Commit Graph

  • 3f1a7cc25b [fix] ddp exit hang master jingyaogong 2026-06-01 17:50:39 +08:00
  • 4a68da72d5 [fix] lora dims jingyaogong 2026-05-31 13:38:51 +08:00
  • 4497610ec0 [fix] issue#771 jingyaogong 2026-05-19 17:40:03 +08:00
  • 9da8e1ab18 [update] requirements jingyaogong 2026-05-16 18:08:37 +08:00
  • dddedc6881 [fix] repetition_penalty jingyaogong 2026-05-07 19:08:52 +08:00
  • 802c15b2b4 [feat] reduce RL memory jingyaogong 2026-05-06 15:07:28 +08:00
  • e73a407f7a Merge pull request #759 from TKiteRunner/fix/grpo-oom-reorder-rewards jingyaogong 2026-05-06 15:00:17 +08:00
  • 10776417aa fix: resolve CUDA OOM in train_grpo.py on GPUs with <=8GB VRAM TKiteRunner 2026-05-06 14:14:15 +08:00
  • 5020dc9dd4 [update] readme jingyaogong 2026-05-06 13:41:46 +08:00
  • bdee223036 [fix] inference bug jingyaogong 2026-05-03 20:48:48 +08:00
  • 06d882e4ef [update] readme jingyaogong 2026-05-01 12:06:47 +08:00
  • da865af63d [update] readme jingyaogong 2026-04-28 17:22:25 +08:00
  • 773e451b11 [fix] bugs jingyaogong 2026-04-27 19:16:08 +08:00
  • 6361510016 [fix] rollout bugs jingyaogong 2026-04-27 17:54:09 +08:00
  • d4c6bc5c7e [update] readme jingyaogong 2026-04-27 10:59:41 +08:00
  • 24896cd2c4 [update] readme jingyaogong 2026-04-24 20:16:06 +08:00
  • e2fc397176 [update] readme jingyaogong 2026-04-24 20:14:10 +08:00
  • 693fb1ccf1 [update] readme jingyaogong 2026-04-21 14:34:46 +08:00
  • 5416a44471 [fix] bugs jingyaogong 2026-04-21 13:03:34 +08:00
  • 1718e9a44d [fix] transformers-5.x jingyaogong 2026-04-19 23:48:54 +08:00
  • 5704766352 [update] tie embedding jingyaogong 2026-04-19 21:57:28 +08:00
  • 1ea113ea2c [update] readme jingyaogong 2026-04-19 14:51:47 +08:00
  • 487f78754d [update] readme jingyaogong 2026-04-10 10:55:24 +08:00
  • e796b8028a [fix] lora compile jingyaogong 2026-04-10 00:01:21 +08:00
  • b2488e6440 [update] readme jingyaogong 2026-04-09 19:00:41 +08:00
  • 939dc8ff42 [update] readme jingyaogong 2026-04-09 18:54:17 +08:00
  • cadacabecb [update] bench jingyaogong 2026-04-09 17:12:48 +08:00
  • 5351424bf0 [fix] lora moe jingyaogong 2026-04-09 16:36:48 +08:00
  • aa3e6affa1 [update] add a comment jingyaogong 2026-04-09 15:09:58 +08:00
  • 299facca84 [update] image website jingyaogong 2026-04-04 14:55:03 +08:00
  • 25a7edcd6f [update] image jingyaogong 2026-04-04 14:54:13 +08:00
  • cacf1d4cd0 [update] readme jingyaogong 2026-04-04 11:25:21 +08:00
  • 2ab6455d9d [update] open causal jingyaogong 2026-04-02 15:28:58 +08:00
  • 9348fde743 [update] readme jingyaogong 2026-04-02 15:28:29 +08:00
  • 90cd275524 [update] readme jingyaogong 2026-04-01 14:00:21 +08:00
  • b7e0ae21d6 [update] default model jingyaogong 2026-03-31 13:40:16 +08:00
  • b1865f75c2 [update] random seed jingyaogong 2026-03-27 21:20:02 +08:00
  • 6b0b0c5e2f [update] fp16 inference jingyaogong 2026-03-27 16:29:46 +08:00
  • 88e675dc2c [update] image jingyaogong 2026-03-26 15:35:42 +08:00
  • b8b3d35257 [update] change default seq_len jingyaogong 2026-03-26 10:09:06 +08:00
  • 101d7df2da [update] minimind-3 jingyaogong 2026-03-24 15:59:39 +08:00
  • 83e52f6a27 Merge pull request #698 from readlnh/master jingyaogong 2026-03-24 13:41:20 +08:00
  • cf4b49a348 [fix] align log/save last-step check and ETA with 1-indexed step readlnh 2026-03-24 02:01:40 +01:00
  • d25500d363 [fix] gradient accumulation step alignment readlnh 2026-03-24 01:45:04 +01:00
  • c3e83db369 [update] minimind intro jingyaogong 2026-03-24 00:39:40 +08:00
  • 0de02a3e6c [update] minimind intro jingyaogong 2026-03-24 00:35:33 +08:00
  • 349e74ec7b [update] empty_think_ratio jingyaogong 2026-02-06 19:15:21 +08:00
  • 288e1ac02a [update] empty_think_ratio jingyaogong 2026-02-06 01:36:02 +08:00
  • ccc190da05 [feat] data process jingyaogong 2026-02-06 01:17:57 +08:00
  • 11a44340ba [update] save interval jingyaogong 2026-01-30 20:30:50 +08:00
