zero_std": 0.0,
28
+ "grad_norm": 0.9375,
29
+ "learning_rate": 9.691780821917808e-07,
30
+ "loss": -0.005,
31
+ "num_tokens": 995975.0,
32
+ "reward": -0.06374586373567581,
33
+ "reward_std": 0.22546745985746383,
34
+ "rewards/ADEnReward/mean": 0.016389049030840395,
35
+ "rewards/ADEnReward/std": 0.048161597922444344,
36
+ "rewards/CounterfactualJustificationReward/mean": -0.08013491020537913,
37
+ "rewards/CounterfactualJustificationReward/std": 0.2300958290696144,
38
+ "step": 10,
39
+ "step_time": 266.3497134976002
40
+ },
41
+ {
42
+ "clip_ratio/high_max": 0.0,
43
+ "clip_ratio/high_mean": 0.0,
44
+ "clip_ratio/low_mean": 0.0,
45
+ "clip_ratio/low_min": 0.0,
46
+ "clip_ratio/region_mean": 0.0,
47
+ "completions/clipped_ratio": 0.0,
48
+ "completions/max_length": 725.4,
49
+ "completions/max_terminated_length": 725.4,
50
+ "completions/mean_length": 689.1125244140625,
51
+ "completions/mean_terminated_length": 689.1125244140625,
52
+ "completions/min_length": 652.9,
53
+ "completions/min_terminated_length": 652.9,
54
+ "entropy": 0.5154734035332997,
55
+ "epoch": 0.0042863266180882984,
56
+ "frac_reward_zero_std": 0.0,
57
+ "grad_norm": 0.87890625,
58
+ "learning_rate": 9.349315068493149e-07,
59
+ "loss": 0.0001,
60
+ "num_tokens": 1992877.0,
61
+ "reward": -0.05411523887887597,
62
+ "reward_std": 0.21374744027853013,
63
+ "rewards/ADEnReward/mean": 0.02242780737578869,
64
+ "rewards/ADEnReward/std": 0.05705951061099768,
65
+ "rewards/CounterfactualJustificationReward/mean": -0.07654304374009371,
66
+ "rewards/CounterfactualJustificationReward/std": 0.2092343047261238,
67
+ "step": 20,
68
+ "step_time": 269.486055393095
69
+ },
70
+ {
71
+ "clip_ratio/high_max": 0.0,
72
+ "clip_ratio/high_mean": 0.0,
73
+ "clip_ratio/low_mean": 0.0,
74
+ "clip_ratio/low_min": 0.0,
75
+ "clip_ratio/region_mean": 0.0,
76
+ "completions/clipped_ratio": 0.002083333395421505,
77
+ "completions/max_length": 756.0,
78
+ "completions/max_terminated_length": 727.1,
79
+ "completions/mean_length": 688.0000183105469,
80
+ "completions/mean_terminated_length": 687.2961120605469,
81
+ "completions/min_length": 652.2,
82
+ "completions/min_terminated_length": 652.2,
83
+ "entropy": 0.5114999602238337,
84
+ "epoch": 0.006429489927132447,
85
+ "frac_reward_zero_std": 0.0,
86
+ "grad_norm": 0.890625,
87
+ "learning_rate": 9.006849315068494e-07,
88
+ "loss": 0.0042,
89
+ "num_tokens": 2988621.0,
90
+ "reward": -0.07193327061831951,
91
+ "reward_std": 0.23947951942682266,
92
+ "rewards/ADEnReward/mean": 0.018894296162761746,
93
+ "rewards/ADEnReward/std": 0.05166068505495787,
94
+ "rewards/CounterfactualJustificationReward/mean": -0.09082756340503692,
95
+ "rewards/CounterfactualJustificationReward/std": 0.23909800499677658,
96
+ "step": 30,
97
+ "step_time": 276.6699794655084
98
+ },
99
+ {
100
+ "clip_ratio/high_max": 0.0,
101
+ "clip_ratio/high_mean": 0.0,
102
+ "clip_ratio/low_mean": 0.0,
103
+ "clip_ratio/low_min": 0.0,
104
+ "clip_ratio/region_mean": 0.0,
105
+ "completions/clipped_ratio": 0.0,
106
+ "completions/max_length": 728.7,
107
+ "completions/max_terminated_length": 728.7,
108
+ "completions/mean_length": 691.1791931152344,
109
+ "completions/mean_terminated_length": 691.1791931152344,
110
+ "completions/min_length": 655.7,
111
+ "completions/min_terminated_length": 655.7,
112
+ "entropy": 0.5192137628793716,
113
+ "epoch": 0.008572653236176597,
114
+ "frac_reward_zero_std": 0.0,
115
+ "grad_norm": 1.03125,
116
+ "learning_rate": 8.664383561643836e-07,
117
+ "loss": 0.0008,
118
+ "num_tokens": 3986499.0,
119
+ "reward": -0.03571146372705698,
120
+ "reward_std": 0.24846212714910507,
121
+ "rewards/ADEnReward/mean": 0.02276311726309359,
122
+ "rewards/ADEnReward/std": 0.06564843580126763,
123
+ "rewards/CounterfactualJustificationReward/mean": -0.05847458196803927,
124
+ "rewards/CounterfactualJustificationReward/std": 0.23850561082363128,
125
+ "step": 40,
126
+ "step_time": 270.7083416894951
127
+ },
128
+ {
129
+ "clip_ratio/high_max": 0.0,
130
+ "clip_ratio/high_mean": 0.0,
131
+ "clip_ratio/low_mean": 0.0,
132
+ "clip_ratio/low_min": 0.0,
133
+ "clip_ratio/region_mean": 0.0,
134
+ "completions/clipped_ratio": 0.0,
135
+ "completions/max_length": 722.6,
136
+ "completions/max_terminated_length": 722.6,
137
+ "completions/mean_length": 686.5562683105469,
138
+ "completions/mean_terminated_length": 686.5562683105469,
139
+ "completions/min_length": 654.7,
140
+ "completions/min_terminated_length": 654.7,
141
+ "entropy": 0.5242228974898656,
142
+ "epoch": 0.010715816545220747,
143
+ "frac_reward_zero_std": 0.0,
144
+ "grad_norm": 0.89453125,
145
+ "learning_rate": 8.321917808219178e-07,
146
+ "loss": 0.0024,
147
+ "num_tokens": 4981982.0,
148
+ "reward": -0.037678991351276635,
149
+ "reward_std": 0.23401633203029631,
150
+ "rewards/ADEnReward/mean": 0.023655857401899995,
151
+ "rewards/ADEnReward/std": 0.06490156231448055,
152
+ "rewards/CounterfactualJustificationReward/mean": -0.06133484859019518,
153
+ "rewards/CounterfactualJustificationReward/std": 0.22413837760686875,
154
+ "step": 50,
155
+ "step_time": 271.4957699022081
156
+ },
157
+ {
158
+ "clip_ratio/high_max": 0.0,
159
+ "clip_ratio/high_mean": 0.0,
160
+ "clip_ratio/low_mean": 0.0,
161
+ "clip_ratio/low_min": 0.0,
162
+ "clip_ratio/region_mean": 0.0,
163
+ "completions/clipped_ratio": 0.0,
164
+ "completions/max_length": 729.0,
165
+ "completions/max_terminated_length": 729.0,
166
+ "completions/mean_length": 688.4916870117188,
167
+ "completions/mean_terminated_length": 688.4916870117188,
168
+ "completions/min_length": 654.9,
169
+ "completions/min_terminated_length": 654.9,
170
+ "entropy": 0.5326574305693309,
171
+ "epoch": 0.012858979854264894,
172
+ "frac_reward_zero_std": 0.0,
173
+ "grad_norm": 0.87109375,
174
+ "learning_rate": 7.97945205479452e-07,
175
+ "loss": -0.0003,
176
+ "num_tokens": 5978394.0,
177
+ "reward": -0.05084102489054203,
178
+ "reward_std": 0.2377728059887886,
179
+ "rewards/ADEnReward/mean": 0.020620170864276588,
180
+ "rewards/ADEnReward/std": 0.062224847916513684,
181
+ "rewards/CounterfactualJustificationReward/mean": -0.07146119233220816,
182
+ "rewards/CounterfactualJustificationReward/std": 0.23566005975008011,
183
+ "step": 60,
184
+ "step_time": 269.84039734689867
185
+ },
186
+ {
187
+ "clip_ratio/high_max": 0.0,
188
+ "clip_ratio/high_mean": 0.0,
189
+ "clip_ratio/low_mean": 0.0,
190
+ "clip_ratio/low_min": 0.0,
191
+ "clip_ratio/region_mean": 0.0,
192
+ "completions/clipped_ratio": 0.0,
193
+ "completions/max_length": 723.0,
194
+ "completions/max_terminated_length": 723.0,
195
+ "completions/mean_length": 689.7208557128906,
196
+ "completions/mean_terminated_length": 689.7208557128906,
197
+ "completions/min_length": 653.6,
198
+ "completions/min_terminated_length": 653.6,
199
+ "entropy": 0.5156665503978729,
200
+ "epoch": 0.015002143163309044,
201
+ "frac_reward_zero_std": 0.0,
202
+ "grad_norm": 1.078125,
203
+ "learning_rate": 7.636986301369863e-07,
204
+ "loss": -0.0011,
205
+ "num_tokens": 6975652.0,
206
+ "reward": -0.007650468964129686,
207
+ "reward_std": 0.24781250208616257,
208
+ "rewards/ADEnReward/mean": 0.023274474567733704,
209
+ "rewards/ADEnReward/std": 0.058971316739916804,
210
+ "rewards/CounterfactualJustificationReward/mean": -0.03092494057491422,
211
+ "rewards/CounterfactualJustificationReward/std": 0.250348636507988,
212
+ "step": 70,
213
+ "step_time": 274.2808645738929
214
+ },
215
+ {
216
+ "epoch": 0.015430775825117874,
217
+ "eval_clip_ratio/high_max": 0.0,
218
+ "eval_clip_ratio/high_mean": 0.0,
219
+ "eval_clip_ratio/low_mean": 0.0,
220
+ "eval_clip_ratio/low_min": 0.0,
221
+ "eval_clip_ratio/region_mean": 0.0,
222
+ "eval_completions/clipped_ratio": 0.0003125,
223
+ "eval_completions/max_length": 718.315,
224
+ "eval_completions/max_terminated_length": 716.775,
225
+ "eval_completions/mean_length": 691.1975,
226
+ "eval_completions/mean_terminated_length": 691.0926043701172,
227
+ "eval_completions/min_length": 667.385,
228
+ "eval_completions/min_terminated_length": 667.385,
229
+ "eval_entropy": 0.5353066678345203,
230
+ "eval_frac_reward_zero_std": 0.0,
231
+ "eval_loss": 0.0011824100511148572,
232
+ "eval_num_tokens": 7174184.0,
233
+ "eval_reward": -0.011725269807502627,
234
+ "eval_reward_std": 0.2379829413443804,
235
+ "eval_rewards/ADEnReward/mean": 0.01436133997845951,
236
+ "eval_rewards/ADEnReward/std": 0.031373489485568846,
237
+ "eval_rewards/CounterfactualJustificationReward/mean": -0.026086609871126713,
238
+ "eval_rewards/CounterfactualJustificationReward/std": 0.2323593620210886,
239
+ "eval_runtime": 9510.9089,
240
+ "eval_samples_per_second": 0.021,
241
+ "eval_steps_per_second": 0.001,
242
+ "step": 72
243
+ },
244
+ {
245
+ "clip_ratio/high_max": 0.0,
246
+ "clip_ratio/high_mean": 0.0,
247
+ "clip_ratio/low_mean": 0.0,
248
+ "clip_ratio/low_min": 0.0,
249
+ "clip_ratio/region_mean": 0.0,
250
+ "completions/clipped_ratio": 0.0,
251
+ "completions/max_length": 722.3,
252
+ "completions/max_terminated_length": 722.3,
253
+ "completions/mean_length": 683.2312805175782,
254
+ "completions/mean_terminated_length": 683.2312805175782,
255
+ "completions/min_length": 597.0,
256
+ "completions/min_terminated_length": 597.0,
257
+ "entropy": 0.5130097369352976,
258
+ "epoch": 0.017145306472353194,
259
+ "frac_reward_zero_std": 0.0,
260
+ "grad_norm": 0.91796875,
261
+ "learning_rate": 7.294520547945205e-07,
262
+ "loss": -0.004,
263
+ "num_tokens": 7969155.0,
264
+ "reward": -0.0016561332624405623,
265
+ "reward_std": 0.22166914492845535,
266
+ "rewards/ADEnReward/mean": 0.02527421610429883,
267
+ "rewards/ADEnReward/std": 0.06894388236105442,
268
+ "rewards/CounterfactualJustificationReward/mean": -0.026930347364395858,
269
+ "rewards/CounterfactualJustificationReward/std": 0.22469179928302765,
270
+ "step": 80,
271
+ "step_time": 271.889700404898
272
+ },
273
+ {
274
+ "clip_ratio/high_max": 0.0,
275
+ "clip_ratio/high_mean": 0.0,
276
+ "clip_ratio/low_mean": 0.0,
277
+ "clip_ratio/low_min": 0.0,
278
+ "clip_ratio/region_mean": 0.0,
279
+ "completions/clipped_ratio": 0.002083333395421505,
280
+ "completions/max_length": 754.8,
281
+ "completions/max_terminated_length": 724.9,
282
+ "completions/mean_length": 691.5583557128906,
283
+ "completions/mean_terminated_length": 690.8669494628906,
284
+ "completions/min_length": 660.1,
285
+ "completions/min_terminated_length": 660.1,
286
+ "entropy": 0.5074795544147491,
287
+ "epoch": 0.01928846978139734,
288
+ "frac_reward_zero_std": 0.0,
289
+ "grad_norm": 1.0390625,
290
+ "learning_rate": 6.952054794520548e-07,
291
+ "loss": 0.0018,
292
+ "num_tokens": 8967791.0,
293
+ "reward": 0.026898569357581437,
294
+ "reward_std": 0.2355131596326828,
295
+ "rewards/ADEnReward/mean": 0.03706806637346745,
296
+ "rewards/ADEnReward/std": 0.08285447619855404,
297
+ "rewards/CounterfactualJustificationReward/mean": -0.010169497784227132,
298
+ "rewards/CounterfactualJustificationReward/std": 0.21885453909635544,
299
+ "step": 90,
300
+ "step_time": 270.5311606264906
301
+ },
302
+ {
303
+ "clip_ratio/high_max": 0.0,
304
+ "clip_ratio/high_mean": 0.0,
305
+ "clip_ratio/low_mean": 0.0,
306
+ "clip_ratio/low_min": 0.0,
307
+ "clip_ratio/region_mean": 0.0,
308
+ "completions/clipped_ratio": 0.0,
309
+ "completions/max_length": 723.9,
310
+ "completions/max_terminated_length": 723.9,
311
+ "completions/mean_length": 688.6875183105469,
312
+ "completions/mean_terminated_length": 688.6875183105469,
313
+ "completions/min_length": 654.3,
314
+ "completions/min_terminated_length": 654.3,
315
+ "entropy": 0.522646211584409,
316
+ "epoch": 0.021431633090441493,
317
+ "frac_reward_zero_std": 0.0,
318
+ "grad_norm": 0.93359375,
319
+ "learning_rate": 6.60958904109589e-07,
320
+ "loss": 0.0008,
321
+ "num_tokens": 9964505.0,
322
+ "reward": -0.00860080262646079,
323
+ "reward_std": 0.241253000497818,
324
+ "rewards/ADEnReward/mean": 0.029191052657552063,
325
+ "rewards/ADEnReward/std": 0.06871706424281002,
326
+ "rewards/CounterfactualJustificationReward/mean": -0.03779185602907091,
327
+ "rewards/CounterfactualJustificationReward/std": 0.2387075498700142,
328
+ "step": 100,
329
+ "step_time": 268.47685881000945
330
+ }
331
+ ],
332
+ "logging_steps": 10,
333
+ "max_steps": 292,
334
+ "num_input_tokens_seen": 9964505,
335
+ "num_train_epochs": 1,
336
+ "save_steps": 100,
337
+ "stateful_callbacks": {
338
+ "TrainerControl": {
339
+ "args": {
340
+ "should_epoch_stop": false,
341
+ "should_evaluate": false,
342
+ "should_log": false,
343
+ "should_save": true,
344
+ "should_training_stop": false
345
+ },
346
+ "attributes": {}
347
+ }
348
+ },
349
+ "total_flos": 0.0,
350
+ "train_batch_size": 8,
351
+ "trial_name": null,
352
+ "trial_params": null
353
+ }
ADEn-CFJ-KL0/checkpoint-100/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0c5e97464cdcc3e01b3a9fb60ed99b89088f1cdc1cd8493defe8506d2eec40
3
+ size 7569
ADEn-CFJ-KL0/checkpoint-100/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
ADEn-CFJ-KL0/checkpoint-200/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
ADEn-CFJ-KL0/checkpoint-200/chat_template.jinja ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- else %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if do_vision_count %}
10
+ {%- set image_count.value = image_count.value + 1 %}
11
+ {%- endif %}
12
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
13
+ <|vision_start|><|image_pad|><|vision_end|>
14
+ {%- elif 'video' in item or item.type == 'video' %}
15
+ {%- if do_vision_count %}
16
+ {%- set video_count.value = video_count.value + 1 %}
17
+ {%- endif %}
18
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
19
+ <|vision_start|><|video_pad|><|vision_end|>
20
+ {%- elif 'text' in item %}
21
+ {{- item.text }}
22
+ {%- endif %}
23
+ {%- endfor %}
24
+ {%- endif %}
25
+ {%- endmacro %}
26
+ {%- if tools %}
27
+ {{- '<|im_start|>system\n' }}
28
+ {%- if messages[0].role == 'system' %}
29
+ {{- render_content(messages[0].content, false) + '\n\n' }}
30
+ {%- endif %}
31
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
32
+ {%- for tool in tools %}
33
+ {{- "\n" }}
34
+ {{- tool | tojson }}
35
+ {%- endfor %}
36
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
37
+ {%- else %}
38
+ {%- if messages[0].role == 'system' %}
39
+ {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
40
+ {%- endif %}
41
+ {%- endif %}
42
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
43
+ {%- for message in messages[::-1] %}
44
+ {%- set index = (messages|length - 1) - loop.index0 %}
45
+ {%- if ns.multi_step_tool and message.role == "user" %}
46
+ {%- set content = render_content(message.content, false) %}
47
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
48
+ {%- set ns.multi_step_tool = false %}
49
+ {%- set ns.last_query_index = index %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- endfor %}
53
+ {%- for message in messages %}
54
+ {%- set content = render_content(message.content, True) %}
55
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
57
+ {%- elif message.role == "assistant" %}
58
+ {%- set reasoning_content = '' %}
59
+ {%- if message.reasoning_content is string %}
60
+ {%- set reasoning_content = message.reasoning_content %}
61
+ {%- else %}
62
+ {%- if '</think>' in content %}
63
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
64
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- if loop.index0 > ns.last_query_index %}
68
+ {%- if loop.last or (not loop.last and reasoning_content) %}
69
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
70
+ {%- else %}
71
+ {{- '<|im_start|>' + message.role + '\n' + content }}
72
+ {%- endif %}
73
+ {%- else %}
74
+ {{- '<|im_start|>' + message.role + '\n' + content }}
75
+ {%- endif %}
76
+ {%- if message.tool_calls %}
77
+ {%- for tool_call in message.tool_calls %}
78
+ {%- if (loop.first and content) or (not loop.first) %}
79
+ {{- '\n' }}
80
+ {%- endif %}
81
+ {%- if tool_call.function %}
82
+ {%- set tool_call = tool_call.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>\n{"name": "' }}
85
+ {{- tool_call.name }}
86
+ {{- '", "arguments": ' }}
87
+ {%- if tool_call.arguments is string %}
88
+ {{- tool_call.arguments }}
89
+ {%- else %}
90
+ {{- tool_call.arguments | tojson }}
91
+ {%- endif %}
92
+ {{- '}\n</tool_call>' }}
93
+ {%- endfor %}
94
+ {%- endif %}
95
+ {{- '<|im_end|>\n' }}
96
+ {%- elif message.role == "tool" %}
97
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
98
+ {{- '<|im_start|>user' }}
99
+ {%- endif %}
100
+ {{- '\n<tool_response>\n' }}
101
+ {{- content }}
102
+ {{- '\n</tool_response>' }}
103
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
104
+ {{- '<|im_end|>\n' }}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- endfor %}
108
+ {%- if add_generation_prompt %}
109
+ {{- '<|im_start|>assistant\n' }}
110
+ {%- endif %}
ADEn-CFJ-KL0/checkpoint-200/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "image_token_id": 151655,
8
+ "model_type": "qwen3_vl",
9
+ "pad_token_id": 151643,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 151643,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 151645,
16
+ "head_dim": 128,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2560,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 9728,
21
+ "max_position_embeddings": 262144,
22
+ "model_type": "qwen3_vl_text",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 36,
25
+ "num_key_value_heads": 8,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_scaling": {
28
+ "mrope_interleaved": true,
29
+ "mrope_section": [
30
+ 24,
31
+ 20,
32
+ 20
33
+ ],
34
+ "rope_type": "default"
35
+ },
36
+ "rope_theta": 5000000,
37
+ "tie_word_embeddings": true,
38
+ "use_cache": true,
39
+ "vocab_size": 151936
40
+ },
41
+ "tie_word_embeddings": true,
42
