ludwig-ai / ludwig
Low-code framework for building custom LLMs, neural networks, and other AI models
Why this job: topics: fine-tuning, llm-training
What it does
- Supervised fine-tuning (SFT) on instruction/response pairs
- Alignment training. DPO, KTO, ORPO, GRPO (reward-model-free RLHF)
- PEFT adapters. LoRA, DoRA, VeRA, LoRA+, TinyLoRA, OFT, HRA, WaveFT, LN-Tuning, VBLoRA, C3A
- LoRA initializers. PiSSA, EVA, CorDA, LoftQ for improved convergence
- Multi-adapter PEFT. multiple named adapters on one base model, switchable at runtime; merge with TIES, DARE, SVD, magnitude pruning
Get started
pip install ludwig
# core
pip install ludwig[full]
# all optional dependencies
pip install ludwig[llm]
# LLM fine-tuning only- Maintenance
- Active
- Last commit 13 days ago
- Stars
- 11,793
- +2 this week
- Licence
- Apache-2.0
- Allows business use
- Downloads for
- None listed
- No release files
- Latest version
- v0.17.10
- Released 13 days ago
- Built with
- Python
- 100% of the code
Is it looked after?
- Contributors
- 2
- Last 90 days
- Issues
- 100% closed
- 1 still open
- Pull requests
- 2,592 merged
- 1 waiting
- Releases
- 75
- 24 in the last year
Similar repos
| Repo | Stars | Last commit | Licence | Downloads for |
|---|---|---|---|---|
| h2oai / h2o-llmstudio | 5,194 | 2 days ago | Apache-2.0 | No downloads |
| Lightning-AI / pytorch-lightning | 31,447 | 49 days ago | Apache-2.0 | No downloads |
| bespokelabsai / curator | 1,764 | 7 days ago | Apache-2.0 | No downloads |
More: languages, topics and project record
Languages
- Python 100%
- Jupyter Notebook <1%
- Dockerfile <1%
- Shell <1%
Topics
- deep-learning
- deeplearning
- deep
- learning
- machine-learning
- machinelearning
- natural-language-processing
- natural-language
- computer-vision
- data-centric
- data-science
- pytorch
Project record
- JobFine-tuning
- StatusListed
- Commits4,142
- Forks1,213
- Watching182
- Stars in 28 days+27
- CreatedDec 27, 2018
- First seen by usNov 7, 2026
- CheckedNov 9, 2026