How LLMs Are Created — Pre-training, Post-training, and RL
· 32 min read#llms#pre-training#post-training
How LLMs are built: from internet-scale pre-training through SFT, RLHF, DPO, GRPO, and Constitutional AI.
1 article
How LLMs are built: from internet-scale pre-training through SFT, RLHF, DPO, GRPO, and Constitutional AI.