+ "transformers_version": "4.57.6",
43
+ "use_cache": false,
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 5,
48
+ 11,
49
+ 17
50
+ ],
51
+ "depth": 24,
52
+ "dtype": "bfloat16",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1024,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 2560,
62
+ "patch_size": 16,
63
+ "spatial_merge_size": 2,
64
+ "temporal_patch_size": 2
65
+ },
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652
68
+ }
ADEn-CFJ-KL0/checkpoint-200/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.57.6"
12
+ }
ADEn-CFJ-KL0/checkpoint-200/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
ADEn-CFJ-KL0/checkpoint-200/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:91d76b83a1cbc3d707eb33feafa62637c36ef393eff0e83419d90528389aa4fb
3
+ size 4990497880
ADEn-CFJ-KL0/checkpoint-200/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ba1240eeadcc26ee083a723cff51f8fcd806394b6cef51cfec74443f66553106
3
+ size 3885221448
ADEn-CFJ-KL0/checkpoint-200/model.safetensors.index.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4437815808,
4
+ "total_size": 8875631616
5
+ },
6
+ "weight_map": {
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
97
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
405
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
406
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
408
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
409
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
410
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
411
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
412
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
413
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
414
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
415
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
416
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
417
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
418
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
420
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
421
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
422
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
423
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
424
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
425
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
426
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
427
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
428
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
429
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
432
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
433
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
438
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
439
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
440
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
441
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
444
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
445
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
446
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
447
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
448
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
449
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
450
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
451
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
452
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
453
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
456
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
457
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
458
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
459
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
460
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
461
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
462
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
463
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
464
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
465
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
466
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
468
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
469
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
470
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
471
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
472
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
473
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
474
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
475
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
476
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
482
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
483
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
484
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
485
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
486
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
487
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
488
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
489
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
490
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
492
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
493
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
494
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
495
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
496
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
497
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
498
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
499
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
500
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
501
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
502
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
504
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
505
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
506
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
507
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
508
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
509
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
510
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
511
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
512
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
513
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
514
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
515
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
516
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
517
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
518
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
519
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
520
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
521
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
522
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
523
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
524
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
525
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
526
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
527
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
528
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
529
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
530
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
531
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
532
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
533
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
534
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
535
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
536
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
537
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
538
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
539
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
540
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
541
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
542
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
543
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
544
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
545
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
546
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
547
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
548
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
549
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
550
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
551
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
552
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
553
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
554
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
555
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
556
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
557
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
558
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
559
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
560
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
561
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
562
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
563
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
564
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
565
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
566
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
567
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
568
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
569
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
570
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
571
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
572
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
573
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
574
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
575
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
576
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
577
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
578
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
579
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
580
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
581
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
582
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
583
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
584
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
585
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
586
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
587
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
588
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
589
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
590
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
591
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
592
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
593
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
594
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
595
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
596
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
597
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
598
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
599
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
600
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
601
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
602
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
603
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
604
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
605
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
606
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
607
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
608
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
609
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
610
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
611
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
612
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
613
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
614
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
615
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
616
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
617
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
618
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
619
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
620
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
621
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
622
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
623
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
624
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
625
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
626
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
627
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
628
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
629
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
630
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
631
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
632
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
633
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
634
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
635
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
636
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
637
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
638
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
639
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
640
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
641
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
642
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
643
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
644
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
645
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
646
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
647
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
648
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
649
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
650
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
651
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
652
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
653
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
654
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
655
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
656
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
657
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
658
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
659
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
660
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
661
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
662
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
663
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
664
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
665
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
666
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
667
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
668
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
669
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
670
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
671
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
672
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
673
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
674
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
675
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
676
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
677
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
678
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
679
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
680
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
681
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
682
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
683
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
684
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
685
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
686
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
687
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
688
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
689
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
690
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
691
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
692
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
693
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
694
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
695
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
696
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
697
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
698
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
699
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
700
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
701
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
702
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
703
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
704
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
705
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
706
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
707
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
708
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
709
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
710
