Repository · CC0-1.0
chrisliu298/awesome-on-policy-distillation
A curated collection of papers, technical reports, frameworks, and tools for on-policy distillation (OPD) of large language models
★ 909
Stars
41 forks · 8 open issues
+1.0/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
26.8
Momentum / 100
see the breakdown below
7mo ago
Created
last push 33d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 5.8 | +1.0/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.81× the monthly pace |
| Freshness | 15 | 12.5 | last push 33d ago; decays to zero at 180 days |
| Scale | 15 | 8.6 | 909 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 26.8 | sum of the above |
Detail
| Topics | awesomeawesome-listdistillationgkdknowledge-distillationllmllm-distillationllm-trainingminillmon-policy-distillationopdpost-trainingreinforcement-learningrlrlhfself-distillationspeculative-decoding |
| Matched on | Learning & Roadmaps (awesome-list) |
| Short window | +7 stars over 7 days = 1.0/day |
| Long window | +32 stars over 26 days = 1.2/day |
| Lifetime average | 4.00 stars/day over 228 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |