{"name":"xTuring: Build, Personalize, and Control Your Own LLMs","description":"xTuring is an open-source framework designed to simplify the process of building, personalizing, and controlling Large Language Models (LLMs). It provides an easy way to fine-tune open-source LLMs on your own data, offering features from data pre-processing to efficient training and inference. This tool empowers developers to create private, personalized LLMs locally or in their private cloud environments.","github":"https://github.com/stochasticai/xTuring","url":"https://osrepos.com/repo/stochasticai-xturing","source":"osrepos.com","sourceDescription":"This repository profile is provided by osrepos.com, an open source repository discovery platform.","repositoryProfile":"https://osrepos.com/repo/stochasticai-xturing","generatedFor":"open source discovery and AI-assisted research","markdown":"https://osrepos.com/repo/stochasticai-xturing.md","json":"https://osrepos.com/repo/stochasticai-xturing.json","topics":["Python","LLM","Fine-tuning","Generative AI","Deep Learning","LoRA","Quantization","Language Model"],"keywords":["Python","LLM","Fine-tuning","Generative AI","Deep Learning","LoRA","Quantization","Language Model"],"stars":null,"summary":"xTuring is an open-source framework designed to simplify the process of building, personalizing, and controlling Large Language Models (LLMs). It provides an easy way to fine-tune open-source LLMs on your own data, offering features from data pre-processing to efficient training and inference. This tool empowers developers to create private, personalized LLMs locally or in their private cloud environments.","content":"## Introduction\n\nxTuring is an open-source framework that simplifies the building, personalization, and control of Large Language Models (LLMs). It offers an easy way to personalize open-source LLMs, from data pre-processing to fine-tuning. With xTuring, you can fine-tune, evaluate, and run private, personalized LLMs locally or in your private cloud, making the process fast and cost-efficient.\n\n## Installation\n\nTo start using xTuring, you can install it via pip:\n\nbash\npip install xturing\n\n\n## Examples\n\nxTuring provides a simple API for fine-tuning and generation. Here's a quick example to fine-tune a lightweight model and generate text:\n\npython\nfrom xturing.datasets import InstructionDataset\nfrom xturing.models import BaseModel\n\n# Load a toy instruction dataset (Alpaca format)\ndataset = InstructionDataset(\"./examples/models/llama/alpaca_data\")\n\n# Start with the lightweight Qwen 0.6B LoRA checkpoint\nmodel = BaseModel.create(\"qwen3_0_6b_lora\")\n\n# Fine-tune and then generate\nmodel.finetune(dataset=dataset)\noutput = model.generate(texts=[\"Explain quantum computing for beginners.\"])\nprint(f\"Model output: {output}\")\n\n\nAdditionally, xTuring includes command-line interface (CLI) and user interface (UI) playgrounds for experimenting and interacting with your models.\n\n## Why Use xTuring\n\nxTuring stands out for several reasons, making it a powerful choice for LLM personalization:\n\n*   **Simple API**: Offers an intuitive API for data preparation, training, and inference.\n*   **Private by Default**: Allows you to run models locally or in your VPC, ensuring data privacy.\n*   **Efficient**: Utilizes techniques like LoRA and low-precision (INT8/INT4) to cut costs and resource requirements.\n*   **Scalable**: Scales easily from CPU/laptop to multi-GPU configurations.\n*   **Model Evaluation**: Includes built-in metrics, such as perplexity, to evaluate model performance.\n\n## Links\n\n*   **GitHub Repository**: [https://github.com/stochasticai/xTuring](https://github.com/stochasticai/xTuring)\n*   **Documentation**: [https://xturing.stochastic.ai/](https://xturing.stochastic.ai/)\n*   **Discord Community**: [https://discord.gg/TgHXuSJEk6](https://discord.gg/TgHXuSJEk6)","metrics":{"detailViews":3,"githubClicks":1},"dates":{"published":null,"modified":"2026-07-06T07:45:52.000Z"}}