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
711
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
712
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
713
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
714
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
715
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
716
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
717
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
718
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
719
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
720
+ }
721
+ }
ADEn-CFJ-KL0/checkpoint-200/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:599bf39ba7128d209d0ddaab6b4b1b895bb0123a55d80c5cd25dd513e318c7f5
3
+ size 16090226537
ADEn-CFJ-KL0/checkpoint-200/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:ecaf60ba5733e80201a5224a9c64ee48f1639ab2ab42581f6fbef59e351e65bb
3
+ size 14853
ADEn-CFJ-KL0/checkpoint-200/rng_state_1.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5a6e6cf923f6b7e83fbcc304477d16377d484fd1530181bd4340f01066ce8954
3
+ size 14981
ADEn-CFJ-KL0/checkpoint-200/scheduler.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:58f22504a9a9649f4dc5ccb3e17d22d4cecfea1c126fee54296e90a97f833ed1
3
+ size 1465
ADEn-CFJ-KL0/checkpoint-200/special_tokens_map.json ADDED
@@ -0,0 +1,31 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "additional_special_tokens": [
3
+ "<|im_start|>",
4
+ "<|im_end|>",
5
+ "<|object_ref_start|>",
6
+ "<|object_ref_end|>",
7
+ "<|box_start|>",
8
+ "<|box_end|>",
9
+ "<|quad_start|>",
10
+ "<|quad_end|>",
11
+ "<|vision_start|>",
12
+ "<|vision_end|>",
13
+ "<|vision_pad|>",
14
+ "<|image_pad|>",
15
+ "<|video_pad|>"
16
+ ],
17
+ "eos_token": {
18
+ "content": "<|im_end|>",
19
+ "lstrip": false,
20
+ "normalized": false,
21
+ "rstrip": false,
22
+ "single_word": false
23
+ },
24
+ "pad_token": {
25
+ "content": "<|endoftext|>",
26
+ "lstrip": false,
27
+ "normalized": false,
28
+ "rstrip": false,
29
+ "single_word": false
30
+ }
31
+ }
ADEn-CFJ-KL0/checkpoint-200/tokenizer.json ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:21f6994642cfbd8473e43b4fae1d60d4a953aea1419dc28b4ae3f41778cd0924
3
+ size 11422922
ADEn-CFJ-KL0/checkpoint-200/tokenizer_config.json ADDED
@@ -0,0 +1,244 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "add_bos_token": false,
3
+ "add_prefix_space": false,
4
+ "added_tokens_decoder": {
5
+ "151643": {
6
+ "content": "<|endoftext|>",
7
+ "lstrip": false,
8
+ "normalized": false,
9
+ "rstrip": false,
10
+ "single_word": false,
11
+ "special": true
12
+ },
13
+ "151644": {
14
+ "content": "<|im_start|>",
15
+ "lstrip": false,
16
+ "normalized": false,
17
+ "rstrip": false,
18
+ "single_word": false,
19
+ "special": true
20
+ },
21
+ "151645": {
22
+ "content": "<|im_end|>",
23
+ "lstrip": false,
24
+ "normalized": false,
25
+ "rstrip": false,
26
+ "single_word": false,
27
+ "special": true
28
+ },
29
+ "151646": {
30
+ "content": "<|object_ref_start|>",
31
+ "lstrip": false,
32
+ "normalized": false,
33
+ "rstrip": false,
34
+ "single_word": false,
35
+ "special": true
36
+ },
37
+ "151647": {
38
+ "content": "<|object_ref_end|>",
39
+ "lstrip": false,
40
+ "normalized": false,
41
+ "rstrip": false,
42
+ "single_word": false,
43
+ "special": true
44
+ },
45
+ "151648": {
46
+ "content": "<|box_start|>",
47
+ "lstrip": false,
48
+ "normalized": false,
49
+ "rstrip": false,
50
+ "single_word": false,
51
+ "special": true
52
+ },
53
+ "151649": {
54
+ "content": "<|box_end|>",
55
+ "lstrip": false,
56
+ "normalized": false,
57
+ "rstrip": false,
58
+ "single_word": false,
59
+ "special": true
60
+ },
61
+ "151650": {
62
+ "content": "<|quad_start|>",
63
+ "lstrip": false,
64
+ "normalized": false,
65
+ "rstrip": false,
66
+ "single_word": false,
67
+ "special": true
68
+ },
69
+ "151651": {
70
+ "content": "<|quad_end|>",
71
+ "lstrip": false,
72
+ "normalized": false,
73
+ "rstrip": false,
74
+ "single_word": false,
75
+ "special": true
76
+ },
77
+ "151652": {
78
+ "content": "<|vision_start|>",
79
+ "lstrip": false,
80
+ "normalized": false,
81
+ "rstrip": false,
82
+ "single_word": false,
83
+ "special": true
84
+ },
85
+ "151653": {
86
+ "content": "<|vision_end|>",
87
+ "lstrip": false,
88
+ "normalized": false,
89
+ "rstrip": false,
90
+ "single_word": false,
91
+ "special": true
92
+ },
93
+ "151654": {
94
+ "content": "<|vision_pad|>",
95
+ "lstrip": false,
96
+ "normalized": false,
97
+ "rstrip": false,
98
+ "single_word": false,
99
+ "special": true
100
+ },
101
+ "151655": {
102
+ "content": "<|image_pad|>",
103
+ "lstrip": false,
104
+ "normalized": false,
105
+ "rstrip": false,
106
+ "single_word": false,
107
+ "special": true
108
+ },
109
+ "151656": {
110
+ "content": "<|video_pad|>",
111
+ "lstrip": false,
112
+ "normalized": false,
113
+ "rstrip": false,
114
+ "single_word": false,
115
+ "special": true
116
+ },
117
+ "151657": {
118
+ "content": "<tool_call>",
119
+ "lstrip": false,
120
+ "normalized": false,
121
+ "rstrip": false,
122
+ "single_word": false,
123
+ "special": false
124
+ },
125
+ "151658": {
126
+ "content": "</tool_call>",
127
+ "lstrip": false,
128
+ "normalized": false,
129
+ "rstrip": false,
130
+ "single_word": false,
131
+ "special": false
132
+ },
133
+ "151659": {
134
+ "content": "<|fim_prefix|>",
135
+ "lstrip": false,
136
+ "normalized": false,
137
+ "rstrip": false,
138
+ "single_word": false,
139
+ "special": false
140
+ },
141
+ "151660": {
142
+ "content": "<|fim_middle|>",
143
+ "lstrip": false,
144
+ "normalized": false,
145
+ "rstrip": false,
146
+ "single_word": false,
147
+ "special": false
148
+ },
149
+ "151661": {
150
+ "content": "<|fim_suffix|>",
151
+ "lstrip": false,
152
+ "normalized": false,
153
+ "rstrip": false,
154
+ "single_word": false,
155
+ "special": false
156
+ },
157
+ "151662": {
158
+ "content": "<|fim_pad|>",
159
+ "lstrip": false,
160
+ "normalized": false,
161
+ "rstrip": false,
162
+ "single_word": false,
163
+ "special": false
164
+ },
165
+ "151663": {
166
+ "content": "<|repo_name|>",
167
+ "lstrip": false,
168
+ "normalized": false,
169
+ "rstrip": false,
170
+ "single_word": false,
171
+ "special": false
172
+ },
173
+ "151664": {
174
+ "content": "<|file_sep|>",
175
+ "lstrip": false,
176
+ "normalized": false,
177
+ "rstrip": false,
178
+ "single_word": false,
179
+ "special": false
180
+ },
181
+ "151665": {
182
+ "content": "<tool_response>",
183
+ "lstrip": false,
184
+ "normalized": false,
185
+ "rstrip": false,
186
+ "single_word": false,
187
+ "special": false
188
+ },
189
+ "151666": {
190
+ "content": "</tool_response>",
191
+ "lstrip": false,
192
+ "normalized": false,
193
+ "rstrip": false,
194
+ "single_word": false,
195
+ "special": false
196
+ },
197
+ "151667": {
198
+ "content": "<think>",
199
+ "lstrip": false,
200
+ "normalized": false,
201
+ "rstrip": false,
202
+ "single_word": false,
203
+ "special": false
204
+ },
205
+ "151668": {
206
+ "content": "</think>",
207
+ "lstrip": false,
208
+ "normalized": false,
209
+ "rstrip": false,
210
+ "single_word": false,
211
+ "special": false
212
+ }
213
+ },
214
+ "additional_special_tokens": [
215
+ "<|im_start|>",
216
+ "<|im_end|>",
217
+ "<|object_ref_start|>",
218
+ "<|object_ref_end|>",
219
+ "<|box_start|>",
220
+ "<|box_end|>",
221
+ "<|quad_start|>",
222
+ "<|quad_end|>",
223
+ "<|vision_start|>",
224
+ "<|vision_end|>",
225
+ "<|vision_pad|>",
226
+ "<|image_pad|>",
227
+ "<|video_pad|>"
228
+ ],
229
+ "bos_token": null,
230
+ "clean_up_tokenization_spaces": false,
231
+ "eos_token": "<|im_end|>",
232
+ "errors": "replace",
233
+ "extra_special_tokens": {},
234
+ "max_length": null,
235
+ "model_max_length": 262144,
236
+ "pad_to_multiple_of": null,
237
+ "pad_token": "<|endoftext|>",
238
+ "pad_token_type_id": 0,
239
+ "padding_side": "left",
240
+ "processor_class": "Qwen3VLProcessor",
241
+ "split_special_tokens": false,
242
+ "tokenizer_class": "Qwen2Tokenizer",
243
+ "unk_token": null
244
+ }
ADEn-CFJ-KL0/checkpoint-200/trainer_state.json ADDED
@@ -0,0 +1,672 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "best_global_step": null,
3
+ "best_metric": null,
4
+ "best_model_checkpoint": null,
5
+ "epoch": 0.042863266180882986,
6
+ "eval_steps": 72,
7
+ "global_step": 200,
8
+ "is_hyper_param_search": false,
9
+ "is_local_process_zero": true,
10
+ "is_world_process_zero": true,
11
+ "log_history": [
12
+ {
13
+ "clip_ratio/high_max": 0.0,
14
+ "clip_ratio/high_mean": 0.0,
15
+ "clip_ratio/low_mean": 0.0,
16
+ "clip_ratio/low_min": 0.0,
17
+ "clip_ratio/region_mean": 0.0,
18
+ "completions/clipped_ratio": 0.0,
19
+ "completions/max_length": 722.4,
20
+ "completions/max_terminated_length": 722.4,
21
+ "completions/mean_length": 687.3479309082031,
22
+ "completions/mean_terminated_length": 687.3479309082031,
23
+ "completions/min_length": 596.1,
24
+ "completions/min_terminated_length": 596.1,
25
+ "entropy": 0.5129013667503993,
26
+ "epoch": 0.0021431633090441492,
27
+ "frac_reward_zero_std": 0.0,
28
+ "grad_norm": 0.9375,
29
+ "learning_rate": 9.691780821917808e-07,
30
+ "loss": -0.005,
31
+ "num_tokens": 995975.0,
32
+ "reward": -0.06374586373567581,
33
+ "reward_std": 0.22546745985746383,
34
+ "rewards/ADEnReward/mean": 0.016389049030840395,
35
+ "rewards/ADEnReward/std": 0.048161597922444344,
36
+ "rewards/CounterfactualJustificationReward/mean": -0.08013491020537913,
37
+ "rewards/CounterfactualJustificationReward/std": 0.2300958290696144,
38
+ "step": 10,
39
+ "step_time": 266.3497134976002
40
+ },
41
+ {
42
+ "clip_ratio/high_max": 0.0,
43
+ "clip_ratio/high_mean": 0.0,
44
+ "clip_ratio/low_mean": 0.0,
45
+ "clip_ratio/low_min": 0.0,
46
+ "clip_ratio/region_mean": 0.0,
47
+ "completions/clipped_ratio": 0.0,
48
+ "completions/max_length": 725.4,
49
+ "completions/max_terminated_length": 725.4,
50
+ "completions/mean_length": 689.1125244140625,
51
+ "completions/mean_terminated_length": 689.1125244140625,
52
+ "completions/min_length": 652.9,
53
+ "completions/min_terminated_length": 652.9,
54
+ "entropy": 0.5154734035332997,
55
+ "epoch": 0.0042863266180882984,
56
+ "frac_reward_zero_std": 0.0,
57
+ "grad_norm": 0.87890625,
58
+ "learning_rate": 9.349315068493149e-07,
59
+ "loss": 0.0001,
60
+ "num_tokens": 1992877.0,
61
+ "reward": -0.05411523887887597,
62
+ "reward_std": 0.21374744027853013,
63
+ "rewards/ADEnReward/mean": 0.02242780737578869,
64
+ "rewards/ADEnReward/std": 0.05705951061099768,
65
+ "rewards/CounterfactualJustificationReward/mean": -0.07654304374009371,
66
+ "rewards/CounterfactualJustificationReward/std": 0.2092343047261238,
67
+ "step": 20,
68
+ "step_time": 269.486055393095
69
+ },
70
+ {
71
+ "clip_ratio/high_max": 0.0,
72
+ "clip_ratio/high_mean": 0.0,
73
+ "clip_ratio/low_mean": 0.0,
74
+ "clip_ratio/low_min": 0.0,
75
+ "clip_ratio/region_mean": 0.0,
76
+ "completions/clipped_ratio": 0.002083333395421505,
77
+ "completions/max_length": 756.0,
78
+ "completions/max_terminated_length": 727.1,
79
+ "completions/mean_length": 688.0000183105469,
80
+ "completions/mean_terminated_length": 687.2961120605469,
81
+ "completions/min_length": 652.2,
82
+ "completions/min_terminated_length": 652.2,
83
+ "entropy": 0.5114999602238337,
84
+ "epoch": 0.006429489927132447,
85
+ "frac_reward_zero_std": 0.0,
86
+ "grad_norm": 0.890625,
87
+ "learning_rate": 9.006849315068494e-07,
88
+ "loss": 0.0042,
89
+ "num_tokens": 2988621.0,
90
+ "reward": -0.07193327061831951,
91
+ "reward_std": 0.23947951942682266,
92
+ "rewards/ADEnReward/mean": 0.018894296162761746,
93
+ "rewards/ADEnReward/std": 0.05166068505495787,
94
+ "rewards/CounterfactualJustificationReward/mean": -0.09082756340503692,
95
+ "rewards/CounterfactualJustificationReward/std": 0.23909800499677658,
96
+ "step": 30,
97
+ "step_time": 276.6699794655084
98
+ },
99
+ {
100
+ "clip_ratio/high_max": 0.0,
101
+ "clip_ratio/high_mean": 0.0,
102
+ "clip_ratio/low_mean": 0.0,
103
+ "clip_ratio/low_min": 0.0,
104
+ "clip_ratio/region_mean": 0.0,
105
+ "completions/clipped_ratio": 0.0,
106
+ "completions/max_length": 728.7,
107
+ "completions/max_terminated_length": 728.7,
108
+ "completions/mean_length": 691.1791931152344,
109
+ "completions/mean_terminated_length": 691.1791931152344,
110
+ "completions/min_length": 655.7,
111
+ "completions/min_terminated_length": 655.7,
112
+ "entropy": 0.5192137628793716,
113
+ "epoch": 0.008572653236176597,
114
+ "frac_reward_zero_std": 0.0,
115
+ "grad_norm": 1.03125,
116
+ "learning_rate": 8.664383561643836e-07,
117
+ "loss": 0.0008,
118
+ "num_tokens": 3986499.0,
119
+ "reward": -0.03571146372705698,
120
+ "reward_std": 0.24846212714910507,
121
+ "rewards/ADEnReward/mean": 0.02276311726309359,
122
+ "rewards/ADEnReward/std": 0.06564843580126763,
123
+ "rewards/CounterfactualJustificationReward/mean": -0.05847458196803927,
124
+ "rewards/CounterfactualJustificationReward/std": 0.23850561082363128,
125
+ "step": 40,
126
+ "step_time": 270.7083416894951
127
+ },
128
+ {
129
+ "clip_ratio/high_max": 0.0,
130
+ "clip_ratio/high_mean": 0.0,
131
+ "clip_ratio/low_mean": 0.0,
132
+ "clip_ratio/low_min": 0.0,
133
+ "clip_ratio/region_mean": 0.0,
134
+ "completions/clipped_ratio": 0.0,
135
+ "completions/max_length": 722.6,
136
+ "completions/max_terminated_length": 722.6,
137
+ "completions/mean_length": 686.5562683105469,
138
+ "completions/mean_terminated_length": 686.5562683105469,
139
+ "completions/min_length": 654.7,
140
+ "completions/min_terminated_length": 654.7,
141
+ "entropy": 0.5242228974898656,
142
+ "epoch": 0.010715816545220747,
143
+ "frac_reward_zero_std": 0.0,
144
+ "grad_norm": 0.89453125,
145
+ "learning_rate": 8.321917808219178e-07,
146
+ "loss": 0.0024,
147
+ "num_tokens": 4981982.0,
148
+ "reward": -0.037678991351276635,
149
+ "reward_std": 0.23401633203029631,
150
+ "rewards/ADEnReward/mean": 0.023655857401899995,
151
+ "rewards/ADEnReward/std": 0.06490156231448055,
152
+ "rewards/CounterfactualJustificationReward/mean": -0.06133484859019518,
153
+ "rewards/CounterfactualJustificationReward/std": 0.22413837760686875,
154
+ "step": 50,
155
+ "step_time": 271.4957699022081
156
+ },
157
+ {
158
+ "clip_ratio/high_max": 0.0,
159
+ "clip_ratio/high_mean": 0.0,
160
+ "clip_ratio/low_mean": 0.0,
161
+ "clip_ratio/low_min": 0.0,
162
+ "clip_ratio/region_mean": 0.0,
163
+ "completions/clipped_ratio": 0.0,
164
+ "completions/max_length": 729.0,
165
+ "completions/max_terminated_length": 729.0,
166
+ "completions/mean_length": 688.4916870117188,
167
+ "completions/mean_terminated_length": 688.4916870117188,
168
+ "completions/min_length": 654.9,
169
+ "completions/min_terminated_length": 654.9,
170
+ "entropy": 0.5326574305693309,
171
+ "epoch": 0.012858979854264894,
172
+ "frac_reward_zero_std": 0.0,
173
+ "grad_norm": 0.87109375,
174
+ "learning_rate": 7.97945205479452e-07,
175
+ "loss": -0.0003,
176
+ "num_tokens": 5978394.0,
177
+ "reward": -0.05084102489054203,
178
+ "reward_std": 0.2377728059887886,
179
+ "rewards/ADEnReward/mean": 0.020620170864276588,
180
+ "rewards/ADEnReward/std": 0.062224847916513684,
181
+ "rewards/CounterfactualJustificationReward/mean": -0.07146119233220816,
182
+ "rewards/CounterfactualJustificationReward/std": 0.23566005975008011,
183
+ "step": 60,
184
+ "step_time": 269.84039734689867
185
+ },
186
+ {
187
+ "clip_ratio/high_max": 0.0,
188
+ "clip_ratio/high_mean": 0.0,
189
+ "clip_ratio/low_mean": 0.0,
190
+ "clip_ratio/low_min": 0.0,
191
+ "clip_ratio/region_mean": 0.0,
192
+ "completions/clipped_ratio": 0.0,
193
+ "completions/max_length": 723.0,
194
+ "completions/max_terminated_length": 723.0,
195
+ "completions/mean_length": 689.7208557128906,
196
+ "completions/mean_terminated_length": 689.7208557128906,
197
+ "completions/min_length": 653.6,
198
+ "completions/min_terminated_length": 653.6,
199
+ "entropy": 0.5156665503978729,
200
+ "epoch": 0.015002143163309044,
201
+ "frac_reward_zero_std": 0.0,
202
+ "grad_norm": 1.078125,
203
+ "learning_rate": 7.636986301369863e-07,
204
+ "loss": -0.0011,
205
+ "num_tokens": 6975652.0,
206
+ "reward": -0.007650468964129686,
207
+ "reward_std": 0.24781250208616257,
208
+ "rewards/ADEnReward/mean": 0.023274474567733704,
209
+ "rewards/ADEnReward/std": 0.058971316739916804,
210
+ "rewards/CounterfactualJustificationReward/mean": -0.03092494057491422,
211
+ "rewards/CounterfactualJustificationReward/std": 0.250348636507988,
212
+ "step": 70,
213
+ "step_time": 274.2808645738929
214
+ },
215
+ {
216
+ "epoch": 0.015430775825117874,
217
+ "eval_clip_ratio/high_max": 0.0,
218
+ "eval_clip_ratio/high_mean": 0.0,
219
+ "eval_clip_ratio/low_mean": 0.0,
220
+ "eval_clip_ratio/low_min": 0.0,
221
+ "eval_clip_ratio/region_mean": 0.0,
222
+ "eval_completions/clipped_ratio": 0.0003125,
223
+ "eval_completions/max_length": 718.315,
224
+ "eval_completions/max_terminated_length": 716.775,
225
+ "eval_completions/mean_length": 691.1975,
226
+ "eval_completions/mean_terminated_length": 691.0926043701172,
227
+ "eval_completions/min_length": 667.385,
228
+ "eval_completions/min_terminated_length": 667.385,
229
+ "eval_entropy": 0.5353066678345203,
230
+ "eval_frac_reward_zero_std": 0.0,
231
+ "eval_loss": 0.0011824100511148572,
232
+ "eval_num_tokens": 7174184.0,
233
+ "eval_reward": -0.011725269807502627,
234
+ "eval_reward_std": 0.2379829413443804,
235
+ "eval_rewards/ADEnReward/mean": 0.01436133997845951,
236
+ "eval_rewards/ADEnReward/std": 0.031373489485568846,
237
+ "eval_rewards/CounterfactualJustificationReward/mean": -0.026086609871126713,
238
+ "eval_rewards/CounterfactualJustificationReward/std": 0.2323593620210886,
239
+ "eval_runtime": 9510.9089,
240
+ "eval_samples_per_second": 0.021,
241
+ "eval_steps_per_second": 0.001,
242
+ "step": 72
243
+ },
244
+ {
245
+ "clip_ratio/high_max": 0.0,
246
+ "clip_ratio/high_mean": 0.0,
247
+ "clip_ratio/low_mean": 0.0,
