Why You (Probably) Don’t Need to Fine-Tune an LLM - Nick the Sick's blog. Writings, projects and ideas.

# Why You (Probably) Don’t Need to Fine-Tune an LLM - Jessica Yao Synced: [[2023_11_30]] 6:03 AM Last Highlighted: [[2023_08_19]] Tags: [[AI]] [[Software]] ![rw-book-cover](https://www.tidepool.so/wp-content/uploads/2023/08/robot_with_box-1024x574.png) ## Highlights [[2023_08_19]] [View Highlight](https://read.readwise.io/read/01h85x9cnwhsfhys20zhwn7ag8) > you can consider a base LLM model to be like a Swiss army knife — it is sufficient and adaptable to most use cases. > Given the upfront time and computational resources required for fine-tuning, we’d recommend starting with this base first (along with the supplemental techniques mentioned) and seeing how far you get with it!