Supervised Fine-tuning
Concept
A post-training method focused on improving a model's behavior, such as generating aesthetically pleasing images or better following text instructions.
Mentioned in 2 videos
Save the 2 videos on Supervised Fine-tuning to your own pod.
Sign up free to keep building your knowledge base on Supervised Fine-tuning as more episodes are added.
Videos Mentioning Supervised Fine-tuning
Stanford CME295 Transformers & LLMs | Autumn 2026 | Lecture 4 - Reinforcement Learning with LLMs
Stanford Online
A training step where a pre-trained LLM is adjusted to be useful, for example, to provide answers to questions, still using cross-entropy loss but focusing on output tokens.
Stanford CME296 Diffusion & Large Vision Models | Spring 2026 | Lecture 6 - Model Training
Stanford Online
A post-training method focused on improving a model's behavior, such as generating aesthetically pleasing images or better following text instructions.