248
+ "clip_ratio/low_min": 0.0,
249
+ "clip_ratio/region_mean": 0.0,
250
+ "completions/clipped_ratio": 0.0,
251
+ "completions/max_length": 722.3,
252
+ "completions/max_terminated_length": 722.3,
253
+ "completions/mean_length": 683.2312805175782,
254
+ "completions/mean_terminated_length": 683.2312805175782,
255
+ "completions/min_length": 597.0,
256
+ "completions/min_terminated_length": 597.0,
257
+ "entropy": 0.5130097369352976,
258
+ "epoch": 0.017145306472353194,
259
+ "frac_reward_zero_std": 0.0,
260
+ "grad_norm": 0.91796875,
261
+ "learning_rate": 7.294520547945205e-07,
262
+ "loss": -0.004,
263
+ "num_tokens": 7969155.0,
264
+ "reward": -0.0016561332624405623,
265
+ "reward_std": 0.22166914492845535,
266
+ "rewards/ADEnReward/mean": 0.02527421610429883,
267
+ "rewards/ADEnReward/std": 0.06894388236105442,
268
+ "rewards/CounterfactualJustificationReward/mean": -0.026930347364395858,
269
+ "rewards/CounterfactualJustificationReward/std": 0.22469179928302765,
270
+ "step": 80,
271
+ "step_time": 271.889700404898
272
+ },
273
+ {
274
+ "clip_ratio/high_max": 0.0,
275
+ "clip_ratio/high_mean": 0.0,
276
+ "clip_ratio/low_mean": 0.0,
277
+ "clip_ratio/low_min": 0.0,
278
+ "clip_ratio/region_mean": 0.0,
279
+ "completions/clipped_ratio": 0.002083333395421505,
280
+ "completions/max_length": 754.8,
281
+ "completions/max_terminated_length": 724.9,
282
+ "completions/mean_length": 691.5583557128906,
283
+ "completions/mean_terminated_length": 690.8669494628906,
284
+ "completions/min_length": 660.1,
285
+ "completions/min_terminated_length": 660.1,
286
+ "entropy": 0.5074795544147491,
287
+ "epoch": 0.01928846978139734,
288
+ "frac_reward_zero_std": 0.0,
289
+ "grad_norm": 1.0390625,
290
+ "learning_rate": 6.952054794520548e-07,
291
+ "loss": 0.0018,
292
+ "num_tokens": 8967791.0,
293
+ "reward": 0.026898569357581437,
294
+ "reward_std": 0.2355131596326828,
295
+ "rewards/ADEnReward/mean": 0.03706806637346745,
296
+ "rewards/ADEnReward/std": 0.08285447619855404,
297
+ "rewards/CounterfactualJustificationReward/mean": -0.010169497784227132,
298
+ "rewards/CounterfactualJustificationReward/std": 0.21885453909635544,
299
+ "step": 90,
300
+ "step_time": 270.5311606264906
301
+ },
302
+ {
303
+ "clip_ratio/high_max": 0.0,
304
+ "clip_ratio/high_mean": 0.0,
305
+ "clip_ratio/low_mean": 0.0,
306
+ "clip_ratio/low_min": 0.0,
307
+ "clip_ratio/region_mean": 0.0,
308
+ "completions/clipped_ratio": 0.0,
309
+ "completions/max_length": 723.9,
310
+ "completions/max_terminated_length": 723.9,
311
+ "completions/mean_length": 688.6875183105469,
312
+ "completions/mean_terminated_length": 688.6875183105469,
313
+ "completions/min_length": 654.3,
314
+ "completions/min_terminated_length": 654.3,
315
+ "entropy": 0.522646211584409,
316
+ "epoch": 0.021431633090441493,
317
+ "frac_reward_zero_std": 0.0,
318
+ "grad_norm": 0.93359375,
319
+ "learning_rate": 6.60958904109589e-07,
320
+ "loss": 0.0008,
321
+ "num_tokens": 9964505.0,
322
+ "reward": -0.00860080262646079,
323
+ "reward_std": 0.241253000497818,
324
+ "rewards/ADEnReward/mean": 0.029191052657552063,
325
+ "rewards/ADEnReward/std": 0.06871706424281002,
326
+ "rewards/CounterfactualJustificationReward/mean": -0.03779185602907091,
327
+ "rewards/CounterfactualJustificationReward/std": 0.2387075498700142,
328
+ "step": 100,
329
+ "step_time": 268.47685881000945
330
+ },
331
+ {
332
+ "clip_ratio/high_max": 0.0,
333
+ "clip_ratio/high_mean": 0.0,
334
+ "clip_ratio/low_mean": 0.0,
335
+ "clip_ratio/low_min": 0.0,
336
+ "clip_ratio/region_mean": 0.0,
337
+ "completions/clipped_ratio": 0.0,
338
+ "completions/max_length": 725.7,
339
+ "completions/max_terminated_length": 725.7,
340
+ "completions/mean_length": 689.8333557128906,
341
+ "completions/mean_terminated_length": 689.8333557128906,
342
+ "completions/min_length": 656.9,
343
+ "completions/min_terminated_length": 656.9,
344
+ "entropy": 0.525945125023524,
345
+ "epoch": 0.02357479639948564,
346
+ "frac_reward_zero_std": 0.0,
347
+ "grad_norm": 0.859375,
348
+ "learning_rate": 6.267123287671232e-07,
349
+ "loss": 0.0003,
350
+ "num_tokens": 10962169.0,
351
+ "reward": -0.03699035234749317,
352
+ "reward_std": 0.24349293857812881,
353
+ "rewards/ADEnReward/mean": 0.019172591564711183,
354
+ "rewards/ADEnReward/std": 0.047863338817842306,
355
+ "rewards/CounterfactualJustificationReward/mean": -0.05616294424980879,
356
+ "rewards/CounterfactualJustificationReward/std": 0.24668247550725936,
357
+ "step": 110,
358
+ "step_time": 266.4469289040979
359
+ },
360
+ {
361
+ "clip_ratio/high_max": 0.0,
362
+ "clip_ratio/high_mean": 0.0,
363
+ "clip_ratio/low_mean": 0.0,
364
+ "clip_ratio/low_min": 0.0,
365
+ "clip_ratio/region_mean": 0.0,
366
+ "completions/clipped_ratio": 0.0,
367
+ "completions/max_length": 733.3,
368
+ "completions/max_terminated_length": 733.3,
369
+ "completions/mean_length": 685.0000183105469,
370
+ "completions/mean_terminated_length": 685.0000183105469,
371
+ "completions/min_length": 649.2,
372
+ "completions/min_terminated_length": 649.2,
373
+ "entropy": 0.49605511824289955,
374
+ "epoch": 0.02571795970852979,
375
+ "frac_reward_zero_std": 0.0,
376
+ "grad_norm": 0.94140625,
377
+ "learning_rate": 5.924657534246575e-07,
378
+ "loss": 0.0006,
379
+ "num_tokens": 11956169.0,
380
+ "reward": 0.0007648288039490581,
381
+ "reward_std": 0.2499717503786087,
382
+ "rewards/ADEnReward/mean": 0.02746972357563209,
383
+ "rewards/ADEnReward/std": 0.06973316624062136,
384
+ "rewards/CounterfactualJustificationReward/mean": -0.026704895636066796,
385
+ "rewards/CounterfactualJustificationReward/std": 0.24132088720798492,
386
+ "step": 120,
387
+ "step_time": 273.5362445599982
388
+ },
389
+ {
390
+ "clip_ratio/high_max": 0.0,
391
+ "clip_ratio/high_mean": 0.0,
392
+ "clip_ratio/low_mean": 0.0,
393
+ "clip_ratio/low_min": 0.0,
394
+ "clip_ratio/region_mean": 0.0,
395
+ "completions/clipped_ratio": 0.0,
396
+ "completions/max_length": 722.9,
397
+ "completions/max_terminated_length": 722.9,
398
+ "completions/mean_length": 687.4541870117188,
399
+ "completions/mean_terminated_length": 687.4541870117188,
400
+ "completions/min_length": 656.3,
401
+ "completions/min_terminated_length": 656.3,
402
+ "entropy": 0.5190879285335541,
403
+ "epoch": 0.02786112301757394,
404
+ "frac_reward_zero_std": 0.0,
405
+ "grad_norm": 0.94921875,
406
+ "learning_rate": 5.582191780821918e-07,
407
+ "loss": 0.0013,
408
+ "num_tokens": 12951923.0,
409
+ "reward": 0.002823332604020834,
410
+ "reward_std": 0.2441198468208313,
411
+ "rewards/ADEnReward/mean": 0.022288725478574634,
412
+ "rewards/ADEnReward/std": 0.05904417345300317,
413
+ "rewards/CounterfactualJustificationReward/mean": -0.019465393107384443,
414
+ "rewards/CounterfactualJustificationReward/std": 0.24469832181930543,
415
+ "step": 130,
416
+ "step_time": 271.9160646090953
417
+ },
418
+ {
419
+ "clip_ratio/high_max": 0.0,
420
+ "clip_ratio/high_mean": 0.0,
421
+ "clip_ratio/low_mean": 0.0,
422
+ "clip_ratio/low_min": 0.0,
423
+ "clip_ratio/region_mean": 0.0,
424
+ "completions/clipped_ratio": 0.0,
425
+ "completions/max_length": 724.5,
426
+ "completions/max_terminated_length": 724.5,
427
+ "completions/mean_length": 689.3708557128906,
428
+ "completions/mean_terminated_length": 689.3708557128906,
429
+ "completions/min_length": 657.9,
430
+ "completions/min_terminated_length": 657.9,
431
+ "entropy": 0.5134656935930252,
432
+ "epoch": 0.03000428632661809,
433
+ "frac_reward_zero_std": 0.0,
434
+ "grad_norm": 0.859375,
435
+ "learning_rate": 5.23972602739726e-07,
436
+ "loss": 0.0002,
437
+ "num_tokens": 13949093.0,
438
+ "reward": 0.01638533966615796,
439
+ "reward_std": 0.2241854265332222,
440
+ "rewards/ADEnReward/mean": 0.025057854782789945,
441
+ "rewards/ADEnReward/std": 0.06769129764288664,
442
+ "rewards/CounterfactualJustificationReward/mean": -0.008672515908256174,
443
+ "rewards/CounterfactualJustificationReward/std": 0.22195084691047667,
444
+ "step": 140,
445
+ "step_time": 270.3432995792915
446
+ },
447
+ {
448
+ "epoch": 0.030861551650235748,
449
+ "eval_clip_ratio/high_max": 0.0,
450
+ "eval_clip_ratio/high_mean": 0.0,
451
+ "eval_clip_ratio/low_mean": 0.0,
452
+ "eval_clip_ratio/low_min": 0.0,
453
+ "eval_clip_ratio/region_mean": 0.0,
454
+ "eval_completions/clipped_ratio": 0.0003125,
455
+ "eval_completions/max_length": 719.13,
456
+ "eval_completions/max_terminated_length": 717.55,
457
+ "eval_completions/mean_length": 691.2096875,
458
+ "eval_completions/mean_terminated_length": 691.1000003051757,
459
+ "eval_completions/min_length": 666.93,
460
+ "eval_completions/min_terminated_length": 666.93,
461
+ "eval_entropy": 0.5347150683403015,
462
+ "eval_frac_reward_zero_std": 0.0,
463
+ "eval_loss": 0.0016415045829489827,
464
+ "eval_num_tokens": 14347025.0,
465
+ "eval_reward": 0.004477454829029739,
466
+ "eval_reward_std": 0.2351816064864397,
467
+ "eval_rewards/ADEnReward/mean": 0.012894519351566451,
468
+ "eval_rewards/ADEnReward/std": 0.027551153795853888,
469
+ "eval_rewards/CounterfactualJustificationReward/mean": -0.00841706475475803,
470
+ "eval_rewards/CounterfactualJustificationReward/std": 0.2298748667165637,
471
+ "eval_runtime": 9527.5151,
472
+ "eval_samples_per_second": 0.021,
473
+ "eval_steps_per_second": 0.001,
474
+ "step": 144
475
+ },
476
+ {
477
+ "clip_ratio/high_max": 0.0,
478
+ "clip_ratio/high_mean": 0.0,
479
+ "clip_ratio/low_mean": 0.0,
480
+ "clip_ratio/low_min": 0.0,
481
+ "clip_ratio/region_mean": 0.0,
482
+ "completions/clipped_ratio": 0.0,
483
+ "completions/max_length": 725.1,
484
+ "completions/max_terminated_length": 725.1,
485
+ "completions/mean_length": 686.439599609375,
486
+ "completions/mean_terminated_length": 686.439599609375,
487
+ "completions/min_length": 654.8,
488
+ "completions/min_terminated_length": 654.8,
489
+ "entropy": 0.5236856470505397,
490
+ "epoch": 0.03214744963566224,
491
+ "frac_reward_zero_std": 0.0,
492
+ "grad_norm": 0.8359375,
493
+ "learning_rate": 4.897260273972603e-07,
494
+ "loss": 0.0001,
495
+ "num_tokens": 14944632.0,
496
+ "reward": 0.02295272913761437,
497
+ "reward_std": 0.22453167736530305,
498
+ "rewards/ADEnReward/mean": 0.022027627262286843,
499
+ "rewards/ADEnReward/std": 0.058279201621189713,
500
+ "rewards/CounterfactualJustificationReward/mean": 0.0009251011069864035,
501
+ "rewards/CounterfactualJustificationReward/std": 0.2218881830573082,
502
+ "step": 150,
503
+ "step_time": 273.3936970937095
504
+ },
505
+ {
506
+ "clip_ratio/high_max": 0.0,
507
+ "clip_ratio/high_mean": 0.0,
508
+ "clip_ratio/low_mean": 0.0,
509
+ "clip_ratio/low_min": 0.0,
510
+ "clip_ratio/region_mean": 0.0,
511
+ "completions/clipped_ratio": 0.0,
512
+ "completions/max_length": 726.0,
513
+ "completions/max_terminated_length": 726.0,
514
+ "completions/mean_length": 688.1125244140625,
515
+ "completions/mean_terminated_length": 688.1125244140625,
516
+ "completions/min_length": 650.0,
517
+ "completions/min_terminated_length": 650.0,
518
+ "entropy": 0.5077318588892619,
519
+ "epoch": 0.03429061294470639,
520
+ "frac_reward_zero_std": 0.0,
521
+ "grad_norm": 0.87890625,
522
+ "learning_rate": 4.554794520547945e-07,
523
+ "loss": 0.0003,
524
+ "num_tokens": 15941102.0,
525
+ "reward": 0.04326854348182678,
526
+ "reward_std": 0.23098409920930862,
527
+ "rewards/ADEnReward/mean": 0.019084953516721726,
528
+ "rewards/ADEnReward/std": 0.05326344482600689,
529
+ "rewards/CounterfactualJustificationReward/mean": 0.024183587031438948,
530
+ "rewards/CounterfactualJustificationReward/std": 0.23466062545776367,
531
+ "step": 160,
532
+ "step_time": 272.7039299202967
533
+ },
534
+ {
535
+ "clip_ratio/high_max": 0.0,
536
+ "clip_ratio/high_mean": 0.0,
537
+ "clip_ratio/low_mean": 0.0,
538
+ "clip_ratio/low_min": 0.0,
539
+ "clip_ratio/region_mean": 0.0,
540
+ "completions/clipped_ratio": 0.0,
541
+ "completions/max_length": 728.8,
542
+ "completions/max_terminated_length": 728.8,
543
+ "completions/mean_length": 688.8229370117188,
544
+ "completions/mean_terminated_length": 688.8229370117188,
545
+ "completions/min_length": 653.0,
546
+ "completions/min_terminated_length": 653.0,
547
+ "entropy": 0.5165835758050282,
548
+ "epoch": 0.036433776253750536,
549
+ "frac_reward_zero_std": 0.0,
550
+ "grad_norm": 0.9296875,
551
+ "learning_rate": 4.212328767123288e-07,
552
+ "loss": 0.0009,
553
+ "num_tokens": 16937449.0,
554
+ "reward": 0.025577808171510695,
555
+ "reward_std": 0.2193770229816437,
556
+ "rewards/ADEnReward/mean": 0.02711736299097538,
557
+ "rewards/ADEnReward/std": 0.06570543125271797,
558
+ "rewards/CounterfactualJustificationReward/mean": -0.0015395540045574307,
559
+ "rewards/CounterfactualJustificationReward/std": 0.221498242020607,
560
+ "step": 170,
561
+ "step_time": 271.8566128635983
562
+ },
563
+ {
564
+ "clip_ratio/high_max": 0.0,
565
+ "clip_ratio/high_mean": 0.0,
566
+ "clip_ratio/low_mean": 0.0,
567
+ "clip_ratio/low_min": 0.0,
568
+ "clip_ratio/region_mean": 0.0,
569
+ "completions/clipped_ratio": 0.0,
570
+ "completions/max_length": 724.4,
571
+ "completions/max_terminated_length": 724.4,
572
+ "completions/mean_length": 688.7646057128907,
573
+ "completions/mean_terminated_length": 688.7646057128907,
574
+ "completions/min_length": 652.9,
575
+ "completions/min_terminated_length": 652.9,
576
+ "entropy": 0.5081893612941106,
577
+ "epoch": 0.03857693956279468,
578
+ "frac_reward_zero_std": 0.0,
579
+ "grad_norm": 0.8046875,
580
+ "learning_rate": 3.86986301369863e-07,
581
+ "loss": 0.0007,
582
+ "num_tokens": 17934072.0,
583
+ "reward": 0.027723559038713576,
584
+ "reward_std": 0.22686380594968797,
585
+ "rewards/ADEnReward/mean": 0.025532000930979848,
586
+ "rewards/ADEnReward/std": 0.05813485663384199,
587
+ "rewards/CounterfactualJustificationReward/mean": 0.0021915548713877797,
588
+ "rewards/CounterfactualJustificationReward/std": 0.22204958498477936,
589
+ "step": 180,
590
+ "step_time": 275.91866672709875
591
+ },
592
+ {
593
+ "clip_ratio/high_max": 0.0,
594
+ "clip_ratio/high_mean": 0.0,
595
+ "clip_ratio/low_mean": 0.0,
596
+ "clip_ratio/low_min": 0.0,
597
+ "clip_ratio/region_mean": 0.0,
598
+ "completions/clipped_ratio": 0.0,
599
+ "completions/max_length": 725.5,
600
+ "completions/max_terminated_length": 725.5,
601
+ "completions/mean_length": 689.4000305175781,
602
+ "completions/mean_terminated_length": 689.4000305175781,
603
+ "completions/min_length": 652.2,
604
+ "completions/min_terminated_length": 652.2,
605
+ "entropy": 0.5114835540453593,
606
+ "epoch": 0.04072010287183883,
607
+ "frac_reward_zero_std": 0.0,
608
+ "grad_norm": 0.94921875,
609
+ "learning_rate": 3.5273972602739726e-07,
610
+ "loss": 0.0009,
611
+ "num_tokens": 18931432.0,
612
+ "reward": 0.04985461551696062,
613
+ "reward_std": 0.2142663285136223,
614
+ "rewards/ADEnReward/mean": 0.021925948932766913,
615
+ "rewards/ADEnReward/std": 0.05890213418751955,
616
+ "rewards/CounterfactualJustificationReward/mean": 0.027928664442151786,
617
+ "rewards/CounterfactualJustificationReward/std": 0.21681737899780273,
618
+ "step": 190,
619
+ "step_time": 276.6402813741908
620
+ },
621
+ {
622
+ "clip_ratio/high_max": 0.0,
623
+ "clip_ratio/high_mean": 0.0,
624
+ "clip_ratio/low_mean": 0.0,
625
+ "clip_ratio/low_min": 0.0,
626
+ "clip_ratio/region_mean": 0.0,
627
+ "completions/clipped_ratio": 0.0,
628
+ "completions/max_length": 721.3,
629
+ "completions/max_terminated_length": 721.3,
630
+ "completions/mean_length": 688.2229431152343,
631
+ "completions/mean_terminated_length": 688.2229431152343,
632
+ "completions/min_length": 652.6,
633
+ "completions/min_terminated_length": 652.6,
634
+ "entropy": 0.5035619725783665,
635
+ "epoch": 0.042863266180882986,
636
+ "frac_reward_zero_std": 0.0,
637
+ "grad_norm": 0.81640625,
638
+ "learning_rate": 3.1849315068493147e-07,
639
+ "loss": 0.0011,
640
+ "num_tokens": 19927667.0,
641
+ "reward": 0.05030048144981265,
642
+ "reward_std": 0.24021378308534622,
643
+ "rewards/ADEnReward/mean": 0.039960830565541984,
644
+ "rewards/ADEnReward/std": 0.09880391005426645,
645
+ "rewards/CounterfactualJustificationReward/mean": 0.010339650232344866,
646
+ "rewards/CounterfactualJustificationReward/std": 0.22648686170578003,
647
+ "step": 200,
648
+ "step_time": 274.837926760799
649
+ }
650
+ ],
651
+ "logging_steps": 10,
652
+ "max_steps": 292,
653
+ "num_input_tokens_seen": 19927667,
654
+ "num_train_epochs": 1,
655
+ "save_steps": 100,
656
+ "stateful_callbacks": {
657
+ "TrainerControl": {
658
+ "args": {
659
+ "should_epoch_stop": false,
660
+ "should_evaluate": false,
661
+ "should_log": false,
662
+ "should_save": true,
663
+ "should_training_stop": false
664
+ },
665
+ "attributes": {}
666
+ }
667
+ },
668
+ "total_flos": 0.0,
669
+ "train_batch_size": 8,
670
+ "trial_name": null,
671
+ "trial_params": null
672
+ }
ADEn-CFJ-KL0/checkpoint-200/training_args.bin ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:fd0c5e97464cdcc3e01b3a9fb60ed99b89088f1cdc1cd8493defe8506d2eec40
3
+ size 7569
ADEn-CFJ-KL0/checkpoint-200/vocab.json ADDED
The diff for this file is too large to render. See raw diff
 
ADEn-CFJ-KL0/checkpoint-292/added_tokens.json ADDED
@@ -0,0 +1,28 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "</think>": 151668,
3
+ "</tool_call>": 151658,
4
+ "</tool_response>": 151666,
5
+ "<think>": 151667,
6
+ "<tool_call>": 151657,
7
+ "<tool_response>": 151665,
8
+ "<|box_end|>": 151649,
9
+ "<|box_start|>": 151648,
10
+ "<|endoftext|>": 151643,
11
+ "<|file_sep|>": 151664,
12
+ "<|fim_middle|>": 151660,
13
+ "<|fim_pad|>": 151662,
14
+ "<|fim_prefix|>": 151659,
15
+ "<|fim_suffix|>": 151661,
16
+ "<|im_end|>": 151645,
17
+ "<|im_start|>": 151644,
18
+ "<|image_pad|>": 151655,
19
+ "<|object_ref_end|>": 151647,
20
+ "<|object_ref_start|>": 151646,
21
+ "<|quad_end|>": 151651,
22
+ "<|quad_start|>": 151650,
