hiyouga a402161631 support FlashAttention2 ...

Former-commit-id: 23e56c5554b948d4f08ad87849b261eafd2c7890

2023-09-10 20:43:56 +08:00

..

core

support FlashAttention2

2023-09-10 20:43:56 +08:00

dpo

fix bug in DPO data collator

2023-09-08 20:45:07 +08:00

ppo

fix lora target

2023-09-09 17:04:45 +08:00

pt

update training resuming

2023-08-18 01:41:17 +08:00

rm

fix lora target

2023-09-09 17:04:45 +08:00

sft

support FlashAttention2

2023-09-10 20:43:56 +08:00

__init__.py

modify code structure

2023-08-02 23:17:36 +08:00

tune.py

support rope scaling, fix #475 #476 #478

2023-08-12 20:46:27 +08:00