AI & Technology Course Catalog

LLM Customisation & Model Adaptation Prompting, RAG or Fine-Tuning: LLM Adaptation Decision Framework RuneLab Academy · 18 hours

Hands-on course on choosing and combining context engineering, RAG and fine-tuning based on knowledge freshness, style/behaviour alignment, latency and TCO, producing an adaptation decision matrix.

18 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Model and Data Readiness: Base Model Selection and Data Suitability RuneLab Academy · 12 hours

Course on selecting open-weight or commercial base models by size, licence, tokenizer and hardware footprint, and auditing enterprise data volume, quality and privacy readiness before adaptation.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Quality, Cost and Risk Analysis in LLM Adaptation RuneLab Academy · 12 hours

Course on modelling total cost of ownership (data curation, training and 24/7 serving), quality-versus-regression trade-offs and operational/regulatory risks for LLM customisation projects.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Baselines and Success Metrics: Pre-Adaptation Benchmarking for LLMs RuneLab Academy · 12 hours

Course on building golden test sets, establishing zero/few-shot baselines, defining deterministic and LLM-as-a-judge metrics and setting acceptance thresholds before starting model adaptation.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Fine-Tuning Fundamentals: Introduction to Customising LLMs RuneLab Academy · 18 hours

Foundational hands-on course on how LLM fine-tuning works: dataset formatting, chat templates, running a first adapter training job with Hugging Face TRL and Unsloth, and avoiding overfitting.

18 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Advanced Fine-Tuning: Continual Pre-Training, Long Context and Model Merging RuneLab Academy · 18 hours

Advanced course covering continual pre-training (CPT), RoPE long-context extension, multi-turn tool-calling fine-tuning, catastrophic forgetting mitigation and model merging (SLERP, TIES, DARE) with MergeKit.

18 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Supervised Fine-Tuning (SFT): Engineering and Optimisation RuneLab Academy · 18 hours

Deep-dive engineering course on Supervised Fine-Tuning (SFT): completion-only loss masking, sequence packing, FlashAttention-2, NEFTune, learning rate schedules and production workflows with TRL SFTTrainer and Axolotl.

18 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Parameter-Efficient Fine-Tuning (PEFT): Architectures and Multi-Adapter Serving RuneLab Academy · 18 hours

Course on PEFT architectures—LoRA, DoRA, rsLoRA, VeRA, LoftQ, IA3 and Prefix Tuning—VRAM memory budgeting and serving dozens of dynamic adapters on a single base model with vLLM and SGLang.

18 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Practical LLM Fine-Tuning with LoRA and QLoRA RuneLab Academy · 12 hours

Hands-on training on Low-Rank Adaptation (LoRA) and 4-bit NormalFloat (NF4) QLoRA: rank/alpha tuning, target modules, double quantisation, paged optimizers and safe adapter merging.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Instruction Tuning: Following Complex Instructions, Schemas and Domain Constraints RuneLab Academy · 12 hours

Course on designing and running instruction tuning so models reliably follow complex system prompts, strict JSON/schema constraints, corporate tone and refusal boundaries.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Preference Optimization: DPO, ORPO, KTO and LLM Alignment RuneLab Academy · 12 hours

Advanced course on post-SFT alignment using DPO, IPO, KTO, ORPO and SimPO: building chosen/rejected preference datasets, tuning beta and KL constraints, and avoiding length bias and reward hacking.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Synthetic Data Generation: Data Synthesis and Distillation for LLM Training RuneLab Academy · 12 hours

Hands-on course on generating high-diversity SFT and preference datasets in low-resource enterprise domains using teacher LLMs, Evol-Instruct, persona matrices, Distilabel and verification filters.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Training Data Design: Dataset Architecture for LLM Fine-Tuning RuneLab Academy · 12 hours

Hands-on course on designing high-leverage SFT and multi-turn conversation datasets: the LIMA principle, task mixture ratios, expert annotation guidelines, schema design and dataset versioning.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Model Evaluation and Fine-Tuning Evals for Custom LLMs RuneLab Academy · 12 hours

Course on evaluating fine-tuned LLMs for task accuracy, catastrophic forgetting regressions, hallucination and safety drift using lm-evaluation-harness, custom task suites and pairwise arena comparisons.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Open-Weight Model Adaptation: Customising Llama, Qwen, Mistral and Gemma RuneLab Academy · 12 hours

Course on adapting open-weight models—Llama, Qwen, Mistral, Gemma and DeepSeek—for enterprise use: architectural differences, custom tokens, post-training quantisation (AWQ/GGUF/FP8) and self-hosted serving.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Turkish Language Models: Tokenization, Evaluation and Adaptation RuneLab Academy · 12 hours

Course on adapting LLMs for Turkish: morphological challenges in BPE tokenization, vocabulary extension, continual pre-training, Turkish evaluation benchmarks and cultural/regulatory alignment.

12 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Distributed LLM Training with PyTorch FSDP and DeepSpeed RuneLab Academy · 24 hours

Advanced course on scaling LLM training across multi-GPU and multi-node clusters using Data, Tensor, Pipeline and Context Parallelism, DeepSpeed ZeRO-1/2/3, PyTorch FSDP2 and communication profiling.

24 hours

Live Course

5 modules

LLM Customisation & Model Adaptation Reinforcement Learning for Reasoning Models (GRPO and RLVR) RuneLab Academy · 24 hours

Advanced hands-on course on training DeepSeek-R1-style reasoning models using Reinforcement Learning with Verifiable Rewards (RLVR) and critic-free Group Relative Policy Optimization (GRPO).

24 hours

Live Course

5 modules