23
+ "<|repo_name|>": 151663,
24
+ "<|video_pad|>": 151656,
25
+ "<|vision_end|>": 151653,
26
+ "<|vision_pad|>": 151654,
27
+ "<|vision_start|>": 151652
28
+ }
ADEn-CFJ-KL0/checkpoint-292/chat_template.jinja ADDED
@@ -0,0 +1,110 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {%- set image_count = namespace(value=0) %}
2
+ {%- set video_count = namespace(value=0) %}
3
+ {%- macro render_content(content, do_vision_count) %}
4
+ {%- if content is string %}
5
+ {{- content }}
6
+ {%- else %}
7
+ {%- for item in content %}
8
+ {%- if 'image' in item or 'image_url' in item or item.type == 'image' %}
9
+ {%- if do_vision_count %}
10
+ {%- set image_count.value = image_count.value + 1 %}
11
+ {%- endif %}
12
+ {%- if add_vision_id %}Picture {{ image_count.value }}: {% endif -%}
13
+ <|vision_start|><|image_pad|><|vision_end|>
14
+ {%- elif 'video' in item or item.type == 'video' %}
15
+ {%- if do_vision_count %}
16
+ {%- set video_count.value = video_count.value + 1 %}
17
+ {%- endif %}
18
+ {%- if add_vision_id %}Video {{ video_count.value }}: {% endif -%}
19
+ <|vision_start|><|video_pad|><|vision_end|>
20
+ {%- elif 'text' in item %}
21
+ {{- item.text }}
22
+ {%- endif %}
23
+ {%- endfor %}
24
+ {%- endif %}
25
+ {%- endmacro %}
26
+ {%- if tools %}
27
+ {{- '<|im_start|>system\n' }}
28
+ {%- if messages[0].role == 'system' %}
29
+ {{- render_content(messages[0].content, false) + '\n\n' }}
30
+ {%- endif %}
31
+ {{- "# Tools\n\nYou may call one or more functions to assist with the user query.\n\nYou are provided with function signatures within <tools></tools> XML tags:\n<tools>" }}
32
+ {%- for tool in tools %}
33
+ {{- "\n" }}
34
+ {{- tool | tojson }}
35
+ {%- endfor %}
36
+ {{- "\n</tools>\n\nFor each function call, return a json object with function name and arguments within <tool_call></tool_call> XML tags:\n<tool_call>\n{\"name\": <function-name>, \"arguments\": <args-json-object>}\n</tool_call><|im_end|>\n" }}
37
+ {%- else %}
38
+ {%- if messages[0].role == 'system' %}
39
+ {{- '<|im_start|>system\n' + render_content(messages[0].content, false) + '<|im_end|>\n' }}
40
+ {%- endif %}
41
+ {%- endif %}
42
+ {%- set ns = namespace(multi_step_tool=true, last_query_index=messages|length - 1) %}
43
+ {%- for message in messages[::-1] %}
44
+ {%- set index = (messages|length - 1) - loop.index0 %}
45
+ {%- if ns.multi_step_tool and message.role == "user" %}
46
+ {%- set content = render_content(message.content, false) %}
47
+ {%- if not(content.startswith('<tool_response>') and content.endswith('</tool_response>')) %}
48
+ {%- set ns.multi_step_tool = false %}
49
+ {%- set ns.last_query_index = index %}
50
+ {%- endif %}
51
+ {%- endif %}
52
+ {%- endfor %}
53
+ {%- for message in messages %}
54
+ {%- set content = render_content(message.content, True) %}
55
+ {%- if (message.role == "user") or (message.role == "system" and not loop.first) %}
56
+ {{- '<|im_start|>' + message.role + '\n' + content + '<|im_end|>' + '\n' }}
57
+ {%- elif message.role == "assistant" %}
58
+ {%- set reasoning_content = '' %}
59
+ {%- if message.reasoning_content is string %}
60
+ {%- set reasoning_content = message.reasoning_content %}
61
+ {%- else %}
62
+ {%- if '</think>' in content %}
63
+ {%- set reasoning_content = content.split('</think>')[0].rstrip('\n').split('<think>')[-1].lstrip('\n') %}
64
+ {%- set content = content.split('</think>')[-1].lstrip('\n') %}
65
+ {%- endif %}
66
+ {%- endif %}
67
+ {%- if loop.index0 > ns.last_query_index %}
68
+ {%- if loop.last or (not loop.last and reasoning_content) %}
69
+ {{- '<|im_start|>' + message.role + '\n<think>\n' + reasoning_content.strip('\n') + '\n</think>\n\n' + content.lstrip('\n') }}
70
+ {%- else %}
71
+ {{- '<|im_start|>' + message.role + '\n' + content }}
72
+ {%- endif %}
73
+ {%- else %}
74
+ {{- '<|im_start|>' + message.role + '\n' + content }}
75
+ {%- endif %}
76
+ {%- if message.tool_calls %}
77
+ {%- for tool_call in message.tool_calls %}
78
+ {%- if (loop.first and content) or (not loop.first) %}
79
+ {{- '\n' }}
80
+ {%- endif %}
81
+ {%- if tool_call.function %}
82
+ {%- set tool_call = tool_call.function %}
83
+ {%- endif %}
84
+ {{- '<tool_call>\n{"name": "' }}
85
+ {{- tool_call.name }}
86
+ {{- '", "arguments": ' }}
87
+ {%- if tool_call.arguments is string %}
88
+ {{- tool_call.arguments }}
89
+ {%- else %}
90
+ {{- tool_call.arguments | tojson }}
91
+ {%- endif %}
92
+ {{- '}\n</tool_call>' }}
93
+ {%- endfor %}
94
+ {%- endif %}
95
+ {{- '<|im_end|>\n' }}
96
+ {%- elif message.role == "tool" %}
97
+ {%- if loop.first or (messages[loop.index0 - 1].role != "tool") %}
98
+ {{- '<|im_start|>user' }}
99
+ {%- endif %}
100
+ {{- '\n<tool_response>\n' }}
101
+ {{- content }}
102
+ {{- '\n</tool_response>' }}
103
+ {%- if loop.last or (messages[loop.index0 + 1].role != "tool") %}
104
+ {{- '<|im_end|>\n' }}
105
+ {%- endif %}
106
+ {%- endif %}
107
+ {%- endfor %}
108
+ {%- if add_generation_prompt %}
109
+ {{- '<|im_start|>assistant\n' }}
110
+ {%- endif %}
ADEn-CFJ-KL0/checkpoint-292/config.json ADDED
@@ -0,0 +1,68 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "architectures": [
3
+ "Qwen3VLForConditionalGeneration"
4
+ ],
5
+ "dtype": "bfloat16",
6
+ "eos_token_id": 151645,
7
+ "image_token_id": 151655,
8
+ "model_type": "qwen3_vl",
9
+ "pad_token_id": 151643,
10
+ "text_config": {
11
+ "attention_bias": false,
12
+ "attention_dropout": 0.0,
13
+ "bos_token_id": 151643,
14
+ "dtype": "bfloat16",
15
+ "eos_token_id": 151645,
16
+ "head_dim": 128,
17
+ "hidden_act": "silu",
18
+ "hidden_size": 2560,
19
+ "initializer_range": 0.02,
20
+ "intermediate_size": 9728,
21
+ "max_position_embeddings": 262144,
22
+ "model_type": "qwen3_vl_text",
23
+ "num_attention_heads": 32,
24
+ "num_hidden_layers": 36,
25
+ "num_key_value_heads": 8,
26
+ "rms_norm_eps": 1e-06,
27
+ "rope_scaling": {
28
+ "mrope_interleaved": true,
29
+ "mrope_section": [
30
+ 24,
31
+ 20,
32
+ 20
33
+ ],
34
+ "rope_type": "default"
35
+ },
36
+ "rope_theta": 5000000,
37
+ "tie_word_embeddings": true,
38
+ "use_cache": true,
39
+ "vocab_size": 151936
40
+ },
41
+ "tie_word_embeddings": true,
42
+ "transformers_version": "4.57.6",
43
+ "use_cache": false,
44
+ "video_token_id": 151656,
45
+ "vision_config": {
46
+ "deepstack_visual_indexes": [
47
+ 5,
48
+ 11,
49
+ 17
50
+ ],
51
+ "depth": 24,
52
+ "dtype": "bfloat16",
53
+ "hidden_act": "gelu_pytorch_tanh",
54
+ "hidden_size": 1024,
55
+ "in_channels": 3,
56
+ "initializer_range": 0.02,
57
+ "intermediate_size": 4096,
58
+ "model_type": "qwen3_vl",
59
+ "num_heads": 16,
60
+ "num_position_embeddings": 2304,
61
+ "out_hidden_size": 2560,
62
+ "patch_size": 16,
63
+ "spatial_merge_size": 2,
64
+ "temporal_patch_size": 2
65
+ },
66
+ "vision_end_token_id": 151653,
67
+ "vision_start_token_id": 151652
68
+ }
ADEn-CFJ-KL0/checkpoint-292/generation_config.json ADDED
@@ -0,0 +1,12 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "do_sample": true,
3
+ "eos_token_id": [
4
+ 151645,
5
+ 151645,
6
+ 151643
7
+ ],
8
+ "pad_token_id": 151643,
9
+ "top_k": 20,
10
+ "top_p": 0.95,
11
+ "transformers_version": "4.57.6"
12
+ }
ADEn-CFJ-KL0/checkpoint-292/merges.txt ADDED
The diff for this file is too large to render. See raw diff
 
ADEn-CFJ-KL0/checkpoint-292/model-00001-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:5cb7d38a32c62dbf8f6a2fa4f5e5c350182babcc51d28a832c8c8a8eb051c4de
3
+ size 4990497880
ADEn-CFJ-KL0/checkpoint-292/model-00002-of-00002.safetensors ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:4c8a668bd4c4108cc4ecb508db11cd1d72d330ea910536c0a64f3a268e67d0c0
3
+ size 3885221448
ADEn-CFJ-KL0/checkpoint-292/model.safetensors.index.json ADDED
@@ -0,0 +1,721 @@
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
1
+ {
2
+ "metadata": {
3
+ "total_parameters": 4437815808,
4
+ "total_size": 8875631616
5
+ },
6
+ "weight_map": {
7
+ "model.language_model.embed_tokens.weight": "model-00001-of-00002.safetensors",
8
+ "model.language_model.layers.0.input_layernorm.weight": "model-00001-of-00002.safetensors",
9
+ "model.language_model.layers.0.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
10
+ "model.language_model.layers.0.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
11
+ "model.language_model.layers.0.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
12
+ "model.language_model.layers.0.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
13
+ "model.language_model.layers.0.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
14
+ "model.language_model.layers.0.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
15
+ "model.language_model.layers.0.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
16
+ "model.language_model.layers.0.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
17
+ "model.language_model.layers.0.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
18
+ "model.language_model.layers.0.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
19
+ "model.language_model.layers.1.input_layernorm.weight": "model-00001-of-00002.safetensors",
20
+ "model.language_model.layers.1.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
21
+ "model.language_model.layers.1.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
22
+ "model.language_model.layers.1.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
23
+ "model.language_model.layers.1.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
24
+ "model.language_model.layers.1.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
25
+ "model.language_model.layers.1.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
26
+ "model.language_model.layers.1.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
27
+ "model.language_model.layers.1.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
28
+ "model.language_model.layers.1.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
29
+ "model.language_model.layers.1.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
30
+ "model.language_model.layers.10.input_layernorm.weight": "model-00001-of-00002.safetensors",
31
+ "model.language_model.layers.10.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
32
+ "model.language_model.layers.10.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
33
+ "model.language_model.layers.10.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
34
+ "model.language_model.layers.10.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
35
+ "model.language_model.layers.10.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
36
+ "model.language_model.layers.10.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
37
+ "model.language_model.layers.10.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
38
+ "model.language_model.layers.10.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
39
+ "model.language_model.layers.10.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
40
+ "model.language_model.layers.10.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
41
+ "model.language_model.layers.11.input_layernorm.weight": "model-00001-of-00002.safetensors",
42
+ "model.language_model.layers.11.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
43
+ "model.language_model.layers.11.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
44
+ "model.language_model.layers.11.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
45
+ "model.language_model.layers.11.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
46
+ "model.language_model.layers.11.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
47
+ "model.language_model.layers.11.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
48
+ "model.language_model.layers.11.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
49
+ "model.language_model.layers.11.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
50
+ "model.language_model.layers.11.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
51
+ "model.language_model.layers.11.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
52
+ "model.language_model.layers.12.input_layernorm.weight": "model-00001-of-00002.safetensors",
53
+ "model.language_model.layers.12.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
54
+ "model.language_model.layers.12.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
55
+ "model.language_model.layers.12.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
56
+ "model.language_model.layers.12.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
57
+ "model.language_model.layers.12.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
58
+ "model.language_model.layers.12.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
59
+ "model.language_model.layers.12.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
60
+ "model.language_model.layers.12.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
61
+ "model.language_model.layers.12.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
62
+ "model.language_model.layers.12.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
63
+ "model.language_model.layers.13.input_layernorm.weight": "model-00001-of-00002.safetensors",
64
+ "model.language_model.layers.13.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
65
+ "model.language_model.layers.13.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
66
+ "model.language_model.layers.13.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
67
+ "model.language_model.layers.13.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
68
+ "model.language_model.layers.13.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
69
+ "model.language_model.layers.13.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
70
+ "model.language_model.layers.13.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
71
+ "model.language_model.layers.13.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
72
+ "model.language_model.layers.13.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
73
+ "model.language_model.layers.13.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
74
+ "model.language_model.layers.14.input_layernorm.weight": "model-00001-of-00002.safetensors",
75
+ "model.language_model.layers.14.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
76
+ "model.language_model.layers.14.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
77
+ "model.language_model.layers.14.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
78
+ "model.language_model.layers.14.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
79
+ "model.language_model.layers.14.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
80
+ "model.language_model.layers.14.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
81
+ "model.language_model.layers.14.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
82
+ "model.language_model.layers.14.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
83
+ "model.language_model.layers.14.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
84
+ "model.language_model.layers.14.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
85
+ "model.language_model.layers.15.input_layernorm.weight": "model-00001-of-00002.safetensors",
86
+ "model.language_model.layers.15.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
87
+ "model.language_model.layers.15.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
88
+ "model.language_model.layers.15.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
89
+ "model.language_model.layers.15.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
90
+ "model.language_model.layers.15.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
91
+ "model.language_model.layers.15.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
92
+ "model.language_model.layers.15.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
93
+ "model.language_model.layers.15.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
94
+ "model.language_model.layers.15.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
95
+ "model.language_model.layers.15.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
96
+ "model.language_model.layers.16.input_layernorm.weight": "model-00002-of-00002.safetensors",
97
+ "model.language_model.layers.16.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
98
+ "model.language_model.layers.16.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
99
+ "model.language_model.layers.16.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
100
+ "model.language_model.layers.16.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
101
+ "model.language_model.layers.16.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
102
+ "model.language_model.layers.16.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
103
+ "model.language_model.layers.16.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
104
+ "model.language_model.layers.16.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
105
+ "model.language_model.layers.16.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
106
+ "model.language_model.layers.16.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
107
+ "model.language_model.layers.17.input_layernorm.weight": "model-00002-of-00002.safetensors",
108
+ "model.language_model.layers.17.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
109
+ "model.language_model.layers.17.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
110
+ "model.language_model.layers.17.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
111
+ "model.language_model.layers.17.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
112
+ "model.language_model.layers.17.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
113
+ "model.language_model.layers.17.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
114
+ "model.language_model.layers.17.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
115
