Coding an LLM from the ground up is an excellent exercise to understand its mechanics and limitations. In the usage of Spam, both traditional machine learning and deep learning for spam classification still require the collection of labels, such as spam or non-spam, which need to be gathered either by an expert or users.

https://github.com/rasbt/LLMs-from-scratch

The general process of creating an LLM includes pretraining and fine-tuning. The “pre” in “pretraining” refers to the initial phase where a model like an LLM is trained on a large, diverse dataset to develop a broad understanding of language. This pretrained model then serves as a foundational resource that can be further refined through fine-tuning, a process where the model is specifically trained on a narrower dataset that is more specific to particular tasks or domains. 15.04.25 The transformer architecture consists of two submodules: an encoder and a decoder. The encoder module processes the input text and encodes it into a series of numerical representations or vectors that capture the contextual information of the input. Then, the decoder module takes these encoded vectors and generates the output text. 15.04.25 This first training stage of an LLM is also known as pretraining, creating an initial pretrained LLM, often called a base or foundation model. A typical example of such a model is the GPT-3 model (the precursor of the original model offered in ChatGPT). This model is capable of text completion—that is, finishing a half-written sentence provided by a user. It also has limited few-shot capabilities, which means it can learn to perform new tasks based on only a few examples instead of needing extensive training data. 15.04.25 Today’s LLMs are based on the transformer architecture. Hence, transformers and LLMs are terms that are often used synonymously in the literature. However, note that not all transformers are LLMs since transformers can also be used for computer vision. Also, not all LLMs are transformers, as there are LLMs based on recurrent and convolutional architectures. The main motivation behind these alternative approaches is to improve the computational efficiency of LLMs. Whether these alternative LLM architectures can compete with the capabilities of transformer-based LLMs and whether they are going to be adopted in practice remains to be seen. For simplicity, I use the term “LLM” to refer to transformer-based LLMs similar to GPT. 15.04.25 Remember that LLMs are next word predictors. This means that the text they generate is heavily dependent on the text they are fed, called the context. 15.04.25

• Home
• Notebook
• Contact us

• Privacy Statement
• 

Copyleft ☠ 2026