How to improve the performance of a RAG model
Optimize Retrieval-Augmented Generation (RAG) models by enhancing vectorization, utilizing multiple data sources, and choosing the right language model for improved performance.
Home
Kevin Vu
History and Future of LLMs
LLMs are marvels of modern technology. They’re complex in their function, massive in size, and enable groundbreaking advancements. Go over the history and future of LLMs.
Why the newest LLMs use a MoE (Mixture of Experts) architecture
Mixture of Experts (MoE) architecture is defined by a mix or blend of different “expert” models working together to complete a specific problem.
How Retrieval Augment Generation (RAG) makes LLMs smarter than before
By feeding LLMs the necessary domain knowledge, prompts can be given context and yield better results. RAG can decrease hallucination along with several other advantages.
Quantization and LLMs – Condensing models to manageable sizes
The scale and complexity of LLMs The incredible abilities of LLMs are powered by their vast neural networks which are made up of billions of… Read More »Quantization and LLMs – Condensing models to manageable sizes
Diffusion and denoising – Explaining text-to-image generative AI
The concept of diffusion Denoising diffusion models are trained to pull patterns out of noise, to generate a desirable image. The training process involves showing… Read More »Diffusion and denoising – Explaining text-to-image generative AI
Question answering tutorial with Hugging Face BERT
What is Question Answering AI Question answering AI refers to systems and models designed to understand natural language questions posed by users and provide relevant… Read More »Question answering tutorial with Hugging Face BERT