Domain-Specific Open Source LLMs

Technical guides and implementation details for adapting specialised open source language models for specific domains and use cases. From cybersecurity assistants to industry-specific assistants, these posts cover the complete process of adapting open source LLMs like Llama for targeted applications. Includes data curation, training strategies, optimisation techniques, and practical deployment methods for creating focused, efficient domain-specific AI assistants.

Turning Llama 3.2 Into a Legal Q&A Pro: Fine-Tuning a Model for UK Legislation - Part 2

In the first part of this series, I shared how I pretrained Meta’s Llama 3.2 model to focus on UK legislation. The goal? To create a...

Nov 30, 20246 min read

23 views

Making a Domain-Specific UK Legislation LLM - Part 1: Pretraining

Continued Pretraining of Llama 3.2 3B for Legal Domain Knowledge In this article, I’ll walk you through how we’re enhancing Meta’s Llama...

Nov 23, 20244 min read

37 views

Building SARA: A Lightweight Cybersecurity Assistant for Everyday Laptops

Introduction: The Challenge of an Offline Cybersecurity Assistant The concept of building an AI assistant for cybersecurity that could...

Nov 15, 202411 min read

58 views