Generation config.
JSON representation |
---|
{ "stopSequences": [ string ], "responseMimeType": string, "temperature": number, "topP": number, "topK": number, "candidateCount": integer, "maxOutputTokens": integer, "presencePenalty": number, "frequencyPenalty": number } |
Fields | |
---|---|
stopSequences[] |
Optional. Stop sequences. |
responseMimeType |
Optional. Output response mimetype of the generated candidate text. Supported mimetype: - |
temperature |
Optional. Controls the randomness of predictions. |
topP |
Optional. If specified, nucleus sampling will be used. |
topK |
Optional. If specified, top-k sampling will be used. |
candidateCount |
Optional. Number of candidates to generate. |
maxOutputTokens |
Optional. The maximum number of output tokens to generate per message. |
presencePenalty |
Optional. Positive penalties. |
frequencyPenalty |
Optional. Frequency penalties. |