Introduction

Predibase enables users to fine-tune and serve open-source Large Language Models (LLMs). Built by the creators of popular open-source frameworks such as LoRAX & Ludwig, Predibase provides an integrated platform for hosting, customizing, and querying LLMs.

​

Key Features

• Serving: Deploy and serve models with production-ready private serverless endpoints
  • LoRAX: Our framework that enables serving hundreds of fine-tuned models on a single GPU, dramatically reducing costs
• Post-training: Customize open source LLMs for your specific use case using supervised fine-tuning, reinforcement fine-tuning, or continued pretraining

​

Additional Capabilities

• SaaS or VPC deployment options: Deploy in our cloud or yours
• UI and SDK: Deploy, fine-tune, and prompt via our UI or Python SDK
• Latest open source models: Deploy and train the newest LLMs, VLMs, and embedding models

​

Getting Started

1. Create an account at Predibase
2. Navigate to Settings and generate your API token
3. Install the SDK and configure your environment:

pip install -U predibase
pbase login  # Enter your API token when prompted

​

Next Steps

• Follow our Quickstart guide to deploy and query your first model
• Explore our comprehensive guides on:
  • Fine-tuning
  • Inference
  • Data preparation

​

Contact Us

Need help or have questions? Reach out to us:

• Email: support@predibase.com