MakazhanAlpamys/Soup
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
- Stars10.1k
- LanguagePython
- LicenseApache-2.0
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU.
Soup turns the pain of LLM fine-tuning into a simple workflow. One config, one command, done.
Fine-tune an 8B model on a 4 GB laptop GPU. Layer streaming keeps the frozen base out of VRAM and feeds it to the GPU one decoder layer at a time. Measured on an RTX 3050 Laptop 4 GB: Llama-3.1-8B-Instruct + NF4 at 119.6 tok/s at 952 MHz, 3.32 GB peak (pre-repair) — bit-exact against a normal resident run, and reproduced independently on an H100 at 113.00 tok/s in the same 3.32 GB. (Both figures were measured on…
Description and README excerpt from MakazhanAlpamys/Soup on GitHub ↗.
MakazhanAlpamys/Soup was first seen on GitHub · Trending Python today on Nov 3, 2026. Since then it has appeared in 9 checks on 2 different days. Its best position was #11 of 18, reached on Nov 3, 11:49 UTC. It dropped off the list after Nov 4, 11:49 UTC.
Position on GitHub · Trending Python today at every check (lower is better).
Best rank per day (UTC).
Platform metric as reported by GitHub.
Archived daily, weekly and monthly lists that include this entry.
Not at the moment. It was last on the list on Nov 4, 11:49 UTC, after 2 days of trending.
#11 on GitHub · Trending Python today, on Nov 3, 11:49 UTC. Trendoday checks this list every 180 minutes.
It was first seen on Nov 3, 2026 and has been on the list on 2 days (9 checks) since.
Mostly Python; it is licensed under Apache-2.0. It has 10.1k stars and 1660 forks.