llama

2 lessons tagged llama: free, quiz-checked micro-lessons.

LLM Post-Training: SFT, RLHF, DPO, and Modern Alignment Recipes

A deep dive into how raw pretrained language models become helpful assistants — from supervised fine-tuning on curated demonstrations, through reward modeling and PPO-based RLHF, to modern direct alignment methods like DPO and the recipes used in Llama 3, Llama 4, and DeepSeek.

12 steps·~18 min

intermediate

Modern LLM Architectures: From Decoder-Only to Mixture-of-Experts

A deep tour of the architectural choices powering today's large language models — decoder-only Transformers, encoder-decoder designs, grouped-query attention, RoPE positional embeddings, and mixture-of-experts routing — with concrete numbers and trade-offs.

12 steps·~18 min

LLM Post-Training: SFT, RLHF, DPO, and Modern Alignment Recipes

Modern LLM Architectures: From Decoder-Only to Mixture-of-Experts

Related topics