Commit Graph

54 Commits (ef1c130a0368905470c2d8ca4550ccb02bc137dc)

Author SHA1 Message Date
jingyaogong 7546729893 [update] open causal 2026-04-02 15:28:58 +08:00
jingyaogong b24fcdc1f9 [update] minimind-3 2026-03-25 23:57:45 +08:00
jingyaogong b189f0046a [update] align loss 2026-01-15 00:56:32 +08:00
jingyaogong caf76fb884 [fix] compile unpack 2026-01-14 20:13:32 +08:00
jingyaogong f0f73a208e [update] prompt prefill 2026-01-13 17:46:54 +08:00
jingyaogong 3c56aca1c1 [update] aux loss 2026-01-01 22:41:46 +08:00
jingyaogong 5b87b9ad8a [fix] experts unused 2025-12-31 21:47:04 +08:00
jingyaogong 4cbca65883 [fix] lora weight 2025-12-22 21:27:29 +08:00
whitesword 65b648be32 Fix: support loading DDP-saved LoRA weights for inference 2025-12-22 20:50:25 +08:00
jingyaogong 37300329c5 [fix] dtype & lr 2025-12-09 13:01:38 +08:00
jingyaogong 7614a3bf90 [fix] reduce aux_loss_alpha 2025-12-05 23:08:29 +08:00
jingyaogong 295b9ad443 [feat] update yarn 2025-12-01 16:15:05 +08:00
jingyaogong cafc3b22df [feat] release memory 2025-11-27 19:39:49 +08:00
jingyaogong 21cadea5f5 [fix] model attn_mask 2025-11-19 22:26:53 +08:00
jingyaogong 7aef898647 [fix] update model 2025-11-18 13:07:20 +08:00
yuyu5333 9c29046d2e fix: attn_forwad when is_causal=True assert attn_mask is None 2025-11-18 03:17:17 +00:00
jingyaogong 00c24568dc [fix] restore 2025-10-23 19:00:06 +08:00
jingyaogong fa935a496e [fix] issue-431 2025-10-23 18:56:30 +08:00
jingyaogong 8bb98c9790 [fix] update model 2025-10-17 00:09:32 +08:00
jingyaogong 5343923e0f update lora 2025-04-27 15:45:06 +08:00
jingyaogong 7d81a0a6f0 fix bugs 2025-04-27 09:56:49 +08:00
jingyaogong be00d302ee 250426 2025-04-26 10:07:55 +08:00
jingyaogong e74843bd09 250426 2025-04-26 10:05:47 +08:00
jingyaogong 8081504f05 update moe note 2025-04-09 17:38:31 +08:00
jingyaogong c688c4fd79 update rlaif 2025-04-05 16:06:08 +08:00
jingyaogong 5701ff1aaa update generate 2025-04-05 15:53:55 +08:00
jingyaogong aab57d5dc5 add hidden state 2025-04-05 14:39:56 +08:00
jingyaogong 85cac44a38 update inference 2025-04-05 12:03:04 +08:00
jingyaogong 73bfbcf1a5 rmsnorm float convert 2025-04-01 16:03:44 +08:00
jingyaogong 97d17c40f4 fix chat mask bug 2025-04-01 13:44:55 +08:00
jingyaogong 9ac9343dc6 delete __pycache__ 2025-04-01 11:51:54 +08:00
gongjy 391e26f07d update generate args 2025-02-15 23:56:09 +08:00
gongjy 3236db14fc update generate args 2025-02-15 23:55:10 +08:00
gongjy fb259aefac update cis init 2025-02-15 20:26:34 +08:00
gongjy 3fb8fcbf3d add minimind2 2025-02-09 23:49:47 +08:00
gongjy 7840e6f270 update model 2024-10-20 15:13:58 +08:00
gongjy e232ed82bb update readme 2024-10-08 23:40:29 +08:00
gongjy 5e67759d1a update model (fix loss bug) 2024-09-29 16:58:48 +08:00
gongjy 682003cec6 Update data preprocessing methods 2024-09-27 17:19:03 +08:00
gongjy f351a61c8a Update data preprocessing methods 2024-09-27 16:19:30 +08:00
gongjy ef45699989 update model mask 2024-09-21 20:00:25 +08:00
gongjy e892df833b Efficient implementation of Inference KV cache 2024-09-21 00:01:05 +08:00
gongjy b38f16b436 Updated some explanations 2024-09-20 17:07:51 +08:00
gongjy beca801dc2 update some explain of the code 2024-09-20 17:04:16 +08:00
Ben 39e07cc79b 添加注释,方便学习者快速理解 2024-09-18 21:53:39 +08:00
gongjy bdf4be2add update minimind-v1-moe 2024-09-17 11:33:31 +08:00
gongjy 955fcecbeb update model 2024-09-16 16:59:52 +08:00
gongjy 6d688a01f7 update model 2024-09-16 15:29:57 +08:00
gongjy 64ae2050de update some config 2024-09-15 15:12:47 +08:00
gongjy cd3733dd50 update config 2024-09-15 15:09:21 +08:00