In this post, we explore the process of fine-tuning a language model for function-calling using MLX-LM. Following the Hugging Face Agents course notebook, we’ll walk through the steps from setting up the environment to training the model with LoRA adapters. The goal is to empower the model with the ability to intelligently plan and generate function calls, making it a versatile tool for interactive applications. Medium post can be found here

In this post, we are going to show a tutorial on using the Qwen2.5-VL model with MLX-VLM for visual understanding tasks. We are going to cover:

This blog post is going to be a tutorial on how to fine-tune a LLM with LoRA and the mlx-lm package. Medium post can be found here and Substack here.

In this post we are going to explore the so called orthogonal functions, and some of their properties. We are also going to show that these orthogonal functions are closely related to the least-squares approximation method. This alternative to the least-squares method can be helpful in certain cases when the least-squares produces a hard to solve linear system.

Chebyshev polynomials are a sequence of orthogonal polynomials that play a central role in numerical analysis, approximation theory, and applied mathematics. They are named after the Russian mathematician Pafnuty Chebyshev and come in two primary types: Chebyshev polynomials of the first kind (\(T_n(x)\)) and Chebyshev polynomials of the second kind (\(U_n(x)\)). In this post we are going to focus on the Chebyshev polynomials of the first kind.

In this post we are going to explore the Fourier method for solving the 1D wave equation. The method is more known under the name of the method of separation of variables. For the 1D wave equation we are going to show the application of the method to a fixed string. We are also going to attempt to outline some of the physical interpretations of the fixed string.