Kevin Vu

Exxact Corp

Kevin Vu manages Exxact Corp blog and works with many of its talented authors who write about different aspects of Deep Learning.

Top 5 Tips for Fine-Tuning LLMs

By Kevin Vu, Exxact Corp on December 6, 2024 in Language Models
Whether you’re building an LLM from scratch or augmenting an LLM with additional finetuning data, following these tips will deliver a more robust model.
How To Improve the Performance of a RAG Model

By Kevin Vu, Exxact Corp on September 27, 2024 in Language Models
In this article, we will focus on how to optimize RAG systems to be as efficient as possible. We’ll cover RAG systems from multiple perspectives, diving deeper into their purpose and how we can optimize them.
History and Future of LLMs

By Kevin Vu, Exxact Corp on August 2, 2024 in Language Models
Check out this concise history and future of large language models.
Why the Newest LLMs use a MoE (Mixture of Experts) Architecture

By Kevin Vu, Exxact Corp on July 26, 2024 in Language Models
When it comes to AI, every expert in an MoE model specializes in a much larger problem—just like every doctor specializes in their medical field. This improves efficiency and increases system efficacy and accuracy.
How Retrieval Augment Generation Makes LLMs Smarter

By Kevin Vu, Exxact Corp on July 19, 2024 in Language Models
One counter to LLMs making up bogus sources or coming up with inaccuracies is retrieval-augmented generation or RAG. Not only can RAG decrease the tendency of LLMs to hallucinate but several other advantages as well.
Managing Python Dependencies with Poetry vs Conda & Pip

By Kevin Vu, Exxact Corp on July 12, 2024 in Python
Pip and Conda remain valuable choices for managing dependencies, with Conda's versatility in handling diverse dependencies. Poetry, on the other hand, provides a modernized and comprehensive solution, offering simplicity in managing Python projects and their dependencies.
How to Speed Up Python Pandas by Over 300x

By Kevin Vu, Exxact Corp on July 5, 2024 in Python
In this blog, we will define Pandas and provide an example of how you can vectorize your Python code to optimize dataset analysis using Pandas to speed up your code over 300x times faster.
Diffusion and Denoising: Explaining Text-to-Image Generative AI

By Kevin Vu, Exxact Corp on June 7, 2024 in Artificial Intelligence
The diffusion process is taking a central role in the evolution of AI and the interaction of technology with the global human environment. Learn all about it here.
Quantization and LLMs: Condensing Models to Manageable Sizes

By Kevin Vu, Exxact Corp on May 24, 2024 in Language Models
High costs can make it challenging for small business deployments to train and power an advanced AI. Here is where quantization comes in handy.
Extractive Summarization with LLM using BERT

By Kevin Vu, Exxact Corp on March 5, 2024 in Natural Language Processing
An in-depth overview of extractive text summarization, how state-of-the-art NLP models like BERT can enhance it, and a coding tutorial for using BERT to generate extractive summaries.

Kevin Vu

Latest Posts

Top Posts