Fine-tuning
Fine-tune a model to write in a style
Basics
Fine-tuning will create an AI model that matches a writing style. The fine-tuning endpoint requires listing one or more files to use to train the AI. You can use as many files as you want.
For best results:
- Use files with a consistent style
- Use files of the same type that you want to style, e.g. fine-tuning on product guides will create a model that works best on product guides
The model is the model to fine-tune. 70B models perform better than 8B models, though they take longer to train and style and are more costly.
base_model is the base AI whose output you want to style (for example, you may want to style outputs from gpt4-o or from Claude Sonnet).
The num_examples is the number of examples used to fine-tune the model. More examples provides more learning. 200 examples is a reasonable default to balance quality and cost.
The response will include a fine-tuned model ID, which you will use to identify the model for inference.
Fine-tuning can sometimes complete in minutes, but may take up to 24 hours based on load. The status of the job will change from ‘queued’ to ‘completed’ when finished.