18 Commits

Author	SHA1	Message	Date
hiyouga	8d4a5ebf6e	fix zero2 high ram usage ... Former-commit-id: 31a0564d4f	2024-05-19 21:53:54 +08:00
hiyouga	5f48c282d3	fix hf gen args ... Former-commit-id: 70214b71b1	2024-05-19 19:39:32 +08:00
hiyouga	32a65e89e5	fix envs ... Former-commit-id: 8ee8ac6eba	2024-05-19 18:27:18 +08:00
hiyouga	df4aec7e72	fix #3807 ... Former-commit-id: 1ebc890a5f	2024-05-19 17:07:57 +08:00
hiyouga	02f716907e	safe output path in webui ... Former-commit-id: 3c2a992caa	2024-05-18 22:42:28 +08:00
hiyouga	7130efff54	fix jetmoe z3 block ... Former-commit-id: d43822fcc2	2024-05-18 22:28:45 +08:00
hiyouga	519d2511ae	improve data process logger ... Former-commit-id: a851056229	2024-05-18 22:02:42 +08:00
hiyouga	1e867c0fa0	fix #3803 ... Former-commit-id: 0edc16769f	2024-05-18 16:13:14 +08:00
hiyouga	13d7b48efe	improve KTO impl., replace datasets ... Former-commit-id: c450ee87a3	2024-05-18 03:44:56 +08:00
hoshi-hiyouga	97469892c3	Merge pull request #3785 from enji-zhou/feature/add_kto ... add kto Former-commit-id: 33a354548e	2024-05-18 03:07:18 +08:00
hoshi-hiyouga	e4a2accf4a	Update model_args.py ... Former-commit-id: 9646727453	2024-05-17 16:16:41 +08:00
juejuezi	20326affde	feat: pass the max_lora_rank parameter to vLLM backend ... Former-commit-id: b20d62ba3c	2024-05-17 16:07:39 +08:00
hiyouga	9af3dce3c8	add deepseek v2 lite model ... Former-commit-id: 8af9817605	2024-05-17 13:25:36 +08:00
enji.zhou	03956053b8	add kto ... Former-commit-id: db1d5a4f51	2024-05-17 13:09:17 +08:00
hiyouga	780a1f5a4e	better dtype handle in loading ... Former-commit-id: d9f190ff1e	2024-05-17 02:14:56 +08:00
hiyouga	f4bf49e891	enable inbrowser in webui ... Former-commit-id: 694a05fd04	2024-05-17 00:08:56 +08:00
hiyouga	22f71c152a	add falcon 11b ... Former-commit-id: d77bed4091	2024-05-17 00:08:33 +08:00
hiyouga	cae823ddf0	rename package ... Former-commit-id: 308edbc426	2024-05-16 18:39:08 +08:00