class

OpenAI::FineTunePreferenceRequestInput

Inherits JSON::Serializable < Reference < Object

The per-line training example of a fine-tuning input file for chat models using the dpo method. Input messages may contain text or image content only. Audio and file input messages are not currently supported for fine-tuning.

Constructors

new(pull : JSON::PullParser)
Source
new(input : FineTunePreferenceRequestInputInput | Nil = nil, preferred_output : Array(FineTunePreferenceRequestInputPreferredOutputItem) | Nil = nil, non_preferred_output : Array(FineTunePreferenceRequestInputNonPreferredOutputItem) | Nil = nil)
Source
new(*, __pull_for_json_serializable pull : JSON::PullParser)
Source

Instance methods

input
Source
input=(input : FineTunePreferenceRequestInputInput | Nil)
Source
non_preferred_output

The non-preferred completion message for the output.

Source
non_preferred_output=(non_preferred_output : Array(FineTunePreferenceRequestInputNonPreferredOutputItem) | Nil)

The non-preferred completion message for the output.

Source
preferred_output

The preferred completion message for the output.

Source
preferred_output=(preferred_output : Array(FineTunePreferenceRequestInputPreferredOutputItem) | Nil)

The preferred completion message for the output.

Source