Three trips into Hugging Face, and what came back

For a while my site only knew the closed half of machine learning: hosted APIs, keys, invoices. Three trips into Hugging Face changed that. Live field notes as I went, a search engine running in the browser instead of on someone's server, and an open model that tied the paid incumbent on a benchmark. The open half turns out to be closer than the pricing pages suggest.

The site had never touched the open half of machine learning. So I made three trips into Hugging Face and wrote down what came back.

The one that stuck: an open model tied the paid incumbent on a benchmark I ran myself. https://www.jakelawrence.xyz/blog/three-trips-into-hugging-face

My site had only ever spoken to the closed half of machine learning: hosted APIs, a key, a bill at the end of the month. Three trips into Hugging Face fixed that. Field notes written live, a search engine that runs in your browser, and an open model that tied the paid incumbent on a benchmark I ran myself.

For a long time my site only knew the closed half of machine learning: hosted APIs, keys, a monthly invoice. Three shipped expeditions into Hugging Face changed that. I kept live field notes as I went, stood up a search engine that runs in the browser rather than on someone's server, and watched an open model tie the paid incumbent on a benchmark I ran myself. The open half is a lot closer than the pricing pages let on. https://www.jakelawrence.xyz/blog/three-trips-into-hugging-face

An open model tied the paid incumbent on a benchmark I ran myself. That was one of three trips into Hugging Face I made to give my site its first taste of the open half of machine learning.

Field notes from all three: https://www.jakelawrence.xyz/blog/three-trips-into-hugging-face

A search engine that runs in your browser instead of on someone's server. That was one of three shipped trips into Hugging Face, my site's first contact with the open half of machine learning.

https://www.jakelawrence.xyz/blog/three-trips-into-hugging-face