Socratic AI Tutoring (SFT + DPO) Aligned open language models (Llama-3.1-8B and Muse-Glimmer-30B) and multi-domain pedagogical preference dataset (1,680 items) for AI education. NextGenInstitute/socraticDataset1680 Viewer • Updated Aug 19 • 1.68k • 19 NextGenInstitute/socraticMuse30B Text Generation • Updated Aug 19 NextGenInstitute/socraticLlama8B Text Generation • Updated Aug 19
Socratic AI Tutoring (SFT + DPO) Aligned open language models (Llama-3.1-8B and Muse-Glimmer-30B) and multi-domain pedagogical preference dataset (1,680 items) for AI education. NextGenInstitute/socraticDataset1680 Viewer • Updated Aug 19 • 1.68k • 19 NextGenInstitute/socraticMuse30B Text Generation • Updated Aug 19 NextGenInstitute/socraticLlama8B Text Generation • Updated Aug 19
