The glossary
Every word you'll meet in AI and machine learning, explained in everyday language.
A fine-tuned model's weights minus its base model's: everything the fine-tuning changed, as one object you can scale, add or subtract.
Six tensors of the base model, before and after the fine-tune. "What changed" shows the delta itself. Its picture is busy everywhere: no row or column was left alone.
Edits are deltas: task vectors, patches and hashes · Subtract a base from a fine-tune and the edit becomes an object: scale it, take it away, ship it as a patch, and prove by hash what was applied. About 35 minutes.
1286 terms in the glossary, each with the lesson that teaches it.
Every word you'll meet in AI and machine learning, explained in everyday language.
Subtract a base from a fine-tune and the edit becomes an object: scale it, take it away, ship it as a patch, and prove by hash what was applied.
Never trained an AI? Teach a small one to write, right in your browser. It takes about 20 seconds and needs no account. Teach it to write