826 Commits

Author	SHA1	Message	Date
hoshi-hiyouga	38a56706e0	Update utils.py	2024-04-16 17:29:30 +08:00
hoshi-hiyouga	a950f3b81d	Update patcher.py	2024-04-16 17:29:19 +08:00
hoshi-hiyouga	750cdf2e74	Update adapter.py	2024-04-16 17:28:12 +08:00
hoshi-hiyouga	4660703674	Update parser.py	2024-04-16 17:27:25 +08:00
hoshi-hiyouga	5b59ff4212	Update parser.py	2024-04-16 17:27:02 +08:00
hoshi-hiyouga	ec899cccf3	Update finetuning_args.py	2024-04-16 17:26:30 +08:00
Jonery	7ecb61822b	resolve gradient checkpointing issue.	2024-04-16 12:05:27 +08:00
Jonery	06c8908d3f	Feature BAdam	2024-04-15 23:15:27 +08:00
hiyouga	cce52351b5	update examples	2024-04-15 22:14:34 +08:00
hoshi-hiyouga	0e0942d388	Merge pull request #3276 from liu-zichen/fix_mixtral ... fix: turn on output_router_logits of mixtral	2024-04-15 15:38:16 +08:00
hiyouga	efc345c4b0	fix #3273	2024-04-15 15:32:58 +08:00
liuzc	9f4fe62386	fix: mixtral output_router_logits	2024-04-15 12:11:49 +08:00
hiyouga	c53a11b6fd	fix model card	2024-04-12 17:11:59 +08:00
hiyouga	232642a621	fix #3238	2024-04-12 14:28:11 +08:00
hiyouga	3dfe4cf611	set dev version	2024-04-11 20:27:34 +08:00
hiyouga	9d4c949461	release v0.6.2	2024-04-11 20:08:51 +08:00
hiyouga	51d0a1a19e	Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory	2024-04-10 23:58:18 +08:00
hiyouga	a99f5ed0b6	fix #3225	2024-04-10 23:57:59 +08:00
hoshi-hiyouga	98bc97d8d2	Update adapter.py	2024-04-10 00:57:51 +08:00
hoshi-hiyouga	2111b586b6	Update adapter.py	2024-04-10 00:57:30 +08:00
Erich Schubert	b5eefe5c4c	Pass additional_target to unsloth ... Fixes #3200	2024-04-09 17:53:40 +02:00
hiyouga	7f6c2486b8	fix quant infer and qwen2moe	2024-04-09 17:12:59 +08:00
hiyouga	9a99fbc86d	tiny fix	2024-04-08 21:28:39 +08:00
hoshi-hiyouga	4c6c4a0d88	Merge pull request #3161 from hiyouga/feature/add-mediatek-model ... support Breeze-7B	2024-04-08 20:56:51 +08:00
codingma	7b76b4ca08	add empty line	2024-04-07 18:28:08 +08:00
codingma	34bdcba017	rename template to breeze	2024-04-07 18:27:20 +08:00
codingma	5a780e9eec	rename template to breeze	2024-04-07 11:39:54 +08:00
codingma	2565a32bd9	support https://github.com/hiyouga/LLaMA-Factory/issues/3152	2024-04-07 11:34:01 +08:00
sliderSun	1d117b7bb6	fix spell error	2024-04-07 10:59:15 +08:00
sliderSun	21650d467c	support Qwen1.5-32B	2024-04-07 10:56:03 +08:00
sliderSun	77044d9ef4	support Qwen1.5-32B	2024-04-07 10:26:13 +08:00
hiyouga	a6d943804b	tiny fix	2024-04-04 02:19:03 +08:00
hiyouga	4b920f24d3	back to gradio 4.21 and fix chat	2024-04-04 02:07:20 +08:00
hiyouga	5ddcecda50	fix bug in latest gradio	2024-04-04 00:55:31 +08:00
hiyouga	7f6e412604	fix requires for windows	2024-04-03 21:56:43 +08:00
hiyouga	148bda353f	fix resize vocab at inference #3022	2024-04-03 18:14:24 +08:00
hiyouga	ce77d98872	fix #3116	2024-04-03 14:47:59 +08:00
hiyouga	92dab8a90b	simplify readme	2024-04-02 20:07:43 +08:00
hiyouga	b267aeb53f	add moe aux loss control #3085	2024-04-02 14:26:31 +08:00
hiyouga	9ddbe2866a	fix #3022	2024-04-02 13:58:39 +08:00
hiyouga	dd73a0c248	set dev version	2024-04-01 23:24:08 +08:00
hiyouga	4a6ca621c0	fix #3083	2024-04-01 22:53:52 +08:00
hiyouga	54b7d34908	add qwen1.5 moe	2024-04-01 21:49:40 +08:00
hiyouga	aee634cd20	fix #3077	2024-04-01 21:35:18 +08:00
hiyouga	eb259cc573	support infer 4bit model on GPUs #3023	2024-04-01 17:34:04 +08:00
hiyouga	d0842f6828	update webui	2024-04-01 16:23:28 +08:00
hiyouga	816d714146	fix ORPO loss	2024-04-01 14:42:41 +08:00
hiyouga	5b9b40403d	fix IPO and ORPO loss	2024-04-01 14:37:53 +08:00
hiyouga	5907216a1c	fix plots	2024-03-31 19:43:48 +08:00
hiyouga	68aaa4904b	use log1p in orpo loss ... https://github.com/huggingface/trl/pull/1491	2024-03-31 19:27:08 +08:00