  • 04616c41a5 [update] safe half jingyaogong 2026-01-30 20:29:31 +08:00
  • fea69cf338 [fix] data skip jingyaogong 2026-01-18 16:56:29 +08:00
  • f7ffdf1fdb [update] shuffle data jingyaogong 2026-01-18 16:39:34 +08:00
  • 3a5aba82db [fix] max length jingyaogong 2026-01-17 13:26:14 +08:00
  • 714abcf802 [update] pretrain load jingyaogong 2026-01-17 12:00:17 +08:00
  • aa539a824a [update] align mask jingyaogong 2026-01-15 11:20:41 +08:00
  • c090b69c4d [update] align loss jingyaogong 2026-01-15 00:56:32 +08:00
  • e119db8478 [fix] compile unpack jingyaogong 2026-01-14 20:13:32 +08:00
  • 81d24a4f16 [feat] add compile jingyaogong 2026-01-14 14:42:30 +08:00
  • 1279a61681 [update] prompt prefill jingyaogong 2026-01-13 17:46:54 +08:00
  • 05d0b216f6 [update] show speed jingyaogong 2026-01-07 23:33:47 +08:00
  • df89069362 [update] params log jingyaogong 2026-01-07 23:08:45 +08:00
  • f55d4c32a0 [update] mask log jingyaogong 2026-01-07 22:12:26 +08:00
  • 20a43d7db0 [update] readme jingyaogong 2026-01-07 00:58:38 +08:00
  • 7641985d14 [update] simplify loader jingyaogong 2026-01-06 01:20:52 +08:00
  • 0b4a8ad4aa [update] readme jingyaogong 2026-01-06 01:18:10 +08:00
  • 07364c3fbe [update] rename train tokenizer jingyaogong 2026-01-06 01:17:33 +08:00
  • 9830915d87 [update] readme jingyaogong 2026-01-05 23:15:25 +08:00
  • 4e73f34823 [update] rename reason jingyaogong 2026-01-05 23:11:49 +08:00
  • a8455ca8a3 [fix] messages num jingyaogong 2026-01-04 11:03:16 +08:00
  • 42a4e8c86a [fix] dist cleanup jingyaogong 2026-01-02 22:25:55 +08:00
  • 9d898576ac [update] aux loss jingyaogong 2026-01-01 22:37:49 +08:00
  • c65335b56f [fix] experts unused jingyaogong 2025-12-31 21:47:04 +08:00
  • bc8fd82166 [fix] layers set 8 jingyaogong 2025-12-31 21:06:37 +08:00
  • 5dd4df7e18 [fix] moe unused jingyaogong 2025-12-31 21:00:06 +08:00
  • 9236260a4a [feat] get params jingyaogong 2025-12-31 20:46:59 +08:00
  • 288a1d7212 [feat] get params jingyaogong 2025-12-31 20:44:34 +08:00
  • eead9538b2 [feat] update config jingyaogong 2025-12-31 10:29:13 +08:00
  • 6242980917 [feat] update lr jingyaogong 2025-12-31 10:27:09 +08:00
  • 936d105e9b [feat] compatible tokenizer jingyaogong 2025-12-31 10:26:46 +08:00
  • 4a5c9f5ece [feat] stream load data jingyaogong 2025-12-28 16:58:52 +08:00
  • 7eae14f3ce [feat] remove empty_cache jingyaogong 2025-12-27 07:14:36 +08:00
  • 0afc6d6741 [fix] table flow jingyaogong 2025-12-24 13:43:10 +08:00
  • 11b962da06 [feat] explicit left padding jingyaogong 2025-12-23 18:59:48 +08:00
  • a9c56b20e9 [fix] lora weight jingyaogong 2025-12-22 21:27:29 +08:00
  • 048d84abc7 Merge pull request #594 from whiteswordLI/fix/lora-load-ddp-weights jingyaogong 2025-12-22 21:19:16 +08:00
  • 3a18fdd666 Fix: support loading DDP-saved LoRA weights for inference whitesword 2025-12-22 20:50:25 +08:00
  • fe24501602 [feat] adjust seq length jingyaogong 2025-12-14 20:41:58 +08:00
  • fa82707c9c [feat] update readme jingyaogong 2025-12-11 15:45:50 +08:00
  • 5129f0e2a2 [fix] dtype & lr jingyaogong 2025-12-09 13:01:38 +08:00
  • aa7dc0f61e Merge pull request #571 from dyhuachi/dyhuachi-patch-1 jingyaogong 2025-12-09 12:59:11 +08:00
  • bf3878ace8 [fix] Refactor get_lr function to include min_lr calculation dyhuachi 2025-12-06 17:09:51 +08:00
  • ecd1ae1563 [fix] reduce aux_loss_alpha jingyaogong 2025-12-05 23:08:29 +08:00
  • 5e1447b913 [fix] cuda memory #559 jingyaogong 2025-12-01 16:17:43 +08:00
  • 151fdf7e76 [feat] update yarn jingyaogong 2025-12-01 16:15:05 +08:00
  • 6b86ea399a [feat] release memory jingyaogong 2025-11-27 19:39:49 +08:00
  • d7f4f4eab8 [fix] ppo mask jingyaogong 2025-11-19 23:39:02 +08:00
  • f5374dc87f [fix] model attn_mask jingyaogong 2025-11-19 22:26:53 +08:00
  • a044578d73 [fix] update model jingyaogong 2025-11-18 13:07:20 +08:00
  • ce9394670b Merge pull request #536 from yuyu5333/fix/attn_forward jingyaogong 2025-11-18 13:02:46 +08:00