Published inTowards Data Science·PinnedMember-only9 Distance Measures in Data ScienceThe advantages and pitfalls of common distance measures — Many algorithms, whether supervised or unsupervised, make use of distance measures. These measures, such as euclidean distance or cosine similarity, can often be found in algorithms such as k-NN, UMAP, HDBSCAN, etc. Understanding the field of distance measures is more important than you might realize. Take k-NN for example, a…Data Science10 min readData Science10 min read
Published inTowards Data Science·Nov 14Member-onlyWhich Quantization Method is Right for You? (GPTQ vs. GGUF vs. AWQ)Exploring Pre-Quantized Large Language Models — Throughout the last year, we have seen the Wild West of Large Language Models (LLMs). The pace at which new technology and models were released was astounding! As a result, we have many different standards and ways of working with LLMs. In this article, we will explore one such topic…Data Science11 min readData Science11 min read
Published inTowards Data Science·Oct 5Member-onlyIntroducing KeyLLM — Keyword Extraction with LLMsUse KeyLLM, KeyBERT, and Mistral 7B to extract keywords — Large Language Models (LLMs) are becoming smaller, faster, and more efficient. Up to the point where I started to consider them for iterative tasks, like keyword extraction. Having created KeyBERT, I felt that it was time to extend the package to also include LLMs. They are quite powerful and I…Data Science9 min readData Science9 min read
Published inTowards Data Science·Sep 15Member-only3 Easy Methods For Improving Your Large Language ModelEnhancing the power of Llama 2 — Large Language Models (LLMs) are here to stay. With the recent release of Llama 2, open-source LLMs are approaching the performance of ChatGPT and with proper tuning can even exceed it. Using these LLMs is often not as straightforward as it seems especially if you want to fine-tune the LLM…Data Science12 min readData Science12 min read
Published inTowards Data Science·Aug 22Member-onlyTopic Modeling with Llama 2Create easily interpretable topics with Large Language Models — With the advent of Llama 2, running strong LLMs locally has become more and more a reality. Its accuracy approaches OpenAI’s GPT-3.5, which serves well for many use cases. In this article, we will explore how we can use Llama2 for Topic Modeling without the need to pass every single…Large Language Models12 min readLarge Language Models12 min read
Published inTowards Data Science·Aug 8Member-onlyDecoding Auto-GPTThe Mechanics of an Autonomous GPT-4 — There have been many interesting, complex, and innovative solutions since the release of ChatGPT. The community has explored countless possibilities for improving its capabilities. One of those is the well-known Auto-GPT package. With more than 140k stars, it is one of the highest-ranking repositories on Github!Data Science8 min readData Science8 min read
Published inTowards Data Science·Jun 29Member-onlyGPT and Human PsychologyAnalogies with Human Thinking and Reasoning. — The state of AI has changed drastically with generative text models, such as ChatGPT, GPT-4, and many others. These GPT (Generative Pretrained Transformer) models seemingly removed the threshold for diving into Artificial intelligence for those without a technical background. …Psychology13 min readPsychology13 min read
Published inRAPIDS AI·Jan 19Faster Topic Modeling with BERTopic and RAPIDS cuMLAuthors (alphabetical): Nick Becker (NVIDIA), Dante Gama Dessavre (NVIDIA), Maarten Grootendorst (BERTopic), and Corey Nolet (NVIDIA) Introduction BERTopic is a topic modeling framework that brings neural network embeddings and classical machine learning techniques together into a state-of-the-art solution. The library provides a friendly user interface for many different tasks, including guided…Data Science7 min readData Science7 min read
Published inTowards Data Science·Nov 21, 2022Member-onlyUsing Whisper and BERTopic to model Kurzgesagt’s videosWhich topics can we find in the videos of Kurzgesagt? — A little over a month ago, OpenAI released a neural net for English speech recognition called Whisper. It has gained quite some popularity over the last few weeks due to its accuracy, ease of use, and most importantly because they open-sourced it! With these kinds of releases, I can hardly…Data Science8 min readData Science8 min read
Published inTowards Data Science·Nov 7, 2022Member-only6 Lessons I learned from developing Open-Source ProjectsA Data Scientist’s Perspective — Open-source is such an amazing concept! By bundling the sources, skills, and knowledge of an entire community, tools can be created that we could have not made in isolation. The tools that come out of these collaborations are truly more than the sum of their parts. As a result, we…Data Science6 min readData Science6 min read
