WorkflowStacks

The marketplace for AI skills that launch offers, rank in AI search, and automate operations. No coding required.

๐•โšก๐Ÿ’ฌ

Marketplace

  • Browse Skills
  • AI Agents
  • Claude Skills
  • MCP Servers
  • Prompts

Solutions

  • For Founders
  • For Agencies
  • For Ecommerce
  • Agent Builder
  • Starter Packs
  • Playbooks

Learn

  • How It Works
  • What Are Skills
  • What Are Agents
  • What Is MCP
  • For Creators
  • Security

Company

  • About
  • Enterprise
  • API Docs
  • Terms
  • Privacy
  • Support
Compatible with
๐Ÿค–ChatGPT
โœจClaude
๐Ÿ’ŽGemini
๐Ÿ›๏ธShopify
๐Ÿ”Ahrefs
๐Ÿ“ŠSheets
๐Ÿ’ฌWhatsApp
๐Ÿ“ฑMeta Ads
+50 more

ยฉ 2026 WorkflowStacks. All rights reserved.

TermsPrivacySupport
ai-agent

ms-swift: Train 600+ LLMs

Train large language models with ms-swift, a tool for startup founders, with 14k+ GitHub stars.
14,372 stars1,450 forksPythonUpdated 6/2/2026100% free ยท open source
What it does

Train and fine-tune large language models using ms-swift, allowing startup founders to leverage AI capabilities for various applications

When to use it
  • โ€ขWhen you need to customize a language model for your specific business needs
  • โ€ขWhen you want to integrate AI-powered text generation or understanding into your product
  • โ€ขWhen you're looking to improve the performance of a pre-trained language model on a particular task
Quick start
  1. 1Install ms-swift using pip: `pip install ms-swift`
  2. 2Choose a pre-trained language model from the ms-swift repository, such as Qwen3.6 or Llama4
  3. 3Use the PEFT or Full-parameter tuning method to adapt the model to your specific task or dataset
  4. 4Evaluate the performance of the fine-tuned model using metrics such as accuracy or perplexity
Ready-to-paste prompt
python -m ms_swift.train --model-name Qwen3.6 --task-name sentiment-analysis --dataset your_custom_dataset

Topics

deepseek-r1
embedding
grpo
internvl
liger
llama
llama4
llm
lora
megatron
moe
multimodal
open-r1
peft
qwen3
qwen3-6
qwen3-omni
qwen3-vl
reranker
sft
What's inside โ€” free to inspect
No purchase needed

Read the entire source before you build โ€” unlike paid marketplaces that hide it behind a buy button.

13
top-level files
9
folders
80.2M
repo size
Apache-2.0
license
Key files
.pre-commit-config.yaml
README_CN.md
README.md
requirements.txt
File tree
.dev_scripts/
.github/
asset/
docs/
examples/
requirements/
scripts/
swift/
tests/
.gitignore
.pre-commit-config.yaml
CODE_OF_CONDUCT.md
CONTRIBUTING_CN.md
CONTRIBUTING.md
LICENSE
Makefile
MANIFEST.in
README_CN.md
README.md
requirements.txt
setup.cfg
setup.py
Quick Actions
Details
Creator
modelscope
Language
Python
Category
ai-agent
Published
8/1/2023

Related skills

More ai-agent tools founders pair with this one.

ai-agentโ˜… 172,909
Ollama: Run AI Models Locally on Your Own Machine
Instantly deploy top open-source AI models without cloud dependencies. Perfect for founders building AI applications with complete privacy and control.
ai-agentโ˜… 165,332
Karpathy Skills: AI Coding Wisdom for Smarter Development
Unlock advanced LLM coding strategies from a leading AI researcher. Essential reference for founders building intelligent code agents and AI products.
ai-agentโ˜… 161,190
Transformers: Ship AI Models in Minutes, Not Months
Quickly define, train, and deploy state-of-the-art machine learning models across text, vision, and audio. Perfect for AI founders building intelligent applications.
ai-agentโ˜… 114,247
llama.cpp
LLM inference in C/C++
ai-agentโ˜… 81,719
RAGFlow: Build Context-Aware AI Agents 10x Faster
Python toolkit for startup founders wanting powerful retrieval-augmented generation with advanced agent capabilities. Supercharge your LLM context management with open-source AI infrastructure.
ai-agentโ˜… 75,645
OpenHands: AI-Driven Dev
Get AI-driven development tools with OpenHands. For founders and developers.