Find out when tuning a model can help you use a foundation model to achieve your goals.
Tune a foundation model when you want to do the following things:
-
Reduce the cost of inferencing at scale
Larger foundation models typically generate better results. However, they are also more expensive to use. By tuning a model, you can get similar, sometimes even better results from a smaller model that costs less to use.
-
Get the model's output to use a certain style or format
-
Improve the model's performance by teaching the model a specialized task
-
Generate output in a reliable form in response to zero-shot prompts
When not to tune a model
Tuning a model is not always the right approach for improving the output of a model. For example, tuning a model cannot help you do the following things:
-
Improve the accuracy of answers in model output
If you're using a foundation model for factual recall in a question-answering scenario, tuning will marginally improve answer accuracy. To get factual answers, you must provide factual information as part of your input to the model. Tuning can be used to help the generated factual answers conform to a format that can be more-easily used by a downstream process in a workflow. To learn about methods for returning factual answers, see Retreival-augmented generation.
-
Get the model to use a specific vocabulary in its output consistently
Large language models that are trained on large amounts of data formulate a vocabulary based on that initial set of data. You can introduce significant terms to the model from training data that you use to tune the model. However, the model might not use these preferred terms reliably in its output.
-
Teach a foundation model to perform an entirely new task
Experimenting with prompt engineering is an important first step because it helps you understand the type of output that a foundation model is and is not capable of generating. You can use tuning to tweak, tailor, and shape the output that a foundation model is able to return.
Learn more
Parent topic: Tuning Studio