Python · Apache-2.0
MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
★ 10.2k
Stars
1.7k forks · 222 open issues
+58/day
Growth · measured
Stars counted between two of our own snapshots roughly a week apart. The repository page gives the exact span.
60.5
Momentum / 100
see the breakdown below
8mo ago
Created
last push 2d ago
Star history
How this score was built
| Component | Weight | Earned | Why |
|---|---|---|---|
| Velocity | 55 | 33.9 | +58/day, log-scaled against a 750/day ceiling |
| Acceleration | 15 | 0.0 | last week ran 0.91× the monthly pace |
| Freshness | 15 | 15.0 | last push 2d ago; decays to zero at 180 days |
| Scale | 15 | 11.6 | 10.2k stars, log-scaled against 150k — stops a 3-star repo topping the board |
| Momentum | 100 | 60.5 | sum of the above |
Detail
| Topics | cliconsumer-gpudpofine-tuningggufhuggingfacellmllmopslocal-ailocal-llmloralow-vrammachine-learningollamapeftpythonpytorchqlorasfttransformers |
| Matched on | LLM & Inference (fine-tuning, llm) Dev Tools (cli) |
| Short window | +409 stars over 7 days = 58.4/day |
| Long window | +1.7k stars over 26 days = 64.2/day |
| Lifetime average | 39.47 stars/day over 258 days |
| First seen here | 2026-10-11 |
| Last read | 2d ago |