XINLI1997/DN-MOPD-Data
Viewer • Updated • 26.7k
Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation. Data and models.
Note Training prompt sets: student (2,700) and GRPO teachers (math/code/IF, 8,000 each)
Note Beyond Teacher Assignment: Domain-Normalized Multi-Teacher On-Policy Distillation