ORPO: Monolithic Preference Optimization without Reference Model
Paper • 2403.07691 • Published • 73 •
9
Seonil Son
fgenie
AI & ML interests
natural language generation;prompting; human preference tuning; LLM; evaluation metric
Organizations
None yet
commented a
paper about 2 years ago
commented 7
papers over 2 years ago
FuseChat: Knowledge Fusion of Chat Models
Paper • 2402.16107 • Published • 39 •
5
FuseChat: Knowledge Fusion of Chat Models
Paper • 2402.16107 • Published • 39 •
5
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 116 •
20
LongRoPE: Extending LLM Context Window Beyond 2 Million Tokens
Paper • 2402.13753 • Published • 116 •
20
FuseChat: Knowledge Fusion of Chat Models
Paper • 2402.16107 • Published • 39 •
5
Nemotron-4 15B Technical Report
Paper • 2402.16819 • Published • 47 •
4
GPT Can Solve Mathematical Problems Without a Calculator
Paper • 2309.03241 • Published • 19 •
9