Class Logprobs
Includes the logarithmic probabilities for the most likely output tokens and the chosen tokens.
For example, if the log probability is 5, the API returns a list of the 5 most likely tokens. The API returns the log probability of the sampled token, so there might be up to logprobs+1 elements in the response.
Inherited Members
Namespace: Oci.GenerativeaiinferenceService.Models
Assembly: OCI.DotNetSDK.Generativeaiinference.dll
Syntax
public class Logprobs
Properties
TextOffset
Declaration
[JsonProperty(PropertyName = "textOffset")]
public List<int> TextOffset { get; set; }
Property Value
Type | Description |
---|---|
List<int> | The text offset. |
TokenLogprobs
Declaration
[JsonProperty(PropertyName = "tokenLogprobs")]
public List<double> TokenLogprobs { get; set; }
Property Value
Type | Description |
---|---|
List<double> | The logarithmic probabilites of the output token. |
Tokens
Declaration
[JsonProperty(PropertyName = "tokens")]
public List<string> Tokens { get; set; }
Property Value
Type | Description |
---|---|
List<string> | The list of output tokens. |
TopLogprobs
Declaration
[JsonProperty(PropertyName = "topLogprobs")]
public List<Dictionary<string, string>> TopLogprobs { get; set; }
Property Value
Type | Description |
---|---|
List<Dictionary<string, string>> | The logarithmic probabilities of each of the top k tokens. |