Using Quantized Models with Ollama for Application Development

Quantization is a frequently used strategy applied to production machine learning models, particularly large and complex ones, to make them lightweight by reducing the numerical precision of the model’s parameters (weights) — usually from 32-bit floating-point to lower representations like 8-bit integers.

Tokenizers in Language Models

This post is divided into five parts; they are: • Naive Tokenization • Stemming and Lemmatization • Byte-Pair Encoding (BPE) • WordPiece • SentencePiece and Unigram The simplest form of tokenization splits text into tokens based on whitespace.

A Gentle Introduction to Learning Rate Schedulers

Ever wondered why your neural network seems to get stuck during training, or why it starts strong but fails to reach its full potential? The culprit might be your learning rate – arguably one of the most important hyperparameters in machine learning.

Custom Fine-Tuning for Domain-Specific LLMs

Fine-tuning a large language model (LLM) is the process of taking a pre-trained model — usually a vast one like GPT or Llama models, with millions to billions of weights — and continuing to train it, exposing it to new data so that the model weights (or typically parts of them) get updated.

Custom Fine-Tuning for Domain-Specific LLMs

Fine-tuning a large language model (LLM) is the process of taking a pre-trained model — usually a vast one like GPT or Llama models, with millions to billions of weights — and continuing to train it, exposing it to new data so that the model weights (or typically parts of them) get updated.

Roadmap to Python in 2025

Python has evolved from a simple scripting language to the backbone of modern data science and machine learning.

Roadmap to Python in 2025

Python has evolved from a simple scripting language to the backbone of modern data science and machine learning.