11 Commits

Author	SHA1	Message	Date
苏阳	174cbde243	Update for multinode finetuning.	2023-12-27 11:15:38 +08:00
yangapku	e8e15962d8	add 72B and 1.8B Qwen models, add Ascend 910 and Hygon DCU support, add docker support	2023-11-30 15:29:13 +08:00
Junyang Lin	343017c4ce	Update finetune_lora_single_gpu.sh	2023-10-09 01:13:08 +08:00
Junyang Lin	05577dea69	Update finetune_qlora_single_gpu.sh	2023-10-08 14:51:50 +08:00
Junyang Lin	26922b81cb	Update finetune_qlora_ds.sh	2023-10-08 14:50:45 +08:00
Junyang Lin	14e6e69f6d	Update finetune_lora_ds.sh	2023-10-08 14:50:28 +08:00
Junyang Lin	7eac4fde6e	Update finetune_lora_single_gpu.sh	2023-10-08 14:50:08 +08:00
JustinLin610	b5fad3d561	fix single-gpu qlora, and add profiling	2023-10-07 10:37:42 +08:00
yangapku	3e5ade9352	update readme	2023-09-28 17:10:20 +08:00
JustinLin610	73f4040abb	add gradient checkpointing	2023-09-12 23:10:59 +08:00
JustinLin610	af22d5e0ce	add finetuning	2023-09-11 23:47:32 +08:00