Part 10: From RAG to Harness. I tried building a mechanism to let a local LLM 'choose its own tools'

Up until the last installment, I verified the process of combining RAG with a local LLM to have it answer questions while ...

From How Many Billion Parameters Can You Use a Local LLM? Real-World Implementation Insights from Testing 1B to 27B Models

When choosing a local LLM, the first thing that catches your eye is the model size. 1B, 4B, 8B, 12B, 27B. The larger the number, the smarter it seems, and in reality, benchmarks generally reflect that ...
Hackaday

An LLM From “Scratch”

Reading a book about bowling is not the same as actually bowling. If that resonates with you and you want to learn more about large language models, check out the LLM From Scratch project. The ...