Prismatic Synthesis Gradient-based Data Diversification Boosts Generalization in LLM Reasoning nvidia/Nemotron-PrismMath Viewer • Updated May 27 • 1M • 304 • 12 Jaehun/PrismNLI Viewer • Updated May 27 • 515k • 23 Jaehun/PrismNLI-0.4B Text Classification • 0.4B • Updated May 28
Prismatic Synthesis Gradient-based Data Diversification Boosts Generalization in LLM Reasoning nvidia/Nemotron-PrismMath Viewer • Updated May 27 • 1M • 304 • 12 Jaehun/PrismNLI Viewer • Updated May 27 • 515k • 23 Jaehun/PrismNLI-0.4B Text Classification • 0.4B • Updated May 28
Jaehun/lpt2-dpo_distill72b_671b_v2__sft_docci_objpt_247k_train_acc7445_acc7589_checkpoint-500 Image-to-Text • 8B • Updated Sep 20 • 2
Jaehun/lpt2-stage2_distill72b_671b_v2__sft_docci_objpt_247k_train_acc7511_checkpoint-2900 Image-to-Text • 8B • Updated Sep 20 • 1