December 6, 2023
We Fine-Tuned GPT-4 to Beat the Industry Standard for Text2SQL
Our machine learning team at Scale has recently fine-tuned GPT-4 to achieve state-of-the-art performance (84% accuracy) for generalized text-to-SQL translation on one of the most popular benchmark datasets, the SpiderDev Set. In this blog post, we will discuss why text2sql is an important use case..
Read more
October 24, 2023
Enhancing LLMs with Retrieval Augmented Generation
RAG enhances Generative AI by integrating external data into prompts, enabling context-driven outputs. This blog explores RAG's significance, mechanics, and enhancements for enterprise applications.
Read more
January 25, 2023
Why is ChatGPT so good?
LLMs have evolved from simple next-word predictors into systems that follow complex instructions and deliver genuinely useful responses. Powered by instruction-tuning and RLHF, today’s models can write, summarize, and problem-solve far beyond what GPT-3 could do. This blog explains how these advances happened and how you can fine-tune such models yourself.
Read more
September 22, 2022
How to Make Your Own AI-Generated Images
Read more
September 13, 2022
The 10 Best Public Datasets for Object Detection in 2022
Great ML models start with great training data. But if you're just starting out, don't worry—public datasets can be your launchpad into data-centric AI!
Read more
August 23, 2022
How to Handle Long Tail Data Distributions in Machine Learning
Read more