+ "model.language_model.layers.17.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
116
+ "model.language_model.layers.17.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
117
+ "model.language_model.layers.17.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
118
+ "model.language_model.layers.18.input_layernorm.weight": "model-00002-of-00002.safetensors",
119
+ "model.language_model.layers.18.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
120
+ "model.language_model.layers.18.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
121
+ "model.language_model.layers.18.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
122
+ "model.language_model.layers.18.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
123
+ "model.language_model.layers.18.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
124
+ "model.language_model.layers.18.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
125
+ "model.language_model.layers.18.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
126
+ "model.language_model.layers.18.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
127
+ "model.language_model.layers.18.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
128
+ "model.language_model.layers.18.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
129
+ "model.language_model.layers.19.input_layernorm.weight": "model-00002-of-00002.safetensors",
130
+ "model.language_model.layers.19.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
131
+ "model.language_model.layers.19.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
132
+ "model.language_model.layers.19.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
133
+ "model.language_model.layers.19.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
134
+ "model.language_model.layers.19.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
135
+ "model.language_model.layers.19.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
136
+ "model.language_model.layers.19.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
137
+ "model.language_model.layers.19.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
138
+ "model.language_model.layers.19.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
139
+ "model.language_model.layers.19.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
140
+ "model.language_model.layers.2.input_layernorm.weight": "model-00001-of-00002.safetensors",
141
+ "model.language_model.layers.2.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
142
+ "model.language_model.layers.2.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
143
+ "model.language_model.layers.2.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
144
+ "model.language_model.layers.2.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
145
+ "model.language_model.layers.2.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
146
+ "model.language_model.layers.2.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
147
+ "model.language_model.layers.2.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
148
+ "model.language_model.layers.2.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
149
+ "model.language_model.layers.2.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
150
+ "model.language_model.layers.2.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
151
+ "model.language_model.layers.20.input_layernorm.weight": "model-00002-of-00002.safetensors",
152
+ "model.language_model.layers.20.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
153
+ "model.language_model.layers.20.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
154
+ "model.language_model.layers.20.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
155
+ "model.language_model.layers.20.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
156
+ "model.language_model.layers.20.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
157
+ "model.language_model.layers.20.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
158
+ "model.language_model.layers.20.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
159
+ "model.language_model.layers.20.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
160
+ "model.language_model.layers.20.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
161
+ "model.language_model.layers.20.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
162
+ "model.language_model.layers.21.input_layernorm.weight": "model-00002-of-00002.safetensors",
163
+ "model.language_model.layers.21.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
164
+ "model.language_model.layers.21.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
165
+ "model.language_model.layers.21.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
166
+ "model.language_model.layers.21.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
167
+ "model.language_model.layers.21.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
168
+ "model.language_model.layers.21.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
169
+ "model.language_model.layers.21.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
170
+ "model.language_model.layers.21.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
171
+ "model.language_model.layers.21.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
172
+ "model.language_model.layers.21.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
173
+ "model.language_model.layers.22.input_layernorm.weight": "model-00002-of-00002.safetensors",
174
+ "model.language_model.layers.22.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
175
+ "model.language_model.layers.22.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
176
+ "model.language_model.layers.22.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
177
+ "model.language_model.layers.22.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
178
+ "model.language_model.layers.22.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
179
+ "model.language_model.layers.22.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
180
+ "model.language_model.layers.22.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
181
+ "model.language_model.layers.22.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
182
+ "model.language_model.layers.22.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
183
+ "model.language_model.layers.22.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
184
+ "model.language_model.layers.23.input_layernorm.weight": "model-00002-of-00002.safetensors",
185
+ "model.language_model.layers.23.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
186
+ "model.language_model.layers.23.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
187
+ "model.language_model.layers.23.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
188
+ "model.language_model.layers.23.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
189
+ "model.language_model.layers.23.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
190
+ "model.language_model.layers.23.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
191
+ "model.language_model.layers.23.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
192
+ "model.language_model.layers.23.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
193
+ "model.language_model.layers.23.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
194
+ "model.language_model.layers.23.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
195
+ "model.language_model.layers.24.input_layernorm.weight": "model-00002-of-00002.safetensors",
196
+ "model.language_model.layers.24.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
197
+ "model.language_model.layers.24.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
198
+ "model.language_model.layers.24.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
199
+ "model.language_model.layers.24.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
200
+ "model.language_model.layers.24.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
201
+ "model.language_model.layers.24.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
202
+ "model.language_model.layers.24.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
203
+ "model.language_model.layers.24.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
204
+ "model.language_model.layers.24.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
205
+ "model.language_model.layers.24.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
206
+ "model.language_model.layers.25.input_layernorm.weight": "model-00002-of-00002.safetensors",
207
+ "model.language_model.layers.25.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
208
+ "model.language_model.layers.25.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
209
+ "model.language_model.layers.25.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
210
+ "model.language_model.layers.25.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
211
+ "model.language_model.layers.25.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
212
+ "model.language_model.layers.25.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
213
+ "model.language_model.layers.25.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
214
+ "model.language_model.layers.25.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
215
+ "model.language_model.layers.25.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
216
+ "model.language_model.layers.25.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
217
+ "model.language_model.layers.26.input_layernorm.weight": "model-00002-of-00002.safetensors",
218
+ "model.language_model.layers.26.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
219
+ "model.language_model.layers.26.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
220
+ "model.language_model.layers.26.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
221
+ "model.language_model.layers.26.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
222
+ "model.language_model.layers.26.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
223
+ "model.language_model.layers.26.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
224
+ "model.language_model.layers.26.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
225
+ "model.language_model.layers.26.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
226
+ "model.language_model.layers.26.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
227
+ "model.language_model.layers.26.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
228
+ "model.language_model.layers.27.input_layernorm.weight": "model-00002-of-00002.safetensors",
229
+ "model.language_model.layers.27.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
230
+ "model.language_model.layers.27.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
231
+ "model.language_model.layers.27.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
232
+ "model.language_model.layers.27.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
233
+ "model.language_model.layers.27.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
234
+ "model.language_model.layers.27.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
235
+ "model.language_model.layers.27.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
236
+ "model.language_model.layers.27.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
237
+ "model.language_model.layers.27.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
238
+ "model.language_model.layers.27.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
239
+ "model.language_model.layers.28.input_layernorm.weight": "model-00002-of-00002.safetensors",
240
+ "model.language_model.layers.28.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
241
+ "model.language_model.layers.28.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
242
+ "model.language_model.layers.28.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
243
+ "model.language_model.layers.28.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
244
+ "model.language_model.layers.28.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
245
+ "model.language_model.layers.28.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
246
+ "model.language_model.layers.28.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
247
+ "model.language_model.layers.28.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
248
+ "model.language_model.layers.28.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
249
+ "model.language_model.layers.28.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
250
+ "model.language_model.layers.29.input_layernorm.weight": "model-00002-of-00002.safetensors",
251
+ "model.language_model.layers.29.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
252
+ "model.language_model.layers.29.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
253
+ "model.language_model.layers.29.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
254
+ "model.language_model.layers.29.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
255
+ "model.language_model.layers.29.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
256
+ "model.language_model.layers.29.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
257
+ "model.language_model.layers.29.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
258
+ "model.language_model.layers.29.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
259
+ "model.language_model.layers.29.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
260
+ "model.language_model.layers.29.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
261
+ "model.language_model.layers.3.input_layernorm.weight": "model-00001-of-00002.safetensors",
262
+ "model.language_model.layers.3.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
263
+ "model.language_model.layers.3.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
264
+ "model.language_model.layers.3.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
265
+ "model.language_model.layers.3.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
266
+ "model.language_model.layers.3.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
267
+ "model.language_model.layers.3.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
268
+ "model.language_model.layers.3.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
269
+ "model.language_model.layers.3.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
270
+ "model.language_model.layers.3.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
271
+ "model.language_model.layers.3.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
272
+ "model.language_model.layers.30.input_layernorm.weight": "model-00002-of-00002.safetensors",
273
+ "model.language_model.layers.30.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
274
+ "model.language_model.layers.30.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
275
+ "model.language_model.layers.30.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
276
+ "model.language_model.layers.30.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
277
+ "model.language_model.layers.30.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
278
+ "model.language_model.layers.30.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
279
+ "model.language_model.layers.30.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
280
+ "model.language_model.layers.30.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
281
+ "model.language_model.layers.30.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
282
+ "model.language_model.layers.30.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
283
+ "model.language_model.layers.31.input_layernorm.weight": "model-00002-of-00002.safetensors",
284
+ "model.language_model.layers.31.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
285
+ "model.language_model.layers.31.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
286
+ "model.language_model.layers.31.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
287
+ "model.language_model.layers.31.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
288
+ "model.language_model.layers.31.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
289
+ "model.language_model.layers.31.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
290
+ "model.language_model.layers.31.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
291
+ "model.language_model.layers.31.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
292
+ "model.language_model.layers.31.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
293
+ "model.language_model.layers.31.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
294
+ "model.language_model.layers.32.input_layernorm.weight": "model-00002-of-00002.safetensors",
295
+ "model.language_model.layers.32.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
296
+ "model.language_model.layers.32.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
297
+ "model.language_model.layers.32.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
298
+ "model.language_model.layers.32.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
299
+ "model.language_model.layers.32.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
300
+ "model.language_model.layers.32.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
301
+ "model.language_model.layers.32.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
302
+ "model.language_model.layers.32.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
303
+ "model.language_model.layers.32.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
304
+ "model.language_model.layers.32.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
305
+ "model.language_model.layers.33.input_layernorm.weight": "model-00002-of-00002.safetensors",
306
+ "model.language_model.layers.33.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
307
+ "model.language_model.layers.33.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
