xTuring: Build, Personalize, and Control Your Own LLMs

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.

Use at your own risk

OSRepos shares public repositories for knowledge and discovery only. Any installation, execution, configuration, or use of code from these repositories is the user's own responsibility. Always review the repository, source code, dependencies, licenses, and security implications before running or installing anything. OSRepos is not responsible for issues, damages, or losses resulting from third-party repositories.

Introduction

xTuring 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.

Installation

To start using xTuring, you can install it via pip:

pip install xturing

Examples

xTuring provides a simple API for fine-tuning and generation. Here's a quick example to fine-tune a lightweight model and generate text:

from xturing.datasets import InstructionDataset
from xturing.models import BaseModel

# Load a toy instruction dataset (Alpaca format)
dataset = InstructionDataset("./examples/models/llama/alpaca_data")

# Start with the lightweight Qwen 0.6B LoRA checkpoint
model = BaseModel.create("qwen3_0_6b_lora")

# Fine-tune and then generate
model.finetune(dataset=dataset)
output = model.generate(texts=["Explain quantum computing for beginners."])
print(f"Model output: {output}")

Additionally, xTuring includes command-line interface (CLI) and user interface (UI) playgrounds for experimenting and interacting with your models.

Why Use xTuring

xTuring stands out for several reasons, making it a powerful choice for LLM personalization:

Simple API: Offers an intuitive API for data preparation, training, and inference.
Private by Default: Allows you to run models locally or in your VPC, ensuring data privacy.
Efficient: Utilizes techniques like LoRA and low-precision (INT8/INT4) to cut costs and resource requirements.
Scalable: Scales easily from CPU/laptop to multi-GPU configurations.
Model Evaluation: Includes built-in metrics, such as perplexity, to evaluate model performance.