From the course: Fine-Tune Your LLMs
Join today to access over 25,000 courses taught by industry experts.
Understand the costs of fine-tuning
From the course: Fine-Tune Your LLMs
Understand the costs of fine-tuning
- [Instructor] Gain confidence in your budget when you understand how to estimate fine tuning costs. You can save on costs when you fine tune a model. If you're familiar with pricing on the OpenAI API, you know you're charged based on tokens, the number of tokens sent to the model and returned from the model. For example, any prompt you send to a model is broken down into tokens. Tokens are parts of the words in your prompt. For example, in the sentence, "How many tokens are in this sentence?" there are eight tokens and 37 characters. You'll save on costs because fine tuning allows you to write shorter prompts, which reduces the number of tokens you need to send to the model. Once a model is fine tuned, you don't need to provide as many examples in the prompt. This saves costs and enables lower latency requests. Knowing how many tokens you're sending to the model is important. This will first tell you how much an OpenAI API call costs, and you'll also know whether the prompt is too…
Download courses and learn on the go
Watch courses on your mobile device without an internet connection. Download courses using your iOS or Android LinkedIn Learning app.