304 Commits

Author	SHA1	Message	Date
codingma	645211dc01	1. change the task name format ... 2. delete split param in data_args.py	2024-07-15 09:55:33 +08:00
hiyouga	99ab7a8c1c	allow computing rouge in training	2024-07-15 01:16:26 +08:00
hiyouga	29ebcd75d5	fix up	2024-07-15 01:04:56 +08:00
hoshi-hiyouga	15b399a82f	Merge pull request #4691 from codemayq/feature-suppot-eval-dataset ... add eval dataset support	2024-07-15 01:00:34 +08:00
hoshi-hiyouga	cba673f491	Update data_args.py	2024-07-15 00:56:03 +08:00
hoshi-hiyouga	df52fb05b1	Update preprocess.py	2024-07-15 00:55:36 +08:00
hoshi-hiyouga	84e4047f8a	Update parser.py	2024-07-15 00:55:21 +08:00
hoshi-hiyouga	97a0e291c7	Update data_utils.py	2024-07-15 00:54:34 +08:00
hoshi-hiyouga	a5b809516e	Update loader.py	2024-07-15 00:50:06 +08:00
hoshi-hiyouga	3d39d74003	Update parser.py	2024-07-14 23:04:34 +08:00
hiyouga	88a20ba797	fix #4699 ... slow tokenizer for yi models	2024-07-14 15:34:22 +08:00
hiyouga	d3c01552e0	tiny fix	2024-07-14 10:56:45 +08:00
hiyouga	2f6af73da2	fix gemma2 attention	2024-07-13 23:33:45 +08:00
hoshi-hiyouga	5da54deb50	Merge pull request #4781 from hzhaoy/fix-dockerfile-cuda ... Fix cuda Dockerfile	2024-07-13 22:25:32 +08:00
hiyouga	6b48308ef9	fix #4792	2024-07-13 22:07:58 +08:00
hzhaoy	8bab99c582	tiny fix	2024-07-12 00:28:44 +08:00
hoshi-hiyouga	555194e150	Merge pull request #4700 from marko1616/patch-1 ... Fix Windows command preview	2024-07-10 13:51:50 +08:00
hoshi-hiyouga	39cd89ce17	Update callbacks.py	2024-07-10 13:32:20 +08:00
-.-	cff89a2e89	fix src/llamafactory/train/callbacks.py	2024-07-10 12:05:51 +08:00
hiyouga	51942acee8	fix #4731	2024-07-10 11:32:36 +08:00
hiyouga	fb0c400116	fix ppo trainer	2024-07-10 11:05:45 +08:00
hiyouga	2f09520c0d	fix #4742	2024-07-09 23:24:24 +08:00
hoshi-hiyouga	f84b007ebb	Update packages.py	2024-07-07 15:48:29 +08:00
Lian Junhong	322663bf90	chore: Update vllm_engine.py to support vllm version >= 0.5.1	2024-07-07 15:08:12 +08:00
hiyouga	a15782cb9f	fix #4705	2024-07-07 13:10:06 +08:00
marko1616	e0562521bb	Update utils.py ... In windows mutiline command should like command --arg1 xxx ` --arg2 xxx `	2024-07-06 20:40:13 +08:00
hiyouga	53b1002fb7	add codegeex4, internlm2.5	2024-07-06 16:16:47 +08:00
codingma	76f3bbcfc0	1. add custom eval dataset support ... 2. merge load dataset and split dataset function	2024-07-05 15:52:10 +08:00
hiyouga	9f33f1edf5	fix processors	2024-07-05 08:33:22 +08:00
hiyouga	e43809bced	fix #4683	2024-07-05 00:58:05 +08:00
hiyouga	ed232311e8	fix #4674	2024-07-05 00:41:03 +08:00
hiyouga	226a9e563f	Merge branch 'main' of https://github.com/hiyouga/LLaMA-Factory	2024-07-04 14:23:37 +08:00
hiyouga	1e27e8c776	fix #4677	2024-07-04 14:22:07 +08:00
hzhaoy	738df47748	tiny fix	2024-07-04 10:20:28 +08:00
hiyouga	0c699de39d	tiny fix	2024-07-04 03:47:05 +08:00
hiyouga	44747cebd2	tiny fix	2024-07-04 03:02:23 +08:00
hiyouga	b5d101e1bf	fix data map for packing	2024-07-04 03:01:31 +08:00
hiyouga	6fd6aa4530	fix packing for eager/sdpa attn	2024-07-04 01:52:43 +08:00
hoshi-hiyouga	87d9b2d005	Merge pull request #4224 from chuan298/main ... Implement efficient packing without cross-contamination attention	2024-07-04 01:18:54 +08:00
hiyouga	cce7083024	update packing	2024-07-04 01:10:55 +08:00
hoshi-hiyouga	a36e8f2dd5	Update packing.py	2024-07-03 23:36:01 +08:00
hiyouga	c346f79f99	update func name	2024-07-03 23:29:33 +08:00
hiyouga	8a6a7b9c8a	update arg name	2024-07-03 23:23:24 +08:00
hiyouga	575a02a23d	update hparams	2024-07-03 23:18:58 +08:00
hiyouga	7f770f6895	update ui	2024-07-03 23:13:49 +08:00
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