Files
gym/README-HF.md
zeekay 3c354b6eb3 🏋️ Complete rebranding: LlamaFactory → Gym by Zoo Labs Foundation
## Major Changes
- **Package Rename**: llamafactory → zoo-gym (PyPI) / gym (internal)
- **Organization**: Rebranded to Zoo Labs Foundation Inc (501c3 non-profit)
- **Complete Module Migration**: All src/llamafactory/ → src/gym/
- **Updated Metadata**: setup.py, pyproject.toml, README.md

## New Features
- **Qwen3 Fine-tuning**: Full support with configs/qwen3_finetune.yaml
- **Zen Nano Integration**: QLoRA config for 4B edge models
- **Enhanced Documentation**: README-HF.md, QUICKSTART.md, LLM.md
- **HuggingFace Integration**: .huggingface deployment config
- **Training Scripts**: train_qwen3.py, train_qwen3_omni.py

## Technical Improvements
- **Import Path Updates**: All internal references updated
- **CLI Rename**: gym-cli command (backward compatible)
- **Gradio WebUI**: Enhanced interface for training
- **Educational Focus**: Democratizing AI education and research

## Testing
- ✅ Package imports successfully
- ✅ CLI functionality verified
- ✅ Core dependencies resolved
- 📋 CI tests pending

## Attribution
Maintains original Apache 2.0 license with updated copyright to Zoo Labs Foundation Inc.
All original LlamaFactory contributors acknowledged in commit history.
2025-09-24 14:41:06 -05:00

3.2 KiB

title, emoji, colorFrom, colorTo, sdk, sdk_version, app_file, pinned, license, tags
title emoji colorFrom colorTo sdk sdk_version app_file pinned license tags
Gym - AI Model Training Platform 🏋️ purple blue gradio 4.29.0 app.py true apache-2.0
AI
LLM
fine-tuning
training
education
non-profit
zoo-labs

🏋️ Gym - AI Model Training Platform

By Zoo Labs Foundation Inc - A 501(c)(3) Non-Profit Organization

🌟 Mission

Gym is an open-source platform that democratizes AI model training and fine-tuning, making advanced AI accessible to researchers, educators, and developers worldwide.

🚀 Features

  • 100+ Supported Models: Fine-tune LLaMA, Mistral, Qwen, DeepSeek, and more
  • Zero-Code Interface: User-friendly web UI for non-technical users
  • Advanced Training Methods: LoRA, QLoRA, Full Fine-tuning, DPO, PPO, and more
  • Multi-Modal Support: Text, vision, and multi-modal model training
  • Educational Focus: Built for learning and research

💡 Quick Start

Using this Space

  1. Select a Model: Choose from our pre-configured model list
  2. Upload Your Data: Use your own dataset or select from examples
  3. Configure Training: Adjust parameters or use our recommended settings
  4. Start Training: Click train and monitor progress in real-time
  5. Export Model: Download your fine-tuned model or push to Hugging Face Hub

Fork and Deploy

To create your own instance:

# Clone from Hugging Face
git clone https://huggingface.co/spaces/zooai/gym

# Or from GitHub
git clone https://github.com/zooai/gym

📚 Documentation

🤝 Community & Support

🎯 Use Cases

  • Research: Fine-tune models for academic research
  • Education: Teach AI/ML concepts with hands-on training
  • Development: Prototype and test model variations
  • Non-Profit: Deploy AI solutions for social good

🛡️ Security & Privacy

  • All training happens in your own environment
  • No data is sent to external servers
  • Models remain under your control
  • Apache 2.0 licensed for maximum flexibility

💖 Support Our Mission

As a 501(c)(3) non-profit, Zoo Labs Foundation relies on community support to maintain and improve Gym.

📋 Requirements

  • GPU Memory: Minimum 8GB VRAM recommended
  • Disk Space: 20GB+ for models and datasets
  • Internet: Required for downloading models

🏆 Acknowledgments

Gym builds upon the excellent work of the open-source AI community. We're grateful to all contributors who make AI accessible to everyone.

📄 License

Apache License 2.0 - Free for commercial and non-commercial use.


Zoo Labs Foundation Inc is a 501(c)(3) non-profit organization dedicated to democratizing AI education and research. Learn more at zoo.ngo