Class AfterTokenSamplingEventArgs
- Namespace
- LMKit.TextGeneration.Events
- Assembly
- LM-Kit.NET.dll
Provides details for the event that occurs after a token sampling operation.
public sealed class AfterTokenSamplingEventArgs : EventArgs- Inheritance
-
AfterTokenSamplingEventArgs
- Inherited Members
Properties
- KeepLast
Gets or sets a value indicating whether the last generated token should be included in the response when the text completion process is terminated prematurely. This property is relevant only if Stop is set to
true. The default value isfalse.
- Model
Gets the language model (LLM) instance associated with this event.
- Perplexity
Gets the perplexity of the model's predictions up to this point. Lower perplexity indicates better predictive performance.
- Stop
Gets or sets a value indicating whether the text completion process should be terminated prematurely. The default value is
false.
- TextChunk
Gets the text representation of the currently selected token.
- Token
Gets or sets the identifier of the selected token for text completion. Initially determined by the sampling engine, but can be adjusted if necessary.
- TokenProbability
Gets the probability of the selected token, ranging from 0 to 1. A higher value indicates a higher likelihood.
Methods
- GetTokenCandidateByRank(int)
Retrieves the identifier of a token based on its rank in terms of likelihood of occurrence.
- GetTokenCandidateProbability(int)
Retrieves the probability of occurrence for a given token. This method evaluates the likelihood of a specific token being the next in the sequence, based on the model's current predictions.
- GetTokenCandidateProbabilityByRank(int)
Retrieves the probability of a token based on its rank in terms of likelihood of occurrence.
- GetTokenCandidateTextChunkByRank(int)
Retrieves the text representation of a token based on its rank in terms of likelihood of occurrence.