64 Commits

Author	SHA1	Message	Date
hoshi-hiyouga	b67085e13a	Merge branch 'main' into feat/support_ms ... Former-commit-id: 6382efec52	2023-12-12 17:55:32 +08:00
xingjun.wang	879209829e	update args for MsDataset.load ... Former-commit-id: 09533e95ed	2023-12-12 13:02:54 +08:00
hiyouga	bd28dd0fe6	update readme ... Former-commit-id: 8cace77808	2023-12-12 11:44:30 +08:00
hiyouga	b641e9e97e	fix #1784 ... Former-commit-id: 28d5de7e78	2023-12-09 20:53:18 +08:00
yuze.zyz	c523613f0a	support ms dataset ... Former-commit-id: 9c2247d700	2023-12-08 18:00:57 +08:00
hiyouga	1cb390b9b2	implement rm server #1543 ... Former-commit-id: 7df4f3ab20	2023-12-03 20:52:54 +08:00
hiyouga	c60e79c12e	patch modelscope ... Former-commit-id: bd42c229b0	2023-12-01 22:53:15 +08:00
hoshi-hiyouga	9a26819a58	Merge branch 'main' into feat/support_ms ... Former-commit-id: 00f5c9ee16	2023-12-01 20:23:46 +08:00
hiyouga	e964fa7df7	fix err hint ... Former-commit-id: a5a248d569	2023-12-01 17:13:22 +08:00
yuze.zyz	e08e0e5814	support ms ... Former-commit-id: d38a2e7341	2023-11-29 20:36:55 +08:00
hiyouga	ae1048db6d	fix #1659 ... Former-commit-id: 475a3fa0f4	2023-11-28 20:52:28 +08:00
hiyouga	b015ac35d8	support export size setting ... Former-commit-id: 859a6ea942	2023-11-26 18:34:09 +08:00
hiyouga	f06c4c8f7a	update ppo trainer ... Former-commit-id: 5021062493	2023-11-20 21:39:15 +08:00
Yuchen Han	ec910a87c0	Update finetuning_args.py ... Former-commit-id: b24635d22b	2023-11-17 00:15:51 -08:00
hiyouga	678052a7ef	fix rlhf callback ... Former-commit-id: 1817ffc86f	2023-11-16 03:26:19 +08:00
hiyouga	b71da932eb	fix bug in PPO training ... Former-commit-id: 856522a3df	2023-11-16 02:32:54 +08:00
hiyouga	f441932bd1	support full-parameter PPO ... Former-commit-id: ce78303600	2023-11-16 02:08:04 +08:00
hiyouga	e30290444a	support multiple modules in freeze training #1514 ... Former-commit-id: 4907452d95	2023-11-15 17:08:18 +08:00
hiyouga	8387f3011c	fix #1494 ... Former-commit-id: d125ef5535	2023-11-14 18:07:20 +08:00
hiyouga	125587b187	refactor evaluation, upgrade trl to 074 ... Former-commit-id: 442aefb925	2023-11-13 22:20:35 +08:00
hiyouga	55e097aaac	add todo ... Former-commit-id: a0c31c68c4	2023-11-10 14:38:18 +08:00
hiyouga	6ee32cf71c	tiny fix ... Former-commit-id: 415bca900e	2023-11-09 17:20:49 +08:00
Yanqing	fc05fd52cf	Update finetuning_args.py ... 更新 chatglm/falcon/bloom 的 lora_target 的名称 Former-commit-id: 3684dffa14	2023-11-09 17:04:40 +08:00
hiyouga	91f406cc99	fix ppo train and dpo eval ... Former-commit-id: 01260d9754	2023-11-07 22:48:51 +08:00
hiyouga	1f2c56bff9	delete file ... Former-commit-id: 479d0af2dc	2023-11-07 16:20:12 +08:00
hiyouga	3d40bdb600	upgrade peft, fix #1088 #1411 ... Former-commit-id: b2a60905f3	2023-11-07 16:13:36 +08:00
hiyouga	a9db89a025	update data readme (zh) ... Former-commit-id: cc8ffa10d8	2023-11-02 23:42:49 +08:00
hiyouga	a1b0655457	support sharegpt format, add datasets ... Former-commit-id: a837172413	2023-11-02 23:10:04 +08:00
hiyouga	15cef791ba	fix #1356 ... Former-commit-id: dff128c7e3	2023-11-02 16:51:52 +08:00
hiyouga	22b3c913e9	fix #1325 ... Former-commit-id: 083787dbfe	2023-11-01 23:38:49 +08:00
hiyouga	fcfcac4858	support dataset cache ... Former-commit-id: 3fe7df628d	2023-10-26 21:48:45 +08:00
hiyouga	d6c77d9196	reimplement neftune ... Former-commit-id: 7b4acf7265	2023-10-22 16:15:08 +08:00
anvie	3635823fbe	add NEFTune optimization ... Former-commit-id: 57fb40aa04	2023-10-21 13:24:10 +07:00
hiyouga	95697652f1	fix #1232 ... Former-commit-id: b665e9e133	2023-10-20 23:28:52 +08:00
hiyouga	4930118761	fix #1218 ... Former-commit-id: 7a11a42dfd	2023-10-19 16:17:41 +08:00
hiyouga	f3fa47fa7d	refactor export, fix #1190 ... Former-commit-id: ea82f8a82a	2023-10-15 16:01:48 +08:00
hiyouga	e585c789ce	fix #1184 ... Former-commit-id: af18b0dce7	2023-10-14 19:20:11 +08:00
hiyouga	2562376f84	fix ppo args ... Former-commit-id: 11bd271364	2023-10-11 23:40:50 +08:00
hiyouga	c9d1cd108d	refactor model_dtype, fix PPO trainer ... Former-commit-id: 2818af0b09	2023-10-11 23:16:01 +08:00
hiyouga	deb17942ab	fix layer norm dtype ... Former-commit-id: 84b7486885	2023-09-28 00:25:55 +08:00
hiyouga	927ff702ff	refactor finetuning Args ... Former-commit-id: 620efe1d8d	2023-09-27 22:28:06 +08:00
hiyouga	108c31e1fc	support LongLoRA ... Former-commit-id: 90375f600d	2023-09-27 21:55:50 +08:00
hiyouga	4581d09fa6	fix #944 ... Former-commit-id: 338b8664ed	2023-09-21 19:51:02 +08:00
hiyouga	8ab5566dc0	support FlashAttention2 ... Former-commit-id: d8aa1404be	2023-09-10 20:43:56 +08:00
hiyouga	9ed4bb63d4	change to right-padding, update reward score #803 ... Former-commit-id: 8ea32e4046	2023-09-08 20:04:31 +08:00
hiyouga	a4fd976048	refactor dataset_attr, add eos in pt, fix #757 ... Former-commit-id: a9d1fb72f7	2023-09-01 19:00:45 +08:00
codemayq	2b979d39f2	add stage in DatasetAttr ... Former-commit-id: ba94c8729d	2023-08-23 20:54:53 +08:00
hiyouga	802494e20a	update template ... Former-commit-id: 4318347d3f	2023-08-22 19:46:09 +08:00
hiyouga	b88f0b396c	support ppo score norm (trl 0.5.1.dev required) ... Former-commit-id: 53e33418d0	2023-08-18 12:02:42 +08:00
hiyouga	03edfd07e7	fix PPO trainer #551 , update readme ... Former-commit-id: 9020524418	2023-08-18 11:43:10 +08:00