Skip to main content


FineTune allows you to customize models by tuning them using your data and enhancing their performance. Set up and start fine-tuning with a few lines of code. Once fine-tuning is complete, the model will be deployed into your assets and ready for use.

This feature relies on two fundamental components:

  • Models - In fine-tuning, we start with a pre-trained machine-learning model previously trained on extensive general data. Fine-tuning adjusts this model's parameters to another dataset, refining its abilities for our particular application, resulting in more accurate predictions or classifications.

  • Data - Data is the core of fine-tuning. It's a specific dataset for the task you want the ML model to specialize in, often including labelled examples. Data quality, quantity, and diversity are crucial for success. It gives the model real-world insights, helping it adapt and specialize for the task or domain.


We currently support the following tasks: text-generation, translation, and search.