Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning
Quantization-aware distillation (QAD) restores much of the short-form question-answering performance lost to sub-3-bit quantization, yet leaves mathematical and code reasoning substantially impaired. Long generations often degenerate into repetitive loops, exhausting the decoding budget without completing a solution. W...
Yuan-Teng Chen, Zhi-Lei Liu, Peisong Wang et al.
· 0 citations