Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
MakazhanAlpamys/Soup
View on GitHub ↗Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Soup grew +34.1% in the last 30 days, ranks 20th of 203 in Fine-Tuning (LoRA / PEFT), actively maintained, last commit yesterday.
Star trajectory
81 days tracked2026-08-069.7k stars today2026-10-26
Momentum
+34.1% in 30d, above the Fine-Tuning (LoRA / PEFT) median of +0.1%.
Maintenance
Last commit yesterday, fresher than the median of 260d.
How it compares in Fine-Tuning (LoRA / PEFT)
Soup
9.7k
stars
+34.1% 30d
commit yesterday
Fine-Tuning (LoRA / PEFT) median
533
stars
+0.1% 30d
commit ~260d ago
Leader · LLMs-from-scratch
107.3k
stars
+1.6% 30d
commit 23 days ago
Ranked 20th of 203 by stars.
- Language
- Python
- License
- Apache License 2.0
- Contributors
- 126
- Forks
- 1.6k
- Watchers
- 60
- Open issues
- 115
- Releases
- 181
- Created
- 2026-02-20
- Stars this week
- +263
You've seen where Soup stands today.
Get the moves before everyone else: the 5 Fine-Tuning (LoRA / PEFT) repos climbing fastest, every Tuesday.
Free weekly digest. Double opt-in, unsubscribe anytime.