The Sarus Blog

Welcome to the Sarus Blog. Here we discuss product updates, industry examples, privacy, data protection, data governance, math, machine learning, and much more! 

LLM DP fine-tuning with Sarus in a Databricks workspace

Learn how to use a Python library to fine-tune a LLM in Databricks, protecting sensitive data with Differential Privacy.

Fine-Tuning GPT-4o mini: Privacy not Included

Fine-tuning is more accessible than ever, thanks to services such as OpenAI’s. But fine-tuned GPT-4o-mini models are blabbermouths

Why anonymizing connected car data is so hard!

The untapped value of connected car data.

Discovering New Knowledge while Protecting Privacy

You can fine-tune an LLM to learn new knowledge from private data, ensuring that no sensitive records are at risk of being regurgitated.

Fine-tuning Mistral 7B with QLoRA for new knowledge learning

Language models do classify well but memorize even better, posing privacy risks.

Sarus Activate: take action on private data without revealing it

Sarus Activate lets data scientists analyze and act on private data without viewing it, ensuring privacy-by-design in workflows for various industries

An open-source dataset to test LLM private knowledge understanding

Sarus just released "medical_extended" a benchmark dataset to study privacy preserving AI

[Product Update] Sarus Data Catalog

Introducing the Catalog feature: Empowering Data Consumers for Data Collaboration

Considerations around Privacy in RAG-Based Architectures

Taking RAG to production? Here are the key privacy and security considerations

Generate Time-Series Data with Fine-Tuned Mistral 7B Instruct

Small open-weights vs OpenAI API for synthetic data

David vs. Goliath in AI

Can Fine-Tuned Smaller Models like XLNet, DistilBERT and T5 Compete with Large Models for Classification Tasks?

Quickly Generate Time-Series Synthetic Data with OpenAI’s Fine-Tuning API

Beyond Few-Shot Learning: How LLMs Excel in Synthetic Data Generation Through Fine-Tuning