Python · MIT
datamllab/OpenEBFM
Open-source code for training and scaling up energy-based foundation models.
★ 266
Stars
21 forks · 2 open issues
+11/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
43.2
Momentum / 100
see the breakdown below
48d ago
Created
last push 5d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 20.5 | +11/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.8 | last week ran 1.05× the monthly pace |
| Freshness | 15 | 14.8 | last push 5d ago; decays to zero at 180 days |
| Scale | 15 | 7.0 | 266 stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 43.2 | sum of the above |
Detail
| Topics | aiclimbmixdclmenergy-based-generationenergy-based-language-modelsenergy-based-modelsfine-tuningfinewebfoundation-modelslanguage-modelslarge-language-modelllmpost-trainingpre-trainingpretraining-modelreinforcement-learningrlscaling-lawscaling-lawssft |
| Matched on | LLM & Inference (fine-tuning, llm) |
| Short window | +76 stars over 7 days = 10.9/day |
| Long window | +217 stars over 21 days = 10.3/day |
| Lifetime average | 5.86 stars/day over 45 days |
| First seen here | 2026-10-15 |
| Last read | 2d ago |