{"name":"WeClone: Create Your AI Digital Twin from Chat History with LLMs","description":"WeClone is an innovative open-source project that provides a comprehensive solution for creating your personal AI digital twin. It allows users to fine-tune Large Language Models (LLMs) using their chat history, capturing unique communication styles. The resulting AI can then be integrated with various chatbots, bringing your digital self to life.","github":"https://github.com/xming521/WeClone","url":"https://osrepos.com/repo/xming521-weclone","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/xming521-weclone","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/xming521-weclone.md","json":"https://osrepos.com/repo/xming521-weclone.json","topics":["chat-history","digital-avatar","llm","qwen","telegram","Python","AI","Machine Learning"],"keywords":["chat-history","digital-avatar","llm","qwen","telegram","Python","AI","Machine Learning"],"stars":null,"summary":"WeClone is an innovative open-source project that provides a comprehensive solution for creating your personal AI digital twin. It allows users to fine-tune Large Language Models (LLMs) using their chat history, capturing unique communication styles. The resulting AI can then be integrated with various chatbots, bringing your digital self to life.","content":"## Introduction\n\nWeClone is an innovative open-source project designed to create your personal AI digital twin from your chat history. It offers a comprehensive, end-to-end solution for fine-tuning Large Language Models (LLMs) with your unique communication style, allowing you to bring a digital version of yourself to life. The project supports various chat data sources and deployment platforms, emphasizing privacy and localized control over your data.\n\n## Installation\n\nTo get started with WeClone, follow these steps. A CUDA environment (version 12.6 or above) is required.\n\n1.  **Clone the repository:**\n    bash\n    git clone https://github.com/xming521/WeClone.git && cd WeClone\n    \n\n2.  **Set up the environment with `uv` (recommended):**\n    bash\n    uv venv .venv --python=3.12\n    source .venv/bin/activate # For Windows: .venv\\Scripts\\activate\n    uv pip install --group main -e .\n    \n\n3.  **Copy the configuration file:**\n    bash\n    cp examples/tg.template.jsonc settings.jsonc\n    \n    Modify `settings.jsonc` for your specific needs.\n\n4.  **Download models:**\n    It is recommended to use Hugging Face or the following command:\n    bash\n    git lfs install\n    git clone https://huggingface.co/Qwen/Qwen2.5-VL-7B-Instruct models/Qwen2.5-VL-7B-Instruct\n    \n\n## Examples\n\nWeClone provides a clear workflow from data preparation to deployment.\n\n1.  **Data Preparation:** Export your chat history (e.g., from Telegram Desktop) as JSON and place it in the `./dataset/telegram` directory.\n\n2.  **Data Preprocessing:** Configure `settings.jsonc` (e.g., `language`, `platform`, `telegram_args.my_id`) and run:\n    bash\n    weclone-cli make-dataset\n    \n    The project includes privacy filtering for sensitive information.\n\n3.  **Fine-tuning the Model:** Adjust training parameters in `settings.jsonc` and execute:\n    bash\n    weclone-cli train-sft\n    \n    Multi-GPU training is also supported with DeepSpeed.\n\n4.  **Inference and Deployment:**\n    *   **Webchat Demo:** Test your fine-tuned model in a browser:\n        bash\n        weclone-cli webchat-demo\n        \n    *   **API Server:** Start an API service for integration:\n        bash\n        weclone-cli server\n        \n    *   **Deploy to Chatbots:** Integrate your AI twin with platforms like AstrBot or LangBot by configuring them to use the WeClone API service.\n\n## Why Use WeClone?\n\nWeClone stands out as a powerful tool for creating personalized AI avatars due to several key features:\n\n*   **End-to-End Solution:** It covers every step, from chat data export and preprocessing to model training and deployment.\n*   **Personalized LLMs:** Fine-tune models with your actual chat history, including image modal data, to capture your unique style and \"flavor.\"\n*   **Privacy and Control:** Supports localized fine-tuning and deployment, along with privacy information filtering, ensuring your data remains secure and under your control.\n*   **Multi-Platform Integration:** Easily integrate your digital avatar with popular messaging platforms like Telegram, Discord, Slack, and WeChat.\n*   **Active Development:** The project is in rapid iteration, continuously adding new features and improvements.\n\n## Links\n\n*   **GitHub Repository:** [https://github.com/xming521/WeClone](https://github.com/xming521/WeClone)\n*   **Project Homepage:** [https://www.weclone.love/](https://www.weclone.love/)\n*   **Documentation:** [https://docs.weclone.love/docs/introduce/what-is-weclone.html](https://docs.weclone.love/docs/introduce/what-is-weclone.html)","metrics":{"detailViews":3,"githubClicks":3},"dates":{"published":null,"modified":"2026-05-03T08:51:23.000Z"}}