AI engineering glossary · Transformers LLM architecture
What is min-p sampling?
Min-p sampling: A sampling method that keeps tokens whose probability is at least a fraction of the most likely token's probability, so the cut-off scales with how confident the model is. It aims to stay coherent even at higher temperatures.
Min-p sampling: an example
If the top token has probability 0.5 and min-p is 0.1, tokens below 0.05 are removed.
Related terms
More Transformers LLM architecture terms
- Mixtral
- Mixture of depths
- Mixture of experts
- Model dimension
- Multi-head attention
- Multi-head latent attention
- Multi-query attention
- Multi-token prediction
Where you learn it
Min-p sampling is part of the AI Engineering Program, which teaches it with notes, a hands-on lab and an exam. The first lesson is free.