📚 从零开始构建大模型
datawhalechina/happy-llm is accelerating — star growth is speeding up by +4.7/day (89th percentile in the tracked cohort), on top of +22.4 stars/day. Forks are climbing too, at +2.4/day.
Elevated breakout odds over the next 14 days, led by star acceleration (89th pctl) and star velocity (82th pctl). Confidence is high given the available history.
Reconstructed from 346 snapshots — the time-series GitHub’s API doesn’t expose.
~11 forks/day, 6.9× the trailing baseline.
~14 forks/day, 8.9× the trailing baseline.
~12 forks/day, 25.8× the trailing baseline.
Live score, refreshed every 6 hours. Links back to this page.
[](https://repoclimb.com/repo/datawhalechina/happy-llm)Transparent heuristic · logged for model training
Percentile rank within the tracked cohort. The score self-calibrates — it answers “accelerating vs. everything else,” not raw size.
~18 forks/day, 5.0× the trailing baseline.
~17 forks/day, 3.6× the trailing baseline.
~16 forks/day, 3.9× the trailing baseline.
~10 forks/day, 3.8× the trailing baseline.
~18 forks/day, 6.8× the trailing baseline.
~16 forks/day, 8.7× the trailing baseline.
~17 forks/day, 6.8× the trailing baseline.
~12 forks/day, 20.1× the trailing baseline.
~21 forks/day, 11.3× the trailing baseline.