We can expect it to be released in November, maybe on the 2nd anniversary of the legendary ChatGPT launch

In similar timeframes, we will also be getting Gemini 2 Ultra, LLaMA-3, Claude-3, Mistral-2 and many other groundbreaking models

(Google’s Gemini already seems to be giving tough competition to GPT-4 turbo)

Introduction

Large Language Models (LLMs) are increasingly utilised across various domains, including question answering over private enterprise documents, where data security and robustness are paramount.

Retrieval-Augmented Generation (RAG) is a prominent framework for building such applications, but ensuring its robustness requires extensive customisation.

In this article, we are going to fine-tune Mistral 7b on the entire code base of a game called Enlighten, all for free in Google Colab(or Kaggle) with synthetic data. The resulting model will outperform Openai’s GPT-4 on our benchmark.

These are the steps:

Introduction

When it comes to bestowing Large Language Models (LLMs) with long-term memory, the prevalent approach often involves a Retrieval Augmented Generation (RAG) solution, with vector databases acting as the storage mechanism for the long-term memory. This begs the question: Can we achieve the same results without vector databases?

从LLM将现代数据堆栈转换为矢量数据库的数据可观察性，以下是我对2024年顶级数据工程趋势的预测。