Glossary · Phase 6 · Modern LLM engineering
Post-training
Everything done to a model after pretraining to turn a text predictor into an assistant: fine-tuning on example chats, preference training and safety work.
Learn it properly
Base models vs assistants · What post-training adds to a pretrained model. About 30 minutes.
Other terms from the same lesson
- chat template: The fixed format, with special tokens, that marks who is speaking in a conversation, so a chat model knows where your message ends and its reply starts.