15 Commits

Author	SHA1	Message	Date
hiyouga	451d271718	tiny fix	2024-10-08 17:48:56 +08:00
hiyouga	76f2e59504	tiny fix	2024-09-05 23:41:16 +08:00
hiyouga	3382317e32	refactor mm training	2024-08-30 02:14:31 +08:00
hiyouga	b7ca6c8dc1	fix #5048	2024-08-05 23:48:19 +08:00
hiyouga	2f6af73da2	fix gemma2 attention	2024-07-13 23:33:45 +08:00
hiyouga	0c699de39d	tiny fix	2024-07-04 03:47:05 +08:00
hiyouga	6fd6aa4530	fix packing for eager/sdpa attn	2024-07-04 01:52:43 +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
ancv	770f75dc83	move configure_packing to llamafactory.model.patcher and fix constants	2024-06-21 00:45:06 +07:00
ancv	238f5c3d99	update packing with sdpa and eager attention mode	2024-06-16 02:25:47 +07:00
ancv	04315c3d92	remove some unused params	2024-06-15 23:00:55 +07:00
ancv	b2c367bc61	implement efficient packing without cross-contamination attention	2024-06-12 11:56:01 +07:00