Commit Graph

5 Commits (62cdac6b7b655e11626382d64e56503146a516ee)

Author SHA1 Message Date
YeAnbang 8a3ff4f315 fix style 2024-07-26 09:55:15 +00:00
YeAnbang b3594d4d68 fix orpo cross entropy loss 2024-07-15 02:12:05 +00:00
YeAnbang e7a8634636 fix eval 2024-07-11 03:35:03 +00:00
YeAnbang d888c3787c add benchmark for sft, dpo, simpo, orpo. Add benchmarking result. Support lora with gradient checkpoint 2024-07-10 10:17:08 +00:00
YeAnbang c8d1b4a968 add orpo 2024-06-27 07:20:28 +00:00