modelscope/ms-swift

Use PEFT or Full-parameter to CPT/SFT/DPO/GRPO 600+ LLMs (Qwen3.5, DeepSeek-R1, GLM-5, InternLM3, Llama4, ...) and 300+ MLLMs (Qwen3-VL, Qwen3-Omni, InternVL3.5, Ovis2.5, GLM4.5v, Llava, Phi4, ...) (AAAI 2025).

78
/ 100
Verified

This framework helps AI developers and researchers customize large language models (LLMs) and multimodal large models (MLLMs) for specific tasks or datasets. It takes a base model and your specialized data, then outputs a fine-tuned model ready for deployment. This is for professionals building custom AI applications.

13,105 stars. Used by 1 other package. Actively maintained with 89 commits in the last 30 days. Available on PyPI.

Use this if you need to fine-tune existing large language or multimodal models to perform better on your unique data or specialized tasks, across various hardware and with advanced optimization techniques.

Not ideal if you are looking for a pre-trained model to use directly, or if you do not have specific data to fine-tune a model.

AI development machine learning engineering natural language processing computer vision model customization
Maintenance 22 / 25
Adoption 11 / 25
Maturity 25 / 25
Community 20 / 25

How are scores calculated?

Stars

13,105

Forks

1,255

Language

Python

License

Apache-2.0

Last pushed

Mar 13, 2026

Commits (30d)

89

Dependencies

40

Reverse dependents

1

Get this data via API

curl "https://pt-edge.onrender.com/api/v1/quality/transformers/modelscope/ms-swift"

Open to everyone — 100 requests/day, no key needed. Get a free key for 1,000/day.