Fine-tuning
Fine-tuning a large language model (LLM) involves taking a pre-trained model, which has
already been trained on a vast amount of general language data, and further training it
on a specific dataset or task.
Hyperparameters
Hyperparameters in LLM fine-tuning are settings or configurations that control the
training process of the model but are not learned from the data. They are predefined
values that you choose before starting the fine-tuning process.
Model deployment
Some fine-tuned models require a deployment to be usable.
- If you choose to deploy the fine-tuned model in the recipe, your model will be directly usable once the job is complete.
- You can also choose to delete inactive saved model versions. In that case, your current deployments attached to saved model versions will be deleted. Your current active version deployment if any won't be deleted if your saved model activation method is manual.