672 Commits

Author	SHA1	Message	Date
hiyouga	64744dde89	support resize embeddings #1786	2023-12-11 17:50:02 +08:00
hiyouga	9ce1b0e2f2	use peft 0.7.0, fix #1561 #1764	2023-12-11 17:13:40 +08:00
hiyouga	28d5de7e78	fix #1784	2023-12-09 20:53:18 +08:00
yuze.zyz	9c2247d700	support ms dataset	2023-12-08 18:00:57 +08:00
hiyouga	d42c0b1d34	fix #1771 and temporarily fix #1764	2023-12-08 16:26:20 +08:00
hiyouga	e25f7bae16	add models	2023-12-06 13:33:18 +08:00
hiyouga	d3dccd0693	fix ppo trainer save logic	2023-12-04 19:00:19 +08:00
hiyouga	c9b166615c	fix #1715	2023-12-03 22:35:47 +08:00
hiyouga	438dea679b	release v0.3.3	2023-12-03 21:59:45 +08:00
hiyouga	8b681ee273	fix bug	2023-12-03 21:40:40 +08:00
hiyouga	747db40172	ppo support rm server	2023-12-03 21:38:51 +08:00
hiyouga	7df4f3ab20	implement rm server #1543	2023-12-03 20:52:54 +08:00
hiyouga	03d05991f8	fix #1707 #1710	2023-12-03 11:33:12 +08:00
hiyouga	b69763ff92	fix #1642	2023-12-02 00:37:53 +08:00
hiyouga	6e7af11b98	add xuanyuan models	2023-12-02 00:35:29 +08:00
hiyouga	f57445c7a0	fix gptq training	2023-12-02 00:27:15 +08:00
hiyouga	a973ce6e89	tiny fix	2023-12-01 23:37:10 +08:00
hiyouga	01e6c539b0	fix gptq model inference	2023-12-01 23:34:14 +08:00
hiyouga	662d9a3a4e	fix #1703	2023-12-01 22:55:41 +08:00
hiyouga	bd42c229b0	patch modelscope	2023-12-01 22:53:15 +08:00
hoshi-hiyouga	00f5c9ee16	Merge branch 'main' into feat/support_ms	2023-12-01 20:23:46 +08:00
yuze.zyz	5a2392f105	remove useless code	2023-12-01 17:28:23 +08:00
tastelikefeet	d9e52957e2	fix bug	2023-12-01 17:27:00 +08:00
hiyouga	a5a248d569	fix err hint	2023-12-01 17:13:22 +08:00
hiyouga	a51b8ec620	add err hint	2023-12-01 17:04:37 +08:00
yuze.zyz	5aa6751e52	add readme	2023-12-01 16:11:30 +08:00
hiyouga	e597d3c084	tiny fix	2023-12-01 15:58:50 +08:00
hoshi-hiyouga	fbc6220692	Merge pull request #1695 from Samge0/dev ... Improve："CUDA_VISIBLE_DEVICES" read from the env	2023-12-01 15:56:18 +08:00
hoshi-hiyouga	d043a4e7ba	Merge pull request #1690 from billvsme/main ... Improve get_current_device	2023-12-01 15:44:35 +08:00
hiyouga	bf6f6aeefe	fix #1696	2023-12-01 15:34:50 +08:00
tastelikefeet	8ce4d11e38	add model	2023-12-01 15:06:17 +08:00
samge	421d4de604	Improve："CUDA_VISIBLE_DEVICES" read from the env	2023-12-01 11:35:02 +08:00
billvsme	40dfcbc3d4	improve get_current_device	2023-11-30 22:40:35 +08:00
hiyouga	327d7f7efe	fix #1597	2023-11-30 21:47:06 +08:00
hiyouga	1585962eb7	fix #1668	2023-11-30 21:02:00 +08:00
hiyouga	a38dbf55e3	fix #1682	2023-11-30 20:03:32 +08:00
hiyouga	509abe8864	add models	2023-11-30 19:16:13 +08:00
yuze.zyz	fb2204c183	fix	2023-11-29 21:43:58 +08:00
yuze.zyz	d38a2e7341	support ms	2023-11-29 20:36:55 +08:00
hiyouga	77d1b14fc2	fix #1658	2023-11-28 20:57:24 +08:00
hiyouga	475a3fa0f4	fix #1659	2023-11-28 20:52:28 +08:00
hiyouga	859a6ea942	support export size setting	2023-11-26 18:34:09 +08:00
hiyouga	ff1c289229	support Yi-34B-Chat models	2023-11-23 19:31:49 +08:00
hiyouga	35c2da3eba	set version	2023-11-20 22:57:44 +08:00
hiyouga	9ea9380145	support GPTQ tuning #729 #1481 #1545 , fix chatglm template #1453 #1480 #1569	2023-11-20 22:52:11 +08:00
hiyouga	5021062493	update ppo trainer	2023-11-20 21:39:15 +08:00
hoshi-hiyouga	48211e3799	Merge pull request #1553 from hannlp/hans ... Change the default argument settings for PPO training	2023-11-20 20:32:55 +08:00
hiyouga	2a36fd5064	fix value head model resuming	2023-11-20 19:01:37 +08:00
hiyouga	99a3f06377	fix #1567	2023-11-20 18:46:36 +08:00
hiyouga	00baaa990e	better data streaming	2023-11-19 23:32:47 +08:00