Posts

Writing about building, evaluating, and scaling intelligent systems in production.

LLM Distillation just got easier - Part 4 - Maximize your fine-tuned model performance with the new Azure AI Evaluation SDK
Evaluation

Discover how to enhance AI model performance with the Azure AI Evaluation SDK. Learn the evaluation process of fine-tuned models, compare distilled and baseline models using…

Oct 31, 2024

LLM Distillation just got easier - Part 3 - Deploying your LoRA Fine-tuned Llama 3.1 8B model, why it’s a breeze!
Infrastructure

Learn how Azure AI makes it effortless to deploy your LoRA fine-tuned models using Azure AI.

Oct 24, 2024

Thoughts about OpenAI’s new Distillation feature
Strategy
OpenAI has recently introduced a compelling new distillation feature, setting itself apart from traditional methods. Unlike Synthetic Data Distillation—on which I wrote…
Cedric Vidal
Oct 2, 2024

LLM Distillation just got easier - Part 2 - Fine-Tuning Llama 3.1 8B on Azure AI Serverless
Infrastructure

How Azure AI Serverless Fine-tuning, LoRA, RAFT and the AI Python SDK are streamlining fine-tuning of domain specific models.

Sep 18, 2024

LLM Distillation just got easier - Part 1 - Synthetic Data Gen with Llama 3.1 405B & RAFT
Infrastructure

How Llama 405B and RAFT on Azure AI are changing the landscape of synthetic dataset generation and making model distillation much more approachable

Sep 4, 2024

GoEX: a safer way to build autonomous Agentic AI applications
Systems

The Gorilla Execution Engine, from a paper by the UC Berkeley researchers behind Gorilla LLM and RAFT, helps developers create safer and more private Agentic AI applications

Apr 24, 2024

RAFT: A new way to teach LLMs to be better at RAG
Infrastructure

‘Retrieval-Augmented Fine-Tuning’ combines the benefits of Retrieval-Augmented Generation and Fine-Tuning for better domain adaptation

Mar 15, 2024
No matching items