Values.PromptModelInferenceConfigurationSourceContains inference configurations related to model inference for a prompt. For more information, see Inference parameters.
type nonrec t = {temperature : Temperature.t option;Controls the randomness of the response. Choose a lower value for more predictable outputs and a higher value for more surprising outputs.
*)topP : TopP.t option;The percentage of most-likely candidates that the model considers for the next token.
*)maxTokens : MaximumLength.t option;The maximum number of tokens to return in the response.
*)stopSequences : StopSequences.t option;A list of strings that define sequences after which the model will stop generating.
*)}val to_value :
t ->
[> `Structure of
(string
* [> `Float of Temperature.t
| `Integer of MaximumLength.t
| `List of [> `String of String_.t ] list ])
list ]