Tag: distillation
All the articles with the tag "distillation".
-
Notes on: OPD+
The actual bug OPD+ finds — stop-gradient drops a real gradient term for every f-divergence except reverse KL, which is why MiniLLM-style training "just happened" to work — plus the fix and the Table 2 numbers.
-
Notes on: f-DISTILL
The actual f-DISTILL framework — the four concrete divergence variants (KL, RKL, JS, TVD), the word-level decomposition that makes them tractable, and why symmetric losses win on DART/XSum/WMT.
-
Notes on: Rethinking On-Policy Distillation of LLMs
The actual mechanism behind when on-policy distillation works — token overlap ratio rising toward 91%, a "stronger teacher can fail while a weaker one succeeds" result, and a reverse-distillation experiment that undercuts the whole premise.
-
Notes on: MiniLLM
The reverse-KL policy-gradient derivation behind MiniLLM — per-token rewards, teacher-mixed sampling, length normalization — plus the actual GPT-2/OPT/LLaMA numbers.