Commit Graph

Select branches

Hide Pull Requests

master

website

#132

#136

#144

#162

#189

#2

#204

#205

#214

#214

#237

#240

#240

#262

#29

#315

#317

#323

#331

#34

#349

#354

#376

#377

#383

#385

#394

#409

#412

#42

#421

#421

#424

#43

#44

#442

#443

#452

#478

#478

#491

#493

#497

#497

#503

#507

#507

#509

#513

#518

#518

#521

#521

#523

#523

#524

#524

#528

#534

#536

#539

#54

#543

#569

#569

#570

#571

#577

#579

#586

#59

#591

#594

#598

#599

#599

#609

#621

#63

#643

#653

#658

#663

#663

#664

#666

#666

#671

#694

#696

#698

#700

#708

#708

#710

#720

#725

#731

#738

#753

#756

#757

#759

#762

#762

#763

#769

#77

#770

#770

#778

#778

#780

#780

#784

#784

#785

#789

#789

#791

#792

#798

#802

#803

#807

#807

#808

#809

#809

#811

#811

#812

#813

#814

#815

#817

#818

#818

#821

#825

#829

#831

#831

#832

#833

#833

#836

#837

#837

#840

#843

#843

#844

#844

#847

#851

#852

#852

#854

#855

#857

#859

#86

#860

#861

#862

#863

#864

#865

#866

#866

#867

#868

#869

#869

#870

#870

#871

#871

#873

#874

#876

#876

#877

#879

#881

#881

#882

#882

#883

#883

#886

#886

#888

#888

#889

#889

#891

#891

#893

#894

#894

#90

#95

minimind-v1

v2

Mono Color

• edc8d26189 update structure image jingyaogong 2025-04-01 16:11:54 +0800
• 73bfbcf1a5 rmsnorm float convert jingyaogong 2025-04-01 16:03:44 +0800
• bf81fd5f5e rmsnorm float convert jingyaogong 2025-04-01 16:03:44 +0800
• ece40de732
  Merge 1c884f47af into e369b33265 Eric 2025-04-01 13:47:59 +0800
• 97d17c40f4 fix chat mask bug jingyaogong 2025-04-01 13:44:55 +0800
• e369b33265 fix chat mask bug jingyaogong 2025-04-01 13:44:55 +0800
• 9ac9343dc6 delete __pycache__ jingyaogong 2025-04-01 11:51:54 +0800
• 258507ff89 delete __pycache__ jingyaogong 2025-04-01 11:51:54 +0800
• 547e0ab2d6
  Little typo SeanHH86 2025-03-09 14:15:45 +0800
• 1c884f47af fix load model and lr update Eric 2025-03-01 00:40:01 +0800
• dc0708af11 add mla, fix model dtype, improve codes Eric 2025-03-01 00:01:17 +0800
• e10d7493fb Merge branch 'integrate-swanlab' of https://github.com/ShaohonChen/minimind into integrate-swanlab ShaohonChen 2025-02-28 14:51:33 +0800
• a2c58bb7da Integrate SwanLab for training log tracking ShaohonChen 2025-02-28 14:38:50 +0800
• fecc4a202e Integrate SwanLab for training log tracking ShaohonChen 2025-02-28 14:38:50 +0800
• d9ad86500f fix bug and typo mingkun 2025-02-26 09:10:23 +0800
• 14244bc23e refact and fix bug mingkun 2025-02-25 23:25:06 +0800
• 9805b9cfc6 update interactive notebook mingkun 2025-02-25 23:01:11 +0800
• 534d4e2c1a update interactive notebook mingkun 2025-02-25 23:00:46 +0800
• 9f405cafe3 add interative notebook mingkun 2025-02-23 21:22:41 +0800
• 706640a4b9 add ipynb mingkun 2025-02-23 21:22:18 +0800
• e74a6c3d9b update readme gongjy 2025-02-23 20:07:26 +0800
• 04b56ea86c update readme gongjy 2025-02-23 20:07:26 +0800
• d37481f48c Add the interface testing interface for model API deployment. jingsongliujing 2025-02-21 17:21:27 +0800
• 54ac9e4462 add smart gradient accumulation powermano 2025-02-21 17:09:35 +0800
• 3b9f2a70d1 update tokenizer load gongjy 2025-02-19 23:24:29 +0800
• e34d4e9371 update tokenizer load gongjy 2025-02-19 23:24:29 +0800
• 56c7ee09da update images gongjy 2025-02-19 22:59:42 +0800
• 45c0d12049 update images gongjy 2025-02-19 22:59:42 +0800
• 03c33d8a2e update images gongjy 2025-02-19 22:55:45 +0800
• ccf2cc6189 update images gongjy 2025-02-19 22:54:57 +0800
• f475e4e407 update images gongjy 2025-02-19 22:54:57 +0800
• f3f651408d
  Add ckp_dir and tokenizer path for train_distill_reason.py xunuohope1107 2025-02-19 11:52:29 +0800
• 1cc496d08b
  Add tokenizer path for eval_model.py xunuohope1107 2025-02-19 11:19:16 +0800
• 45a4bb3a0f
  Fix lora save path xunuohope1107 2025-02-19 10:38:26 +0800
• 68762f084a
  Add ckp_dir and tokenizer path for train_lora.py xunuohope1107 2025-02-19 10:18:26 +0800
• 05b0a06aaa update structure figure gongjy 2025-02-18 23:36:13 +0800
