iREPO: implicit Reward Pairwise Difference based Empirical Preference Optimization
Paper
•
2405.15230
•
Published
•
3
Long Le
lole25
AI & ML interests
None yet
Recent Activity
updated
a model
2 months ago
DUAL-GPO/zephyr-7b-ipo-qlora-v0-merged
updated
a model
2 months ago
DUAL-GPO/zephyr-7b-dpo-new-lora-v1-merged
Organizations