308
+ "model.language_model.layers.33.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
309
+ "model.language_model.layers.33.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
310
+ "model.language_model.layers.33.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
311
+ "model.language_model.layers.33.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
312
+ "model.language_model.layers.33.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
313
+ "model.language_model.layers.33.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
314
+ "model.language_model.layers.33.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
315
+ "model.language_model.layers.33.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
316
+ "model.language_model.layers.34.input_layernorm.weight": "model-00002-of-00002.safetensors",
317
+ "model.language_model.layers.34.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
318
+ "model.language_model.layers.34.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
319
+ "model.language_model.layers.34.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
320
+ "model.language_model.layers.34.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
321
+ "model.language_model.layers.34.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
322
+ "model.language_model.layers.34.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
323
+ "model.language_model.layers.34.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
324
+ "model.language_model.layers.34.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
325
+ "model.language_model.layers.34.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
326
+ "model.language_model.layers.34.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
327
+ "model.language_model.layers.35.input_layernorm.weight": "model-00002-of-00002.safetensors",
328
+ "model.language_model.layers.35.mlp.down_proj.weight": "model-00002-of-00002.safetensors",
329
+ "model.language_model.layers.35.mlp.gate_proj.weight": "model-00002-of-00002.safetensors",
330
+ "model.language_model.layers.35.mlp.up_proj.weight": "model-00002-of-00002.safetensors",
331
+ "model.language_model.layers.35.post_attention_layernorm.weight": "model-00002-of-00002.safetensors",
332
+ "model.language_model.layers.35.self_attn.k_norm.weight": "model-00002-of-00002.safetensors",
333
+ "model.language_model.layers.35.self_attn.k_proj.weight": "model-00002-of-00002.safetensors",
334
+ "model.language_model.layers.35.self_attn.o_proj.weight": "model-00002-of-00002.safetensors",
335
+ "model.language_model.layers.35.self_attn.q_norm.weight": "model-00002-of-00002.safetensors",
336
+ "model.language_model.layers.35.self_attn.q_proj.weight": "model-00002-of-00002.safetensors",
337
+ "model.language_model.layers.35.self_attn.v_proj.weight": "model-00002-of-00002.safetensors",
338
+ "model.language_model.layers.4.input_layernorm.weight": "model-00001-of-00002.safetensors",
339
+ "model.language_model.layers.4.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
340
+ "model.language_model.layers.4.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
341
+ "model.language_model.layers.4.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
342
+ "model.language_model.layers.4.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
343
+ "model.language_model.layers.4.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
344
+ "model.language_model.layers.4.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
345
+ "model.language_model.layers.4.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
346
+ "model.language_model.layers.4.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
347
+ "model.language_model.layers.4.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
348
+ "model.language_model.layers.4.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
349
+ "model.language_model.layers.5.input_layernorm.weight": "model-00001-of-00002.safetensors",
350
+ "model.language_model.layers.5.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
351
+ "model.language_model.layers.5.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
352
+ "model.language_model.layers.5.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
353
+ "model.language_model.layers.5.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
354
+ "model.language_model.layers.5.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
355
+ "model.language_model.layers.5.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
356
+ "model.language_model.layers.5.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
357
+ "model.language_model.layers.5.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
358
+ "model.language_model.layers.5.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
359
+ "model.language_model.layers.5.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
360
+ "model.language_model.layers.6.input_layernorm.weight": "model-00001-of-00002.safetensors",
361
+ "model.language_model.layers.6.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
362
+ "model.language_model.layers.6.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
363
+ "model.language_model.layers.6.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
364
+ "model.language_model.layers.6.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
365
+ "model.language_model.layers.6.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
366
+ "model.language_model.layers.6.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
367
+ "model.language_model.layers.6.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
368
+ "model.language_model.layers.6.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
369
+ "model.language_model.layers.6.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
370
+ "model.language_model.layers.6.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
371
+ "model.language_model.layers.7.input_layernorm.weight": "model-00001-of-00002.safetensors",
372
+ "model.language_model.layers.7.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
373
+ "model.language_model.layers.7.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
374
+ "model.language_model.layers.7.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
375
+ "model.language_model.layers.7.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
376
+ "model.language_model.layers.7.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
377
+ "model.language_model.layers.7.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
378
+ "model.language_model.layers.7.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
379
+ "model.language_model.layers.7.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
380
+ "model.language_model.layers.7.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
381
+ "model.language_model.layers.7.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
382
+ "model.language_model.layers.8.input_layernorm.weight": "model-00001-of-00002.safetensors",
383
+ "model.language_model.layers.8.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
384
+ "model.language_model.layers.8.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
385
+ "model.language_model.layers.8.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
386
+ "model.language_model.layers.8.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
387
+ "model.language_model.layers.8.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
388
+ "model.language_model.layers.8.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
389
+ "model.language_model.layers.8.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
390
+ "model.language_model.layers.8.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
391
+ "model.language_model.layers.8.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
392
+ "model.language_model.layers.8.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
393
+ "model.language_model.layers.9.input_layernorm.weight": "model-00001-of-00002.safetensors",
394
+ "model.language_model.layers.9.mlp.down_proj.weight": "model-00001-of-00002.safetensors",
395
+ "model.language_model.layers.9.mlp.gate_proj.weight": "model-00001-of-00002.safetensors",
396
+ "model.language_model.layers.9.mlp.up_proj.weight": "model-00001-of-00002.safetensors",
397
+ "model.language_model.layers.9.post_attention_layernorm.weight": "model-00001-of-00002.safetensors",
398
+ "model.language_model.layers.9.self_attn.k_norm.weight": "model-00001-of-00002.safetensors",
399
+ "model.language_model.layers.9.self_attn.k_proj.weight": "model-00001-of-00002.safetensors",
400
+ "model.language_model.layers.9.self_attn.o_proj.weight": "model-00001-of-00002.safetensors",
401
+ "model.language_model.layers.9.self_attn.q_norm.weight": "model-00001-of-00002.safetensors",
402
+ "model.language_model.layers.9.self_attn.q_proj.weight": "model-00001-of-00002.safetensors",
403
+ "model.language_model.layers.9.self_attn.v_proj.weight": "model-00001-of-00002.safetensors",
404
+ "model.language_model.norm.weight": "model-00002-of-00002.safetensors",
405
+ "model.visual.blocks.0.attn.proj.bias": "model-00001-of-00002.safetensors",
406
+ "model.visual.blocks.0.attn.proj.weight": "model-00001-of-00002.safetensors",
407
+ "model.visual.blocks.0.attn.qkv.bias": "model-00001-of-00002.safetensors",
408
+ "model.visual.blocks.0.attn.qkv.weight": "model-00001-of-00002.safetensors",
409
+ "model.visual.blocks.0.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
410
+ "model.visual.blocks.0.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
411
+ "model.visual.blocks.0.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
412
+ "model.visual.blocks.0.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
413
+ "model.visual.blocks.0.norm1.bias": "model-00001-of-00002.safetensors",
414
+ "model.visual.blocks.0.norm1.weight": "model-00001-of-00002.safetensors",
415
+ "model.visual.blocks.0.norm2.bias": "model-00001-of-00002.safetensors",
416
+ "model.visual.blocks.0.norm2.weight": "model-00001-of-00002.safetensors",
417
+ "model.visual.blocks.1.attn.proj.bias": "model-00001-of-00002.safetensors",
418
+ "model.visual.blocks.1.attn.proj.weight": "model-00001-of-00002.safetensors",
419
+ "model.visual.blocks.1.attn.qkv.bias": "model-00001-of-00002.safetensors",
420
+ "model.visual.blocks.1.attn.qkv.weight": "model-00001-of-00002.safetensors",
421
+ "model.visual.blocks.1.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
422
+ "model.visual.blocks.1.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
423
+ "model.visual.blocks.1.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
424
+ "model.visual.blocks.1.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
425
+ "model.visual.blocks.1.norm1.bias": "model-00001-of-00002.safetensors",
426
+ "model.visual.blocks.1.norm1.weight": "model-00001-of-00002.safetensors",
427
+ "model.visual.blocks.1.norm2.bias": "model-00001-of-00002.safetensors",
428
+ "model.visual.blocks.1.norm2.weight": "model-00001-of-00002.safetensors",
429
+ "model.visual.blocks.10.attn.proj.bias": "model-00001-of-00002.safetensors",
430
+ "model.visual.blocks.10.attn.proj.weight": "model-00001-of-00002.safetensors",
431
+ "model.visual.blocks.10.attn.qkv.bias": "model-00001-of-00002.safetensors",
432
+ "model.visual.blocks.10.attn.qkv.weight": "model-00001-of-00002.safetensors",
433
+ "model.visual.blocks.10.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
434
+ "model.visual.blocks.10.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
435
+ "model.visual.blocks.10.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
436
+ "model.visual.blocks.10.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
437
+ "model.visual.blocks.10.norm1.bias": "model-00001-of-00002.safetensors",
438
+ "model.visual.blocks.10.norm1.weight": "model-00001-of-00002.safetensors",
439
+ "model.visual.blocks.10.norm2.bias": "model-00001-of-00002.safetensors",
440
+ "model.visual.blocks.10.norm2.weight": "model-00001-of-00002.safetensors",
441
+ "model.visual.blocks.11.attn.proj.bias": "model-00001-of-00002.safetensors",
442
+ "model.visual.blocks.11.attn.proj.weight": "model-00001-of-00002.safetensors",
443
+ "model.visual.blocks.11.attn.qkv.bias": "model-00001-of-00002.safetensors",
444
+ "model.visual.blocks.11.attn.qkv.weight": "model-00001-of-00002.safetensors",
445
+ "model.visual.blocks.11.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
446
+ "model.visual.blocks.11.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
447
+ "model.visual.blocks.11.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
448
+ "model.visual.blocks.11.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
449
+ "model.visual.blocks.11.norm1.bias": "model-00001-of-00002.safetensors",
450
+ "model.visual.blocks.11.norm1.weight": "model-00001-of-00002.safetensors",
451
+ "model.visual.blocks.11.norm2.bias": "model-00001-of-00002.safetensors",
452
+ "model.visual.blocks.11.norm2.weight": "model-00001-of-00002.safetensors",
453
+ "model.visual.blocks.12.attn.proj.bias": "model-00001-of-00002.safetensors",
454
+ "model.visual.blocks.12.attn.proj.weight": "model-00001-of-00002.safetensors",
455
+ "model.visual.blocks.12.attn.qkv.bias": "model-00001-of-00002.safetensors",
456
+ "model.visual.blocks.12.attn.qkv.weight": "model-00001-of-00002.safetensors",
457
+ "model.visual.blocks.12.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
458
+ "model.visual.blocks.12.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
459
+ "model.visual.blocks.12.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
460
+ "model.visual.blocks.12.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
461
+ "model.visual.blocks.12.norm1.bias": "model-00001-of-00002.safetensors",
462
+ "model.visual.blocks.12.norm1.weight": "model-00001-of-00002.safetensors",
463
+ "model.visual.blocks.12.norm2.bias": "model-00001-of-00002.safetensors",
464
+ "model.visual.blocks.12.norm2.weight": "model-00001-of-00002.safetensors",
465
+ "model.visual.blocks.13.attn.proj.bias": "model-00001-of-00002.safetensors",
466
+ "model.visual.blocks.13.attn.proj.weight": "model-00001-of-00002.safetensors",
467
+ "model.visual.blocks.13.attn.qkv.bias": "model-00001-of-00002.safetensors",
468
+ "model.visual.blocks.13.attn.qkv.weight": "model-00001-of-00002.safetensors",
469
+ "model.visual.blocks.13.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
470
+ "model.visual.blocks.13.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
471
+ "model.visual.blocks.13.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
472
+ "model.visual.blocks.13.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
473
+ "model.visual.blocks.13.norm1.bias": "model-00001-of-00002.safetensors",
474
+ "model.visual.blocks.13.norm1.weight": "model-00001-of-00002.safetensors",
475
+ "model.visual.blocks.13.norm2.bias": "model-00001-of-00002.safetensors",
476
+ "model.visual.blocks.13.norm2.weight": "model-00001-of-00002.safetensors",
477
+ "model.visual.blocks.14.attn.proj.bias": "model-00001-of-00002.safetensors",
478
+ "model.visual.blocks.14.attn.proj.weight": "model-00001-of-00002.safetensors",
479
+ "model.visual.blocks.14.attn.qkv.bias": "model-00001-of-00002.safetensors",
480
+ "model.visual.blocks.14.attn.qkv.weight": "model-00001-of-00002.safetensors",
481
+ "model.visual.blocks.14.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
482
+ "model.visual.blocks.14.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
483
+ "model.visual.blocks.14.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
484
+ "model.visual.blocks.14.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
485
+ "model.visual.blocks.14.norm1.bias": "model-00001-of-00002.safetensors",
486
+ "model.visual.blocks.14.norm1.weight": "model-00001-of-00002.safetensors",
487
+ "model.visual.blocks.14.norm2.bias": "model-00001-of-00002.safetensors",
488
+ "model.visual.blocks.14.norm2.weight": "model-00001-of-00002.safetensors",
489
+ "model.visual.blocks.15.attn.proj.bias": "model-00001-of-00002.safetensors",
490
+ "model.visual.blocks.15.attn.proj.weight": "model-00001-of-00002.safetensors",
491
+ "model.visual.blocks.15.attn.qkv.bias": "model-00001-of-00002.safetensors",
492
+ "model.visual.blocks.15.attn.qkv.weight": "model-00001-of-00002.safetensors",
493
+ "model.visual.blocks.15.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
494
+ "model.visual.blocks.15.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
495
+ "model.visual.blocks.15.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
496
+ "model.visual.blocks.15.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
497
+ "model.visual.blocks.15.norm1.bias": "model-00001-of-00002.safetensors",
498
+ "model.visual.blocks.15.norm1.weight": "model-00001-of-00002.safetensors",
499
+ "model.visual.blocks.15.norm2.bias": "model-00001-of-00002.safetensors",
500
+ "model.visual.blocks.15.norm2.weight": "model-00001-of-00002.safetensors",
501
+ "model.visual.blocks.16.attn.proj.bias": "model-00001-of-00002.safetensors",
502
+ "model.visual.blocks.16.attn.proj.weight": "model-00001-of-00002.safetensors",
503
+ "model.visual.blocks.16.attn.qkv.bias": "model-00001-of-00002.safetensors",
504
+ "model.visual.blocks.16.attn.qkv.weight": "model-00001-of-00002.safetensors",
505
+ "model.visual.blocks.16.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
506
+ "model.visual.blocks.16.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
507
+ "model.visual.blocks.16.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
508
+ "model.visual.blocks.16.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
509
+ "model.visual.blocks.16.norm1.bias": "model-00001-of-00002.safetensors",
510
+ "model.visual.blocks.16.norm1.weight": "model-00001-of-00002.safetensors",
511
