Logprobs Result
The log probabilities of the tokens generated by the model. This is useful for understanding the model's confidence in its predictions and for debugging. For example, you can use log probabilities to identify when the model is making a less confident prediction or to explore alternative responses that the model considered. A low log probability can also indicate that the model is "hallucinating" or generating factually incorrect information.
Properties
Functions
Link copied to clipboard
Instantiates a builder for LogprobsResult.
Link copied to clipboard
A list of the chosen candidate tokens at each decoding step.
Link copied to clipboard
Deserializes a JSON string to a LogprobsResult object.
Link copied to clipboard
@InternalApi()
Deserializes a JsonNode to an object of the given type.
Link copied to clipboard
@InternalApi()
Deserializes a Json string to an object of the given type.
Link copied to clipboard
Sum of log probabilities for all tokens.
Link copied to clipboard
Link copied to clipboard
Overrides the default maximum JSON string length (20MB) for the JSON parser.
Link copied to clipboard
Converts a Json string to a JsonNode.
Link copied to clipboard
Creates a builder with the same values as this instance.
Link copied to clipboard
Serializes an object to a JsonNode.
Link copied to clipboard
Serializes an object to a Json string.
Link copied to clipboard
A list of the top candidate tokens at each decoding step.