1279 Commits

Author	SHA1	Message	Date
hiyouga	8845e94f91	fix #4609 ... unwrap_model_for_generation(reward_model) is necessary for zero3 training	2024-07-03 19:45:51 +08:00
hiyouga	8b1172b910	tiny fix	2024-07-03 02:31:50 +08:00
hiyouga	71cdf8956e	tiny fix	2024-07-02 23:06:13 +08:00
hiyouga	821bb6660e	remove rlhf support for chatglm2&3	2024-07-02 23:03:17 +08:00
hiyouga	c13ae2df19	upcast logits	2024-07-02 22:32:05 +08:00
hiyouga	c47ab6c072	improve rlhf	2024-07-02 22:23:08 +08:00
hoshi-hiyouga	4e4b3cc905	Merge pull request #4651 from hzhaoy/add-telechat-1b ... Add TeleChat-1B	2024-07-02 17:56:43 +08:00
hzhaoy	57b7c00430	add TeleChat-1B	2024-07-02 17:49:04 +08:00
hiyouga	4c296001c4	fix ppo callbacks	2024-07-02 17:34:56 +08:00
hiyouga	73280b7dc7	tiny fix	2024-07-01 05:43:17 +08:00
hiyouga	8c41a0aa6d	tiny fix	2024-07-01 03:55:20 +08:00
hiyouga	1856a08e87	add eval acc	2024-07-01 03:51:20 +08:00
hiyouga	1771251ce3	fix #4402 #4617 ... Deprecate reserved_label_len arg	2024-07-01 01:19:27 +08:00
hiyouga	d74244d568	fix #4398 #4592	2024-06-30 21:28:51 +08:00
hiyouga	2f4b89ace1	loose gemma2 attention	2024-06-29 01:42:14 +08:00
hiyouga	4d35e218b1	bf16 by default, gemma2 attns ... Gemma2 finetuning cannot work until merging https://github.com/huggingface/transformers/pull/31674	2024-06-28 06:00:26 +08:00
hiyouga	64f4337dac	increase pissa_iter for stability	2024-06-28 03:18:54 +08:00
hiyouga	6f63050e1b	add Gemma2 models	2024-06-28 01:26:50 +08:00
hiyouga	8baf3b22b0	refactor pissa, improve llamaboard	2024-06-28 01:04:24 +08:00
hoshi-hiyouga	ef38daa0a4	Merge pull request #4580 from hzhaoy/bugfix-deepspeed-pissa ... Fix bug when using pissa method with deepspeed	2024-06-28 00:46:51 +08:00
hiyouga	8ed6b367e2	fix #4549	2024-06-28 00:41:58 +08:00
hiyouga	e44a4f07f0	tiny fix	2024-06-27 20:14:48 +08:00
faddddeout	f6b62f0070	Exit the process with the subprocess's return code when utilizing the CLI	2024-06-27 09:58:00 +00:00
hzhaoy	677c86594e	fix #4579	2024-06-27 13:49:57 +08:00
hiyouga	96a5044394	add quant checks	2024-06-27 01:12:25 +08:00
hiyouga	f17c9dfd84	tiny fix	2024-06-27 00:46:41 +08:00
hiyouga	29c710da3a	tiny fix	2024-06-27 00:36:04 +08:00
hiyouga	ad144c2265	support HQQ/EETQ #4113	2024-06-27 00:29:42 +08:00
hiyouga	addca926de	improve autogptq integration	2024-06-26 22:11:44 +08:00
hiyouga	8d6cd69ac4	fix #4458	2024-06-26 19:52:35 +08:00
hiyouga	59e0b4f616	fix #4556	2024-06-26 19:43:16 +08:00
hiyouga	555ca8d780	lint	2024-06-25 02:55:50 +08:00
hiyouga	1e9d0aa1e4	fix #4432	2024-06-25 02:34:04 +08:00
hiyouga	cc016461e6	fix #4379	2024-06-25 02:31:44 +08:00
hiyouga	095fab58d3	tiny fix about badam	2024-06-25 01:54:53 +08:00
hoshi-hiyouga	d0f953bf5b	Merge pull request #4352 from Ledzy/main ... [Enhancement] Support ZeRO-3 when using BAdam	2024-06-25 01:49:13 +08:00
hiyouga	41086059b1	tiny fix	2024-06-25 01:15:19 +08:00
hoshi-hiyouga	3bed18c644	Merge pull request #4409 from kno10/patch-2 ... Print help if no arguments given	2024-06-24 23:21:31 +08:00
hoshi-hiyouga	acb61f7ab7	Update cli.py	2024-06-24 23:21:10 +08:00
hoshi-hiyouga	def6d280db	Merge pull request #4417 from mMrBun/main ... Add tool_format parameter to rewrite templates for different function call formats.	2024-06-24 23:17:55 +08:00
hoshi-hiyouga	1240bd57d8	Update template.py	2024-06-24 23:12:59 +08:00
hoshi-hiyouga	dddfd516ee	Update loader.py	2024-06-24 23:06:18 +08:00
hiyouga	fca893d73c	fix #4410	2024-06-24 22:34:31 +08:00
hoshi-hiyouga	cc452c32c7	Merge pull request #4446 from stceum/bug-fix ... Bug Fix: `off` is parsed as `False` in yaml file	2024-06-24 21:41:28 +08:00
hoshi-hiyouga	e90c424f55	Update parser.py	2024-06-24 21:37:42 +08:00
stceum	3ed063f281	Bug Fix: off is parsed as False in yaml file, changed to disabled to avoid this.	2024-06-24 20:39:31 +08:00
hiyouga	e507e60638	update readme	2024-06-24 18:22:12 +08:00
mMrBun	20e2e6fdcb	Add tool_format to overwrite tool formatter template	2024-06-22 02:13:23 +08:00
hiyouga	db9a1912e3	remove dup template	2024-06-22 01:31:32 +08:00
hiyouga	3ce44dda99	fix api	2024-06-22 00:00:38 +08:00