+ "model.visual.blocks.16.norm2.bias": "model-00001-of-00002.safetensors",
512
+ "model.visual.blocks.16.norm2.weight": "model-00001-of-00002.safetensors",
513
+ "model.visual.blocks.17.attn.proj.bias": "model-00001-of-00002.safetensors",
514
+ "model.visual.blocks.17.attn.proj.weight": "model-00001-of-00002.safetensors",
515
+ "model.visual.blocks.17.attn.qkv.bias": "model-00001-of-00002.safetensors",
516
+ "model.visual.blocks.17.attn.qkv.weight": "model-00001-of-00002.safetensors",
517
+ "model.visual.blocks.17.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
518
+ "model.visual.blocks.17.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
519
+ "model.visual.blocks.17.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
520
+ "model.visual.blocks.17.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
521
+ "model.visual.blocks.17.norm1.bias": "model-00001-of-00002.safetensors",
522
+ "model.visual.blocks.17.norm1.weight": "model-00001-of-00002.safetensors",
523
+ "model.visual.blocks.17.norm2.bias": "model-00001-of-00002.safetensors",
524
+ "model.visual.blocks.17.norm2.weight": "model-00001-of-00002.safetensors",
525
+ "model.visual.blocks.18.attn.proj.bias": "model-00001-of-00002.safetensors",
526
+ "model.visual.blocks.18.attn.proj.weight": "model-00001-of-00002.safetensors",
527
+ "model.visual.blocks.18.attn.qkv.bias": "model-00001-of-00002.safetensors",
528
+ "model.visual.blocks.18.attn.qkv.weight": "model-00001-of-00002.safetensors",
529
+ "model.visual.blocks.18.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
530
+ "model.visual.blocks.18.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
531
+ "model.visual.blocks.18.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
532
+ "model.visual.blocks.18.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
533
+ "model.visual.blocks.18.norm1.bias": "model-00001-of-00002.safetensors",
534
+ "model.visual.blocks.18.norm1.weight": "model-00001-of-00002.safetensors",
535
+ "model.visual.blocks.18.norm2.bias": "model-00001-of-00002.safetensors",
536
+ "model.visual.blocks.18.norm2.weight": "model-00001-of-00002.safetensors",
537
+ "model.visual.blocks.19.attn.proj.bias": "model-00001-of-00002.safetensors",
538
+ "model.visual.blocks.19.attn.proj.weight": "model-00001-of-00002.safetensors",
539
+ "model.visual.blocks.19.attn.qkv.bias": "model-00001-of-00002.safetensors",
540
+ "model.visual.blocks.19.attn.qkv.weight": "model-00001-of-00002.safetensors",
541
+ "model.visual.blocks.19.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
542
+ "model.visual.blocks.19.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
543
+ "model.visual.blocks.19.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
544
+ "model.visual.blocks.19.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
545
+ "model.visual.blocks.19.norm1.bias": "model-00001-of-00002.safetensors",
546
+ "model.visual.blocks.19.norm1.weight": "model-00001-of-00002.safetensors",
547
+ "model.visual.blocks.19.norm2.bias": "model-00001-of-00002.safetensors",
548
+ "model.visual.blocks.19.norm2.weight": "model-00001-of-00002.safetensors",
549
+ "model.visual.blocks.2.attn.proj.bias": "model-00001-of-00002.safetensors",
550
+ "model.visual.blocks.2.attn.proj.weight": "model-00001-of-00002.safetensors",
551
+ "model.visual.blocks.2.attn.qkv.bias": "model-00001-of-00002.safetensors",
552
+ "model.visual.blocks.2.attn.qkv.weight": "model-00001-of-00002.safetensors",
553
+ "model.visual.blocks.2.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
554
+ "model.visual.blocks.2.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
555
+ "model.visual.blocks.2.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
556
+ "model.visual.blocks.2.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
557
+ "model.visual.blocks.2.norm1.bias": "model-00001-of-00002.safetensors",
558
+ "model.visual.blocks.2.norm1.weight": "model-00001-of-00002.safetensors",
559
+ "model.visual.blocks.2.norm2.bias": "model-00001-of-00002.safetensors",
560
+ "model.visual.blocks.2.norm2.weight": "model-00001-of-00002.safetensors",
561
+ "model.visual.blocks.20.attn.proj.bias": "model-00001-of-00002.safetensors",
562
+ "model.visual.blocks.20.attn.proj.weight": "model-00001-of-00002.safetensors",
563
+ "model.visual.blocks.20.attn.qkv.bias": "model-00001-of-00002.safetensors",
564
+ "model.visual.blocks.20.attn.qkv.weight": "model-00001-of-00002.safetensors",
565
+ "model.visual.blocks.20.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
566
+ "model.visual.blocks.20.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
567
+ "model.visual.blocks.20.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
568
+ "model.visual.blocks.20.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
569
+ "model.visual.blocks.20.norm1.bias": "model-00001-of-00002.safetensors",
570
+ "model.visual.blocks.20.norm1.weight": "model-00001-of-00002.safetensors",
571
+ "model.visual.blocks.20.norm2.bias": "model-00001-of-00002.safetensors",
572
+ "model.visual.blocks.20.norm2.weight": "model-00001-of-00002.safetensors",
573
+ "model.visual.blocks.21.attn.proj.bias": "model-00001-of-00002.safetensors",
574
+ "model.visual.blocks.21.attn.proj.weight": "model-00001-of-00002.safetensors",
575
+ "model.visual.blocks.21.attn.qkv.bias": "model-00001-of-00002.safetensors",
576
+ "model.visual.blocks.21.attn.qkv.weight": "model-00001-of-00002.safetensors",
577
+ "model.visual.blocks.21.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
578
+ "model.visual.blocks.21.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
579
+ "model.visual.blocks.21.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
580
+ "model.visual.blocks.21.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
581
+ "model.visual.blocks.21.norm1.bias": "model-00001-of-00002.safetensors",
582
+ "model.visual.blocks.21.norm1.weight": "model-00001-of-00002.safetensors",
583
+ "model.visual.blocks.21.norm2.bias": "model-00001-of-00002.safetensors",
584
+ "model.visual.blocks.21.norm2.weight": "model-00001-of-00002.safetensors",
585
+ "model.visual.blocks.22.attn.proj.bias": "model-00001-of-00002.safetensors",
586
+ "model.visual.blocks.22.attn.proj.weight": "model-00001-of-00002.safetensors",
587
+ "model.visual.blocks.22.attn.qkv.bias": "model-00001-of-00002.safetensors",
588
+ "model.visual.blocks.22.attn.qkv.weight": "model-00001-of-00002.safetensors",
589
+ "model.visual.blocks.22.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
590
+ "model.visual.blocks.22.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
591
+ "model.visual.blocks.22.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
592
+ "model.visual.blocks.22.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
593
+ "model.visual.blocks.22.norm1.bias": "model-00001-of-00002.safetensors",
594
+ "model.visual.blocks.22.norm1.weight": "model-00001-of-00002.safetensors",
595
+ "model.visual.blocks.22.norm2.bias": "model-00001-of-00002.safetensors",
596
+ "model.visual.blocks.22.norm2.weight": "model-00001-of-00002.safetensors",
597
+ "model.visual.blocks.23.attn.proj.bias": "model-00001-of-00002.safetensors",
598
+ "model.visual.blocks.23.attn.proj.weight": "model-00001-of-00002.safetensors",
599
+ "model.visual.blocks.23.attn.qkv.bias": "model-00001-of-00002.safetensors",
600
+ "model.visual.blocks.23.attn.qkv.weight": "model-00001-of-00002.safetensors",
601
+ "model.visual.blocks.23.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
602
+ "model.visual.blocks.23.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
603
+ "model.visual.blocks.23.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
604
+ "model.visual.blocks.23.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
605
+ "model.visual.blocks.23.norm1.bias": "model-00001-of-00002.safetensors",
606
+ "model.visual.blocks.23.norm1.weight": "model-00001-of-00002.safetensors",
607
+ "model.visual.blocks.23.norm2.bias": "model-00001-of-00002.safetensors",
608
+ "model.visual.blocks.23.norm2.weight": "model-00001-of-00002.safetensors",
609
+ "model.visual.blocks.3.attn.proj.bias": "model-00001-of-00002.safetensors",
610
+ "model.visual.blocks.3.attn.proj.weight": "model-00001-of-00002.safetensors",
611
+ "model.visual.blocks.3.attn.qkv.bias": "model-00001-of-00002.safetensors",
612
+ "model.visual.blocks.3.attn.qkv.weight": "model-00001-of-00002.safetensors",
613
+ "model.visual.blocks.3.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
614
+ "model.visual.blocks.3.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
615
+ "model.visual.blocks.3.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
616
+ "model.visual.blocks.3.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
617
+ "model.visual.blocks.3.norm1.bias": "model-00001-of-00002.safetensors",
618
+ "model.visual.blocks.3.norm1.weight": "model-00001-of-00002.safetensors",
619
+ "model.visual.blocks.3.norm2.bias": "model-00001-of-00002.safetensors",
620
+ "model.visual.blocks.3.norm2.weight": "model-00001-of-00002.safetensors",
621
+ "model.visual.blocks.4.attn.proj.bias": "model-00001-of-00002.safetensors",
622
+ "model.visual.blocks.4.attn.proj.weight": "model-00001-of-00002.safetensors",
623
+ "model.visual.blocks.4.attn.qkv.bias": "model-00001-of-00002.safetensors",
624
+ "model.visual.blocks.4.attn.qkv.weight": "model-00001-of-00002.safetensors",
625
+ "model.visual.blocks.4.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
626
+ "model.visual.blocks.4.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
627
+ "model.visual.blocks.4.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
628
+ "model.visual.blocks.4.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
629
+ "model.visual.blocks.4.norm1.bias": "model-00001-of-00002.safetensors",
630
+ "model.visual.blocks.4.norm1.weight": "model-00001-of-00002.safetensors",
631
+ "model.visual.blocks.4.norm2.bias": "model-00001-of-00002.safetensors",
632
+ "model.visual.blocks.4.norm2.weight": "model-00001-of-00002.safetensors",
633
+ "model.visual.blocks.5.attn.proj.bias": "model-00001-of-00002.safetensors",
634
+ "model.visual.blocks.5.attn.proj.weight": "model-00001-of-00002.safetensors",
635
+ "model.visual.blocks.5.attn.qkv.bias": "model-00001-of-00002.safetensors",
636
+ "model.visual.blocks.5.attn.qkv.weight": "model-00001-of-00002.safetensors",
637
+ "model.visual.blocks.5.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
638
+ "model.visual.blocks.5.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
639
+ "model.visual.blocks.5.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
640
+ "model.visual.blocks.5.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
641
+ "model.visual.blocks.5.norm1.bias": "model-00001-of-00002.safetensors",
642
+ "model.visual.blocks.5.norm1.weight": "model-00001-of-00002.safetensors",
643
+ "model.visual.blocks.5.norm2.bias": "model-00001-of-00002.safetensors",
644
+ "model.visual.blocks.5.norm2.weight": "model-00001-of-00002.safetensors",
645
+ "model.visual.blocks.6.attn.proj.bias": "model-00001-of-00002.safetensors",
646
+ "model.visual.blocks.6.attn.proj.weight": "model-00001-of-00002.safetensors",
647
+ "model.visual.blocks.6.attn.qkv.bias": "model-00001-of-00002.safetensors",
648
+ "model.visual.blocks.6.attn.qkv.weight": "model-00001-of-00002.safetensors",
649
+ "model.visual.blocks.6.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
650
+ "model.visual.blocks.6.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
651
+ "model.visual.blocks.6.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
652
+ "model.visual.blocks.6.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
653
+ "model.visual.blocks.6.norm1.bias": "model-00001-of-00002.safetensors",
654
+ "model.visual.blocks.6.norm1.weight": "model-00001-of-00002.safetensors",
655
+ "model.visual.blocks.6.norm2.bias": "model-00001-of-00002.safetensors",
656
+ "model.visual.blocks.6.norm2.weight": "model-00001-of-00002.safetensors",
657
+ "model.visual.blocks.7.attn.proj.bias": "model-00001-of-00002.safetensors",
658
+ "model.visual.blocks.7.attn.proj.weight": "model-00001-of-00002.safetensors",
659
+ "model.visual.blocks.7.attn.qkv.bias": "model-00001-of-00002.safetensors",
660
+ "model.visual.blocks.7.attn.qkv.weight": "model-00001-of-00002.safetensors",
661
+ "model.visual.blocks.7.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
662
+ "model.visual.blocks.7.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
663
+ "model.visual.blocks.7.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
664
+ "model.visual.blocks.7.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
665
+ "model.visual.blocks.7.norm1.bias": "model-00001-of-00002.safetensors",
666
+ "model.visual.blocks.7.norm1.weight": "model-00001-of-00002.safetensors",
667
+ "model.visual.blocks.7.norm2.bias": "model-00001-of-00002.safetensors",
668
+ "model.visual.blocks.7.norm2.weight": "model-00001-of-00002.safetensors",
669
+ "model.visual.blocks.8.attn.proj.bias": "model-00001-of-00002.safetensors",
670
+ "model.visual.blocks.8.attn.proj.weight": "model-00001-of-00002.safetensors",
671
+ "model.visual.blocks.8.attn.qkv.bias": "model-00001-of-00002.safetensors",
672
+ "model.visual.blocks.8.attn.qkv.weight": "model-00001-of-00002.safetensors",
673
+ "model.visual.blocks.8.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
674
+ "model.visual.blocks.8.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
675
+ "model.visual.blocks.8.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
676
+ "model.visual.blocks.8.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
677
+ "model.visual.blocks.8.norm1.bias": "model-00001-of-00002.safetensors",
678
+ "model.visual.blocks.8.norm1.weight": "model-00001-of-00002.safetensors",
679
+ "model.visual.blocks.8.norm2.bias": "model-00001-of-00002.safetensors",
680
+ "model.visual.blocks.8.norm2.weight": "model-00001-of-00002.safetensors",
681
+ "model.visual.blocks.9.attn.proj.bias": "model-00001-of-00002.safetensors",
682
+ "model.visual.blocks.9.attn.proj.weight": "model-00001-of-00002.safetensors",
683
+ "model.visual.blocks.9.attn.qkv.bias": "model-00001-of-00002.safetensors",
684
+ "model.visual.blocks.9.attn.qkv.weight": "model-00001-of-00002.safetensors",
685
+ "model.visual.blocks.9.mlp.linear_fc1.bias": "model-00001-of-00002.safetensors",
686
+ "model.visual.blocks.9.mlp.linear_fc1.weight": "model-00001-of-00002.safetensors",
687
+ "model.visual.blocks.9.mlp.linear_fc2.bias": "model-00001-of-00002.safetensors",
688
+ "model.visual.blocks.9.mlp.linear_fc2.weight": "model-00001-of-00002.safetensors",
689
+ "model.visual.blocks.9.norm1.bias": "model-00001-of-00002.safetensors",
690
+ "model.visual.blocks.9.norm1.weight": "model-00001-of-00002.safetensors",
691
+ "model.visual.blocks.9.norm2.bias": "model-00001-of-00002.safetensors",
692
+ "model.visual.blocks.9.norm2.weight": "model-00001-of-00002.safetensors",
693
+ "model.visual.deepstack_merger_list.0.linear_fc1.bias": "model-00001-of-00002.safetensors",
694
+ "model.visual.deepstack_merger_list.0.linear_fc1.weight": "model-00001-of-00002.safetensors",
695
+ "model.visual.deepstack_merger_list.0.linear_fc2.bias": "model-00001-of-00002.safetensors",
696
+ "model.visual.deepstack_merger_list.0.linear_fc2.weight": "model-00001-of-00002.safetensors",
697
+ "model.visual.deepstack_merger_list.0.norm.bias": "model-00001-of-00002.safetensors",
698
+ "model.visual.deepstack_merger_list.0.norm.weight": "model-00001-of-00002.safetensors",
699
+ "model.visual.deepstack_merger_list.1.linear_fc1.bias": "model-00001-of-00002.safetensors",
700
+ "model.visual.deepstack_merger_list.1.linear_fc1.weight": "model-00001-of-00002.safetensors",
701
+ "model.visual.deepstack_merger_list.1.linear_fc2.bias": "model-00001-of-00002.safetensors",
702
+ "model.visual.deepstack_merger_list.1.linear_fc2.weight": "model-00001-of-00002.safetensors",
703
+ "model.visual.deepstack_merger_list.1.norm.bias": "model-00001-of-00002.safetensors",
704
+ "model.visual.deepstack_merger_list.1.norm.weight": "model-00001-of-00002.safetensors",
705
+ "model.visual.deepstack_merger_list.2.linear_fc1.bias": "model-00001-of-00002.safetensors",
706
+ "model.visual.deepstack_merger_list.2.linear_fc1.weight": "model-00001-of-00002.safetensors",
707
+ "model.visual.deepstack_merger_list.2.linear_fc2.bias": "model-00001-of-00002.safetensors",
708
+ "model.visual.deepstack_merger_list.2.linear_fc2.weight": "model-00001-of-00002.safetensors",
709
+ "model.visual.deepstack_merger_list.2.norm.bias": "model-00001-of-00002.safetensors",
710
+ "model.visual.deepstack_merger_list.2.norm.weight": "model-00001-of-00002.safetensors",
711
+ "model.visual.merger.linear_fc1.bias": "model-00001-of-00002.safetensors",
712
+ "model.visual.merger.linear_fc1.weight": "model-00001-of-00002.safetensors",
713
+ "model.visual.merger.linear_fc2.bias": "model-00001-of-00002.safetensors",
714
+ "model.visual.merger.linear_fc2.weight": "model-00001-of-00002.safetensors",
715
+ "model.visual.merger.norm.bias": "model-00001-of-00002.safetensors",
716
+ "model.visual.merger.norm.weight": "model-00001-of-00002.safetensors",
717
+ "model.visual.patch_embed.proj.bias": "model-00001-of-00002.safetensors",
718
+ "model.visual.patch_embed.proj.weight": "model-00001-of-00002.safetensors",
719
+ "model.visual.pos_embed.weight": "model-00001-of-00002.safetensors"
720
+ }
721
+ }
ADEn-CFJ-KL0/checkpoint-292/optimizer.pt ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:1f509c3d11ffd70b771733370f781da587304ccf9fddab479b19e07fe287d9e1
3
+ size 16090226537
ADEn-CFJ-KL0/checkpoint-292/rng_state_0.pth ADDED
@@ -0,0 +1,3 @@
 
 
 
 
1
+ version https://git-lfs.github.com/spec/v1
2
+ oid sha256:e44cbebe55d26f3995cd1a90005bbe51ab71b15a540c44b91b3a1ab0ed261a9d
3
+ size 14917