Decoding and inference behavior · MLD-0735
Min-p sampling
Filtering tokens by a probability threshold relative to the most probable token, then sampling.
Original reference page · detailed expansion pending. Original definitions, examples, notes and citations are preserved below. New examples are illustrative, not benchmark results.
Original example
Exclude very unlikely continuations adaptively.
Original caveat
Exact filtering conventions can vary by implementation.
Context and aliases
Level: Intermediate. Stages: Inference · Evaluation · Deployment.
Tags: SLM · LLM · NLP.
Aliases: None recorded.
Related concepts
Original references
- Hugging Face: generation strategies ↗ · Reference link
- Fast Inference from Transformers via Speculative Decoding ↗ · Consulted
- vLLM documentation ↗ · Consulted
- Original reference URL ↗