workflowstacks
ai-agent

ms-swift: Train 600+ LLMs

Train large language models with ms-swift, a tool.
advanced⏱ 1-2 hours💵 Free (self-hosted)
15,329 stars1,624 forksPythonUpdated 8/22/2026100% free · open source
What it is

Train your own large language model using Python code.

Real use case example

"A founder wants to create a custom chatbot for their new support platform. They use ms-swift to train a model on their support data, then integrate it with their website and chat systems."

Best insideClaude DesktopAny AI Client
When to use it
  • •When you need to customize a language model for your specific business needs
  • •When you want to integrate AI-powered text generation or understanding into your product
  • •When you're looking to improve the performance of a pre-trained language model on a particular task
Ready-to-paste prompt
python -m ms_swift.train --model-name Qwen3.6 --task-name sentiment-analysis --dataset your_custom_dataset
Saves to your device
Use with Claude
New

Skip the builder — one click puts this in Claude, Cursor, Antigravity and more.

🛠️ Technical setup

Expect 20–40 minutes in a terminal — or let your AI agent drive it.

Try it instantly — no install
Claude Code
mkdir -p ~/.claude/skills/ms-swift && curl -fsSL https://workflowstacks.com/api/skills/ms-swift/claude-skill -o ~/.claude/skills/ms-swift/SKILL.md
Open in another AI app

Opens the app with this repo with the prompt ready to go — no copy-paste needed.

Connect the whole catalog (MCP)
claude mcp add --transport http workflowstacks https://workflowstacks.com/api/mcp

Adds a WorkflowStacks connector to Claude Code: search and load any skill here by chatting.

How ms-swift: Train 600+ LLMs works
Codeflow
Free to inspect

Ms-swift: Train 600+ LLMs is a very large Python project (~141k lines across 997 code files, plus 132 test files). It is a full software project: use it through its install path rather than reading it end to end. Last commit this month, Apache-2.0 license, has a test suite.

Size
Very large codebase
~141k lines · 997 code files · days to read — use, don't read
Setup
Developer setup
A real software project. Use it via its install path; don't expect to read it all.
Runs on
Python
No API keys detected
Python 100%
Where to start reading
  1. 1
    README.md
    Start here — what it does and how to install it
  2. 2
    requirements.txt
    Dependencies and the commands it exposes
  3. 3
    examples/README.md
    A worked example — copy this to get going
What's in each folder
examples/Examples you can copy498 files
docs/Documentation181 files
swift/Folder539 files
requirements/Folder9 files
scripts/Helper scripts9 files
tests/Tests — proof it works150 files
.github/CI / automation (GitHub Actions)12 files
.dev_scripts/Tool / agent settings4 files
READMEHas testsDocumentedCI checksExamples includedApache-2.0 licenseUpdated this month
Quick Actions
Details
Creator
modelscope
Language
Python
Category
ai-agent
Published
8/1/2023

Are you the creator of this tool? Claim your listing → and earn 85% of every sale.

Related skills

More ai-agent tools founders pair with this one.

ai-agent★ 276,806
Track GitHub Stars with 996.ICU
Get a popular GitHub star counter for your startup, ideal.
ai-agent★ 264,191
Superpowers
An agentic skills framework & software development methodology that works.
ai-agent★ 244,424
Linux: Open Source Kernel
Get the Linux kernel source tree for custom development, ideal for startup founders in need of a flexible OS foundation
ai-agent★ 210,750
Vue
This is the repo for Vue 2. For Vue 3, go to https://github.com/vuejs/core
ai-agent★ 204,069
Improve Code with andrej-karpathy-skills
Get better code behavior with andrej-karpathy-skills, 165k+ GitHub stars, for founders using LLMs.
ai-agent★ 197,010
FreeDomain: Free Website Domain
Get a free domain with FreeDomain.