#1212th of 31 in Training and fine-tuning
soup
CLI for fine-tuning and post-training LLMs from a single YAML config
- Stars
- 9.5k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Oct 2026
- Language
- Python
22 on 1 Apr 20269,534 on 21 Oct 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
Soup is a Python CLI that runs LoRA/QLoRA fine-tuning and preference or RL post-training (SFT, DPO, GRPO, PPO, KTO, ORPO and others) from one soup.yaml. It also covers batch inference, an OpenAI-compatible server, merge and GGUF export, and a local web dashboard. An opt-in beta layer-streaming mode trains an 8B NF4 model in about 3.3 GB peak VRAM.
Who it is for: Engineers fine-tuning open LLMs on their own GPUs, including small laptop cards
Strengths
- Many tasks in one config: SFT, DPO, GRPO, PPO, KTO, ORPO, SimPO, IPO, vision, audio
- Layer streaming trains Llama-3.1-8B NF4 in 3.32 GB peak on a 4 GB laptop GPU
- Same tool merges adapters, exports GGUF, serves an OpenAI-compatible API, has a web UI
- Light install without PyTorch for data tools; 100+ ready-made model recipes
Weaknesses
- Python 3.10-3.12 only; 3.13+ is unsupported
- Layer streaming is opt-in and still beta; a correctness repair changed its benchmark numbers
- Recent releases are breaking: unused settings and unknown config keys now fail at load
- AWQ and GPTQ export are deprecated and slated for removal in v0.77
What it needs
- GPU optional
- Docker + Compose
- Needs PyTorch, transformers, peft, trl, HuggingFace Hub
- Models: HuggingFace Hub causal LMs, Llama 3.x/4, Qwen 2.5/3, Gemma 3, Mistral
- port 7860
Also in Training and fine-tuning
See all 31| Rank | Project | Score |
|---|---|---|
| 1 | unslothDesktop and web app to run, fine-tune and export open models | 88 out of 100 |
| 2 | deepspeedPyTorch library for distributed training of large models with ZeRO | 84 out of 100 |
| 3 | verlReinforcement learning training library for LLM post-training with PPO and GRPO | 84 out of 100 |
| #4 | peftPython library for LoRA and other parameter-efficient fine-tuning of Transformers models | 84 out of 100 |
| #5 | trlPost-training library with SFT, DPO, GRPO and KTO trainers | 81 out of 100 |