Scratch

with Ollama, LangChain, LangGraph (No GPU, No APIKEY)(All images are by the writer unless otherwise noted)IntroPrompt Engineering is the practice of designing and refining prompts (text inputs) to boost the behavior of Large Language...

A step-by-step guide to constructing a Thai multilingual sub-word tokenizer based on a BPE algorithm trained on Thai and English datasets using only PythonPerfect. Our Thai Tokenizer can now successfully and accurately encode and...

LLMs like GPT-3, GPT-4, and their open-source counterpart often struggle with up-to-date information retrieval and might sometimes generate hallucinations or misinformation.Retrieval-Augmented Generation (RAG) is a way that mixes the ability of LLMs with external...

In June 2007, Apple unveiled the primary iPhone. But the corporate made...

Part I: Game concepts and Causal Graphs for LLMsA number of months ago, I used to be debating with a friend concerning the use of Large Language Models (LLMs) in game design.My friend argued...

Solving XOR gate problem— using just NumPy, then compare with PyTorch implementation.Outline・Introduction to the XOR Gate Problem・Constructing a 2-Layer Neural Network・Forward Propagation・Chain Rules for Backpropagation・Implementation with NumPy・Comparing Results with PyTorch・Summary・ReferencesIntroduction to the XOR Gate...

Learn critical knowledge for constructing AI apps, in plain englishRetrieval Augmented Generation, or RAG, is all the craze nowadays since it introduces some serious capabilities to large language models like OpenAI’s GPT-4 — and...

“It’s cool work,” says Matthew Gudzial, an AI researcher on the University of Alberta, who developed a similar game generator just a few years ago.  Genie was trained on 30,000 hours of...