Operating Intelligence - Cedric Vidal https://vidal.biz/posts.html Operating Intelligence by Cedric Vidal. Writing about building, evaluating, and scaling intelligent systems in production. https://vidal.biz/profile.jpeg Operating Intelligence - Cedric Vidal https://vidal.biz/posts.html quarto-1.8.27 Thu, 31 Oct 2024 00:00:00 GMT LLM Distillation just got easier - Part 4 - Maximize your fine-tuned model performance with the new Azure AI Evaluation SDK https://vidal.biz/ 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 advanced metrics. Evaluation https://vidal.biz/ Thu, 31 Oct 2024 00:00:00 GMT LLM Distillation just got easier - Part 3 - Deploying your LoRA Fine-tuned Llama 3.1 8B model, why it's a breeze! https://vidal.biz/ Learn how Azure AI makes it effortless to deploy your LoRA fine-tuned models using Azure AI. Infrastructure https://vidal.biz/ Thu, 24 Oct 2024 00:00:00 GMT Thoughts about OpenAI’s new Distillation feature Cedric Vidal https://vidal.biz/posts/2024-10-02-openai-distillation-thoughts/ Synthetic Data Distillation—on which I wrote previously and coded a ⁠raft-distillation-recipe repository Github repository—this approach leverages Production Data driven Distillation. This innovative method harnesses real-time production data, offering a dynamic and practical alternative for optimizing AI models. ]]> Strategy https://vidal.biz/posts/2024-10-02-openai-distillation-thoughts/ Wed, 02 Oct 2024 00:00:00 GMT LLM Distillation just got easier - Part 2 - Fine-Tuning Llama 3.1 8B on Azure AI Serverless https://vidal.biz/ How Azure AI Serverless Fine-tuning, LoRA, RAFT and the AI Python SDK are streamlining fine-tuning of domain specific models. Infrastructure https://vidal.biz/ Wed, 18 Sep 2024 00:00:00 GMT LLM Distillation just got easier - Part 1 - Synthetic Data Gen with Llama 3.1 405B & RAFT https://vidal.biz/ How Llama 405B and RAFT on Azure AI are changing the landscape of synthetic dataset generation and making model distillation much more approachable Infrastructure https://vidal.biz/ Wed, 04 Sep 2024 00:00:00 GMT GoEX: a safer way to build autonomous Agentic AI applications https://vidal.biz/ 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 Systems https://vidal.biz/ Wed, 24 Apr 2024 00:00:00 GMT RAFT: A new way to teach LLMs to be better at RAG https://vidal.biz/ 'Retrieval-Augmented Fine-Tuning' combines the benefits of Retrieval-Augmented Generation and Fine-Tuning for better domain adaptation Infrastructure https://vidal.biz/ Fri, 15 Mar 2024 00:00:00 GMT