OpenAI | Fine-Tuning

Manage fine-tuning jobs to tailor a model to your specific training data. Fine-tuning lets you get more out of the models by providing higher quality results, the ability to train on more examples, and cost savings.

Simple Example

Create a fine-tuning job and list existing jobs.

OpenAI := TsgcHTTP_API_OpenAI.Create(nil);
OpenAI.OpenAIOptions.ApiKey := 'API_KEY';

// Create a fine-tuning job
WriteLn(OpenAI._CreateFineTuningJob('gpt-4o-mini-2024-07-18', 'file-abc123'));

// List fine-tuning jobs
WriteLn(OpenAI._ListFineTuningJobs());

Methods

• CreateFineTuningJob: Creates a fine-tuning job which begins the process of creating a new model from a given dataset.
  • Model: The name of the model to fine-tune.
  • TrainingFile: The ID of an uploaded file that contains training data.
• ListFineTuningJobs: List your organization's fine-tuning jobs.
• RetrieveFineTuningJob: Get info about a fine-tuning job.
  • JobId: The ID of the fine-tuning job.
• CancelFineTuningJob: Immediately cancel a fine-tuning job.
  • JobId: The ID of the fine-tuning job to cancel.
• ListFineTuningJobEvents: Get status updates for a fine-tuning job.
  • JobId: The ID of the fine-tuning job.
• ListFineTuningJobCheckpoints: List checkpoints for a fine-tuning job.
  • JobId: The ID of the fine-tuning job.