Add a first example for the new Dlib layers to build a transform-type network

[Cydral]

This example demonstrates a minimal implementation of a Very Small Language Model (VSLM) using Dlib's Transformer architecture.
The code showcases key features of the new Transformer layers, including attention mechanisms, positional embeddings, and a classification head, while maintaining a simple character-based tokenization approach.

Using Shakespeare's text as training data, the example illustrates both the training process and text generation capabilities, making it an excellent educational tool for understanding Transformer architecture basics.
The implementation is intentionally kept lightweight with a small parameter count to ensure quick training and generation while still achieving perfect memorization of training sequences, demonstrating the effectiveness of attention mechanisms in sequence learning tasks.