Magpie: Alignment Data Synthesis from Scratch by Prompting Aligned LLMs with Nothing
Paper • 2406.08464 • Published • 72
shisa-v2-research
-
-
Scaling Synthetic Data Creation with 1,000,000,000 Personas
Paper • 2406.20094 • Published • 107 -
argilla/magpie-ultra-v1.0
Viewer • Updated • 3.22M • 785 • 50 -
simplescaling/s1K-1.1
Viewer • Updated • 1k • 2.1k • 155 -
GAIR/LIMO
Viewer • Updated • 817 • 1.48k • 177 -
Self-Play Fine-Tuning Converts Weak Language Models to Strong Language Models
Paper • 2401.01335 • Published • 69 -
Direct Nash Optimization: Teaching Language Models to Self-Improve with General Preferences
Paper • 2404.03715 • Published • 62 -
Self-Boosting Large Language Models with Synthetic Preference Data
Paper • 2410.06961 • Published • 16 -
SPaR: Self-Play with Tree-Search Refinement to Improve Instruction-Following in Large Language Models
Paper • 2412.11605 • Published • 18 -
Magpie-Align/Magpie-Reasoning-V1-150K-CoT-Deepseek-R1-Llama-70B
Viewer • Updated • 150k • 108 • 18 -
sbintuitions/modernbert-ja-130m
Fill-Mask • 0.1B • Updated • 8.71k • • 47 -
bespokelabs/Bespoke-Stratos-17k
Viewer • Updated • 16.7k • 7.78k • 341 -
SymNoise: Advancing Language Model Fine-tuning with Symmetric Noise
Paper • 2312.01523 • Published -
TÜLU 3: Pushing Frontiers in Open Language Model Post-Training
Paper • 2411.15124 • Published • 67