Soup
by MakazhanAlpamys (personal account)
Fine-tune LLMs from one YAML. Layer streaming trains an 8B model on a 4 GB laptop GPU. (description from the project’s GitHub page)
Repository facts
- Stars
- 9,314
- Forks
- 1,522
- Open issues and pull requests
- 210
- Primary language
- Python
- License
- Apache License 2.0 (Apache-2.0)
- Owner
- MakazhanAlpamys · Personal account
- Created
- Feb 20, 2026
- Last push
- Oct 18, 2026
Topics
Add this badge to your README
Shows this repository’s rank in AI on GitHub and links back to this page. Ranks are by stars and change when the list is refreshed. The badge is not an endorsement or a rating. About the badges
Markdown (for a README)
[](https://unitedstatesofamericasuperintelligence.com/github/makazhanalpamys--soup/)
HTML
<a href="https://unitedstatesofamericasuperintelligence.com/github/makazhanalpamys--soup/"><img src="https://unitedstatesofamericasuperintelligence.com/badges/github/makazhanalpamys--soup.svg" alt="Ranked #890 in AI on GitHub" height="20"></a>
Related projects
Projects that share this one’s GitHub topics.
Rank 6,932: whitecircle/halo
Halo is an open-source framework built by White Circle for training large language and multimodal models
825 starsPythonOther licenseLast push Oct 15, 2026
Rank 7,129: DaoyuanLi2816/can-i-finetune-this
Single-GPU LLM fine-tuning preflight: memory estimates, runnable LoRA/QLoRA recipes, and local measurements.
793 starsPythonMITLast push Oct 8, 2026
Rank 4,701: ARahim3/mlx-tune
Fine-tune LLMs on your Mac with Apple Silicon. SFT, DPO, GRPO, Vision, TTS, STT, Embedding, and OCR fine-tuning — natively on MLX. Unsloth-compatible API.
1,444 starsPythonApache-2.0Last push Jun 23, 2026
Rank 64: hiyouga/LlamaFactory
Unified Efficient Fine-Tuning of 100+ LLMs & VLMs (ACL 2024)
75,561 starsPythonApache-2.0Last push Oct 10, 2026
Rank 882: oumi-ai/oumi
Easily fine-tune (SFT/RL), evaluate, and deploy Qwen, Gemma, or any open agentic LLM/VLM!
9,403 starsPythonApache-2.0Last push Oct 15, 2026
Rank 378: huggingface/peft
🤗 PEFT: State-of-the-art Parameter-Efficient Fine-Tuning.
21,800 starsPythonApache-2.0Last push Oct 16, 2026