10 insightful strategies to use embeddings for leveraging data at its fullest in a variety of ML tasks, models, or projects as a whole.
Quantizing LLMs Step-by-Step: Converting FP16 Models to GGUF
Learn to run large AI models locally with just a few simple steps.
Supervised Learning: The Foundation of Predictive Modeling
In the latest entry in our series on visualizing the foundations of machine learning, we focus on supervised learning, the foundation of predictive modeling.
A Gentle Introduction to Language Model Fine-tuning
After pretraining, a language model learns about human languages. You can enhance the model’s domain-specific understanding by training it on additional data. You can also train the model to perform specific tasks when you provide a specific instruction. These additional training after pretraining is called fine-tuning. In this article, you will learn how to fine-tune […]
Mastering LLM Tool Calling: The Complete Framework for Connecting Models to the Real World
Learn the three-pillar framework for building production-ready LLM agents using data access, computation, and actions tools.
7 Agentic AI Trends to Watch in 2026
Discover the seven emerging trends reshaping agentic AI in 2026, from multi-agent orchestration to production scaling challenges.
Gradient Descent:The Engine of Machine Learning Optimization
This article is the first entry in our series on visualizing the foundations of machine learning, focusing on the engine of machine learning optimization: gradient descent.
Train Your Large Model on Multiple GPUs with Tensor Parallelism
Tensor parallelism is a model-parallelism technique that shards a tensor along a specific dimension. It distributes the computation of a tensor across multiple devices with minimal communication overhead. This technique is suitable for models with very large parameter tensors where even a single matrix multiplication is too large to fit on a single GPU. In […]
Train Your Large Model on Multiple GPUs with Fully Sharded Data Parallelism
Some language models are too large to train on a single GPU. In addition to creating the model as a pipeline of stages, as in Pipeline Parallelism, you can split the model across multiple GPUs using Fully Sharded Data Parallelism (FSDP). In this article, you will learn how to use FSDP to split models for […]
Beyond Short-term Memory: The 3 Types of Long-term Memory AI Agents Need
Discover the three types of long-term memory that transform AI agents from simple chatbots into autonomous systems that learn and adapt.