• d1893efac2 update structure figure gongjy 2025-02-18 23:35:16 +0800
• ef7dff9fd4 update structure figure gongjy 2025-02-18 23:35:16 +0800
• a5a45b6411 update model structure figure gongjy 2025-02-18 23:25:28 +0800
• 73534cad18 update structure figure gongjy 2025-02-18 23:24:51 +0800
• dcf5fcdb08 update structure figure gongjy 2025-02-18 23:24:51 +0800
• 5d3f3449ed
  Add ckp_dir and tokenizer path for train_dpo.py xunuohope1107 2025-02-18 16:51:22 +0800
• 44f30197ac
  Add ckp_dir and tokenizer path xunuohope1107 2025-02-18 16:36:29 +0800
• 391e26f07d update generate args gongjy 2025-02-15 23:56:09 +0800
• 844e79148c update generate args gongjy 2025-02-15 23:56:09 +0800
• 3236db14fc update generate args gongjy 2025-02-15 23:55:10 +0800
• 19b388cd87 update generate args gongjy 2025-02-15 23:55:10 +0800
• fb259aefac update cis init gongjy 2025-02-15 20:26:34 +0800
• 5b65bc767e update cis init gongjy 2025-02-15 20:26:34 +0800
• 06152a106e update web_demo gongjy 2025-02-14 19:38:55 +0800
• c1a77f5c0f update web_demo gongjy 2025-02-14 19:38:55 +0800
• 4985f9df37 update web_demo gongjy 2025-02-14 19:37:27 +0800
• d519d2a233 update web_demo gongjy 2025-02-14 19:37:27 +0800
• 4499e77a49 fix bug gongjy 2025-02-13 21:07:43 +0800
• e7ed05834b fix bug gongjy 2025-02-13 21:07:43 +0800
• d0c0dd6e66 fix bugs gongjy 2025-02-13 20:56:14 +0800
• b5d10d9a7d fix bugs gongjy 2025-02-13 20:56:14 +0800
• 00316e9b41 update ckp-path gongjy 2025-02-12 20:34:47 +0800
• 416cc90b58 update ckp-path gongjy 2025-02-12 20:34:47 +0800
• e53b90fb8b update lr gongjy 2025-02-11 23:53:48 +0800
• bab480073e update lr gongjy 2025-02-11 23:53:48 +0800
• 9f6c951945 update lr gongjy 2025-02-11 23:52:40 +0800
• d2f5ef4355 update lr gongjy 2025-02-11 23:52:40 +0800
• 0eacfad745 update readme gongjy 2025-02-10 23:34:52 +0800
• fea5b0eafc update readme gongjy 2025-02-10 23:34:52 +0800
• df2fda0365 update markdown gongjy 2025-02-10 23:22:53 +0800
• 291c19dc5e update markdown gongjy 2025-02-10 23:22:53 +0800
• 6dc245e7e5 update markdown gongjy 2025-02-10 23:19:23 +0800
• 6f383e29fb update markdown gongjy 2025-02-10 23:19:23 +0800
• 68c9dce946 update readme gongjy 2025-02-10 22:25:35 +0800
• 97886fef2e update readme gongjy 2025-02-10 22:25:35 +0800
• 6495bf9f65 update readme gongjy 2025-02-10 22:22:35 +0800
• be9b434379 update readme gongjy 2025-02-10 22:22:35 +0800
• ed48b61b63 update html gongjy 2025-02-10 20:46:20 +0800
• 9550aadeba update readme gongjy 2025-02-10 13:32:01 +0800
• ddb7e666a3 update readme gongjy 2025-02-10 13:32:01 +0800
• 5f7980085f update readme gongjy 2025-02-10 13:30:55 +0800
• 0c5104885a update readme gongjy 2025-02-10 13:30:55 +0800
• 4134228fcc update readme gongjy 2025-02-10 11:55:09 +0800
• dd7a7ef730 update readme gongjy 2025-02-10 11:55:09 +0800
• 33d291fc4a update readme gongjy 2025-02-10 11:44:43 +0800
• fe2f1199ac update readme gongjy 2025-02-10 11:44:43 +0800
• 724b95310e update readme gongjy 2025-02-10 11:14:52 +0800
• c2e67c25f7 update readme gongjy 2025-02-10 11:14:52 +0800
• 7a92470feb update track gongjy 2025-02-10 00:32:33 +0800
• b60fd11f85 update track gongjy 2025-02-10 00:32:33 +0800
• 9ba14add38 update minimind2 gongjy 2025-02-10 00:22:10 +0800
• 56adf84170 update readme gongjy 2025-02-10 00:16:54 +0800
• 4c2b283b93 update readme gongjy 2025-02-10 00:16:54 +0800
• be1a8a32fb update config gongjy 2025-02-10 00:14:11 +0800
• c9ca0f57dc update config gongjy 2025-02-10 00:14:11 +0800
• 9c8f6200bd update online demo gongjy 2025-02-09 23:55:59 +0800
• 30f8614c97 update online demo gongjy 2025-02-09 23:55:59 +0800
• daf9e3ab7c update scripts file gongjy 2025-02-09 23:52:50 +0800
• 29d6cd9cd2 update scripts file gongjy 2025-02-09 23:52:50 +0800
• 3fb8fcbf3d add minimind2 gongjy 2025-02-09 23:49:47 +0800
• 58e3af0359 add minimind2 gongjy 2025-02-09 23:49:47 +0800
• 41020c161f
  Update README.md Carlo 2025-02-07 11:25:14 +0800
• 5f84ee6370 fix weight initialization for residual block CohleM 2025-02-03 15:50:50 +0545
• 19db1a10ed fix 5-dpo train guomin 2025-01-31 23:21:43 +0800