Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit Reasoning

T1Covered by 1 source · first reported by arXiv at 24 Sept, 04:00 UTC

arXiv:2609.26708v1 Announce Type: cross Abstract: 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…

science

Sources

• T1Train Where the Quantized Model Goes: On-Policy Distillation for Low-Bit ReasoningarXiv24 Sept, 04:00