Advanced Data Prep and Visualisation Techniques for Fine-tuning LLMs

📜Get repo access at Trelis.com/ADVANCED-fine-tuning Tip: If you subscribe here on YouTube, click the bell to be notified of new vids 🛠️ (NEW) Trelis Fine-tuning Workshops: https://trelis.com/workshops-and-semi... 💡 Need Technical or Market Assistance? Book a Consult Here: https://forms.gle/wJXVZXwioKMktjyVA 🤝 Are You a Top Developer? Work for Trelis: https://trelis.com/jobs/ 💸 Starting a New Project/Venture? Apply for a Trelis Grant: https://trelis.com/trelis-ai-grants/ 📧 Get Trelis AI Tutorials by Email Subscribe on Substack: https://trelis.substack.com Video Links: slides: https://docs.google.com/presentation/... TIMESTAMPS: 0:00 Advanced Data Preparation Techniques 0:33 Video Overview 1:52 Synthetic Dataset Generation Goals 3:48 Synthetic Data Generation Pipeline 5:34 Document Ingestion Approaches (e.g. pdf to markdown) - comparing markitdown marker and Gemini 13:44 Chunking Approaches and Trade-offs 22:45 Question-Answer Pair Generation Approaches 31:56 Q-A pair visualization with embeddings or tags AND how to choose a model for synthetic data generation 44:29 How to create an Evaluation Dataset? Best Practice. 54:41 Preview of the upcoming fine-tuning video

Join Today
Train an LLM to Self-Correct with Verifiable Backtracking
▶︎

Train an LLM to Self-Correct with Verifiable Backtracking

Fine tune Gemma 3, Qwen3, Llama 4, Phi 4 and Mistral Small with Unsloth and Transformers
▶︎

Fine tune Gemma 3, Qwen3, Llama 4, Phi 4 and Mistral Small with Unsloth and Transformers

Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers
▶︎

Mastering Retrieval for LLMs - BM25, Fine-tuned Embeddings, and Re-Rankers

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026
▶︎

Keynote: After the AI Hype – What’s Real, and What’s Next - Richard Campbell - 2026

Is RAG Still Needed? Choosing the Best Approach for LLMs
▶︎

Is RAG Still Needed? Choosing the Best Approach for LLMs

Over 6x Faster AI DiffusionGemma Explained, Deployed & Benchmarked. INSANE SPEED!
▶︎

Over 6x Faster AI DiffusionGemma Explained, Deployed & Benchmarked. INSANE SPEED!

Reinforcement Learning for LLMs in 2025
▶︎

Reinforcement Learning for LLMs in 2025

Yann LeCun's $1B Bet Against LLMs [Part 1]
▶︎

Yann LeCun's $1B Bet Against LLMs [Part 1]

QLoRA—How to Fine-tune an LLM on a Single GPU (w/ Python Code)
▶︎

QLoRA—How to Fine-tune an LLM on a Single GPU (w/ Python Code)

Fine-Tuning Local LLMs with Unsloth & Ollama
▶︎

Fine-Tuning Local LLMs with Unsloth & Ollama

Fine Tuning Large Language Models with InstructLab
▶︎

Fine Tuning Large Language Models with InstructLab

ASMR Best Triggers For Sleep Collection (No Talking) 3 Hours of Tapping & Scratching
▶︎

ASMR Best Triggers For Sleep Collection (No Talking) 3 Hours of Tapping & Scratching

263 DIOS TE DICE HOY： ESA ANGUSTIA QUE TE ROBA LA PAZ SERÁ CAMBIADA POR DESCANSO
▶︎

263 DIOS TE DICE HOY： ESA ANGUSTIA QUE TE ROBA LA PAZ SERÁ CAMBIADA POR DESCANSO

Fine-Tuning Text Embeddings For Domain-specific Search (w/ Python)
▶︎

Fine-Tuning Text Embeddings For Domain-specific Search (w/ Python)

How To Think SO CLEARLY People Assume You're A Genius
▶︎

How To Think SO CLEARLY People Assume You're A Genius

How to Fine-tune LLMs with Unsloth: Complete Guide
▶︎

How to Fine-tune LLMs with Unsloth: Complete Guide

How to finetune LLMs to THINK with Reinforcement Learning (GRPO from scratch!)
▶︎

How to finetune LLMs to THINK with Reinforcement Learning (GRPO from scratch!)

Fast Fine Tuning with Unsloth
▶︎

Fast Fine Tuning with Unsloth

How RAG, GraphRAG, and Context Engineering Improve AI Performance
▶︎

How RAG, GraphRAG, and Context Engineering Improve AI Performance

Knowledge Distillation: How LLMs train each other
▶︎

Knowledge Distillation: How LLMs train each other