ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 75
🔄 In a Training Loop
Abdullah Mujeeb Khawaja
amkkk
AI & ML interests
Tough question as I love all areas of DL, but from all of it, embeddings are my favourite topic. Currently obsessed with what can we do around LLMs.
MLE @ DPD, prev DS in Recs Systems @ Alibaba Group
Recent Activity
upvoted a paper about 22 hours ago
ORPO: Monolithic Preference Optimization without Reference Model liked a dataset about 23 hours ago
NicolaiSivesind/human-vs-machine liked a dataset about 23 hours ago
dmitva/human_ai_generated_textOrganizations
upvoted a paper about 22 hours ago
upvoted an article 17 days ago
Article
Making any LLM model "reasoning"
Metal3d
• • 26 upvoted a collection 6 months ago