Blackhole Collection A black hole with lots of high-quality dialogue datasets in many fields, and multilingual helps to train LLMs with SFT and DPO methods easier. • 32 items • Updated Aug 18 • 6
GaLore: Memory-Efficient LLM Training by Gradient Low-Rank Projection Paper • 2403.03507 • Published Mar 6 • 182
MultiHop-RAG: Benchmarking Retrieval-Augmented Generation for Multi-Hop Queries Paper • 2401.15391 • Published Jan 27 • 6
ORPO: Monolithic Preference Optimization without Reference Model Paper • 2403.07691 • Published Mar 12 • 62
Design2Code: How Far Are We From Automating Front-End Engineering? Paper • 2403.03163 • Published Mar 5 • 93
ShortGPT: Layers in Large Language Models are More Redundant Than You Expect Paper • 2403.03853 • Published Mar 6 • 62
VinaLLaMA Collection Second Generation, Most Powerful Open-Source Vietnamese LLMs. • 8 items • Updated Feb 9 • 12