FineTuneChatRequestInput
objectThe per-line training example of a fine-tuning input file for chat models using the supervised method.
One Of>= 1 items
Developer-provided instructions that the model should follow, regardless of
messages sent by the user. With o1 models and newer, use developer messages
for this purpose instead.
Show Child Parameters
A list of tools the model may generate JSON inputs for.
Show Child Parameters
A list of functions the model may generate JSON inputs for.
>= 1 items<= 128 items
Show Child Parameters
FineTuneCompletionRequestInput
objectThe per-line training example of a fine-tuning input file for completions models
The input prompt for this training example.
The desired completion for this training example.
FineTuneDPOMethod
objectConfiguration for the DPO fine-tuning method.
The hyperparameters used for the fine-tuning job.
Show Child Parameters
FineTuneMethod
objectThe method used for fine-tuning.
The type of method. Is either supervised or dpo.
Allowed values:superviseddpo
Configuration for the supervised fine-tuning method.
Show Child Parameters
Configuration for the DPO fine-tuning method.
Show Child Parameters
FineTunePreferenceRequestInput
objectThe per-line training example of a fine-tuning input file for chat models using the dpo method.
Show Child Parameters
One OfThe preferred completion message for the output.
<= 1 items
Messages sent by the model in response to user messages.
Show Child Parameters
One OfThe non-preferred completion message for the output.
<= 1 items
Messages sent by the model in response to user messages.