Python · MIT
Zihao-Wu06/distillops
Black-box LLM distillation for any verifiable task, with text or image inputs: teacher API -> rejection sampling -> SFT -> eval -> GRPO
★ 80
Stars
1 forks · 1 open issues
+6.6/day
Growth · lifetime avg
Average since the repo was created — it is young enough that this still describes now. Not a recent-week figure.
36.9
Momentum / 100
see the breakdown below
12d ago
Created
last push 4d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 16.8 | +6.6/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | needs 7-day and 30-day rates side by side |
| Freshness | 15 | 14.6 | last push 4d ago; decays to zero at 180 days |
| Scale | 15 | 5.5 | 80 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 36.9 | sum of the above |
Detail
| Topics | ai-agentsdistillationdocument-understandingfine-tuninggrpoknowledge-distillationllmmultimodalposttrainingqwenqwen3-vlreinforcement-learningrlvrsftsmall-language-modelstrlvision-language-modelvllm |
| Matched on | LLM & Inference (fine-tuning) |
| Short window | no snapshot 5–10 days old yet |
| Long window | no snapshot 14–45 days old yet |
| Lifetime average | 6.56 stars/day over 12 days |
| First seen here | 2026-11-06 |
| Last read | 1h ago |