OneRange

Fine-tuning & Model Customization

This course helps technical teams decide when and how to customize models beyond prompting and RAG. It covers fine-tune versus RAG versus prompt, data preparation, training and evaluation, and deployment and maintenance. Learners finish able to make and execute the right customization decision.

What this course covers

The course runs across 6 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.

  • Architectural Decisions: Prompting, RAG, and Fine-Tuning — Evaluate the trade-offs between prompt engineering, Retrieval-Augmented Generation (RAG), and fine-tuning. Analyze cost, latency, domain specificity, and implementation complexity to select the optimal customization strategy for specific use cases.
  • Data Engineering and Formatting for Fine-Tuning — Source, clean, and structure raw datasets into training-ready formats (such as JSONL for chat completion). Implement validation scripts to check for formatting errors, token limits, and data distribution issues.
  • Configuring Hyperparameters and Launching Training Jobs — Configure critical hyperparameters including learning rate, epochs, and batch size. Programmatically initiate and monitor fine-tuning runs using cloud APIs and command-line interfaces.
  • Evaluating Fine-Tuned Model Performance — Assess post-training performance using quantitative metrics (loss curves, token accuracy) and qualitative evaluation frameworks. Set up automated test suites to compare the fine-tuned model against baseline models.
  • Model Deployment and Hosting Infrastructure — Deploy the fine-tuned model to a production-grade hosting environment. Configure autoscaling, manage concurrency, optimize inference latency, and set up secure API endpoints for application integration.
  • Production Maintenance, Monitoring, and Iteration — Establish monitoring pipelines to track inference costs, latency, and data drift in production. Design data feedback loops to continuously collect edge cases and refine the model through iterative training runs.

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 Model Evaluation & Selection, Fine-tuning, Retrieval-Augmented Generation (RAG), Fine-tuning LLMs, Model Monitoring & Maintenance.

  • Model Evaluation & Selection
  • Fine-tuning
  • Retrieval-Augmented Generation (RAG)
  • Fine-tuning LLMs
  • Model Monitoring & Maintenance

Who it is for

ML/AI builders, technical teams. The material is pitched at expert 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: Customization 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 branching scenario, code lab, guided lab exercises. There is no video to sit through and no slide deck to click past.

Understanding is checked with a code 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.

Related

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-FT.