GRANDMASTER

Training & Alignment

Pre-training from scratch, tokenizers, datasets, and the RLHF → DPO → GRPO alignment pipeline. Part of the free Open Source AI Academy — every lesson below is open to everyone, no signup required.

2 lessons300 XP~24 min total100% free

// LESSONS IN THIS MODULE

  1. 01Pre-Training & Tokenization12 min · 150 XP

    Training an LLM From Scratch Pre-training requires three components: a tokenizer , a dataset , and massive compute . Tokenizer Selection Algorithm Lib...

  2. 02The Alignment Stack: RLHF → DPO → GRPO12 min · 150 XP

    Modern Post-Training Pipeline Raw pre-trained models are "completion engines" — they continue text, not follow instructions. Alignment transforms them...

Explore the full Open Source AI Academy
Training & Alignment — Open Source AI Academy Module | Free Lessons