Large Language Models Deep Dive

This course gives a deeper understanding of how large language models work so learners can use and choose them well. It covers architecture and tokens, training and alignment, key parameters, and model selection tradeoffs. Participants finish able to make informed decisions about which model to use and why.

What this course covers

The course runs across 10 topics, each one a short adaptive session rather than a recorded lecture. The tutor explains the idea, works an example, checks understanding, and adjusts the next step to the answer given.

LLM Architecture & Tokenization — Understand the Transformer architecture, attention mechanisms, and how text is converted into tokens. Learn how tokenization affects context windows and billing.
Analyzing Tokenizer Behavior — Hands-on practice using tokenizer tools to inspect how different models process code, non-English text, and numbers, identifying potential efficiency bottlenecks.
Training Phases: Pre-training to Alignment — Explore how models are trained, contrasting the self-supervised pre-training phase with supervised fine-tuning (SFT) and Reinforcement Learning from Human Feedback (RLHF).
Aligning Models for Safety and Utility — A scenario-based exercise evaluating how different alignment techniques affect model helpfulness, harmlessness, and tone in real-world deployments.
Demystifying Model Parameters: Temperature & Top-P — Deep dive into generation parameters. Learn how temperature, top-p, and frequency/presence penalties alter the probability distribution of output tokens.
Hands-on Parameter Tuning — Directly manipulate temperature, top-p, and system prompts in a playground environment to achieve specific creative, deterministic, or structured outputs.
Model Selection: Size, Latency, and Cost Tradeoffs — Analyze the tradeoffs between proprietary frontier models and lightweight open-weights models, focusing on cost, latency, hosting requirements, and data privacy.
Scenario: Architecting an LLM Solution — A branching decision exercise where you select and configure the optimal model, context strategy, and parameters for a strict enterprise budget and latency requirement.
Fine-Tuning vs. RAG (Retrieval-Augmented Generation) — Evaluate when to fine-tune a model for style/task adherence versus when to use RAG to inject dynamic external knowledge.
Scenario: Resolving Performance and Hallucination Issues — Navigate a realistic scenario to diagnose why a deployed model is hallucinating or failing, choosing the correct remediation path (RAG, prompting, or fine-tuning).

Skills you build

Results are measured against named skills in the OneRange taxonomy of more than 10,000 skills, so a manager sees proficiency per skill rather than a completion tick. This course maps to Tokenization, Large Language Models (LLMs), Transformer Models, Model Evaluation & Selection, Fine-tuning LLMs.

Tokenization
Large Language Models (LLMs)
Transformer Models
Model Evaluation & Selection
Fine-tuning LLMs

Who it is for

Builders, technical staff, curious users. The material is pitched at intermediate level, and takes roughly 150 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

It sits in the Category: LLMs track of the Vero AI Catalog, and can be assigned to one person, a team, or the whole company.

How it is delivered and assessed

Delivery is conversational and interactive, including guided lab, branching scenario exercises. There is no video to sit through and no slide deck to click past.

Understanding is checked with a quiz assessment of 5 items, with a pass mark of 70%.

Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Also in this track

Reasoning Models in Practice — A practical course on reasoning-class models: what extended thinking buys you, when it is worth the cost and latency, and how to prompt them well. Learners compare standard and reasoning models on real tasks.
Small & Efficient Models — This course covers the economics and technique of small models: what they can genuinely do, distillation concepts, on-device deployment, and routing between small and frontier models by task.
Become an AI Builder — Technical foundation to build AI applications
Knowledge & Search Systems (RAG) — Ground AI in your organization's data

Frequently asked questions

How long does this course take?

It runs roughly 150 minutes at a typical pace. Because every session adapts, someone who already knows a topic moves through it quickly instead of sitting through an explanation they do not need.

How is it assigned to a team?

An administrator assigns it from the Vero dashboard to one person, a team, a department or the whole company, and sees progress and results per person and per skill.

Can we customise it with our own documents and terminology?

Yes. Administrators can copy this course into their own library and adapt it — edit the outline, change the duration, swap the assessment format, or ground it in internal documentation so answers cite the company's own source material.

Course code CAT-LLM.