GoodMem
ReferenceClient SDKs.NET SDKModels

LLMSamplingParams Model

LLMSamplingParams Model documentation for .NET SDK

Sampling and generation parameters for controlling LLM text output

Properties

NameTypeDescriptionNotes
MaxTokensint?Maximum tokens to generate (>0 if set; provider-dependent limits apply)[optional]
Temperaturefloat?Sampling temperature 0.0-2.0 (0.0=deterministic, 2.0=highly random)[optional]
TopPfloat?Nucleus sampling threshold 0.0-1.0 (smaller values focus on higher probability tokens)[optional]
TopKint?Top-k sampling limit (>0 if set; primarily for local/open-source models)[optional]
FrequencyPenaltyfloat?Frequency penalty -2.0 to 2.0 (positive values reduce repetition based on frequency)[optional]
PresencePenaltyfloat?Presence penalty -2.0 to 2.0 (positive values encourage topic diversity)[optional]
StopSequencesList<string>Generation stop sequences (≤10 sequences; each ≤100 chars; generation halts on exact match)[optional]

↑ Back to .NET SDK ↑ Back to .NET SDK ↑ Back to .NET SDK

On this page