Tale
Artificial Intelligence
How GPT works: A Metaphoric Explanation of Key, Value, Query in Attention, using a Tale of Potion
Side note: the language “decoder” is a vestige from the unique paper, as Transformer was first used for machine translation tasks. You “encode” the source language into embeddings, and “decode” from the embeddings to...
Artificial Intelligence
How GPT works: A Metaphoric Explanation of Key, Value, Query in Attention, using a Tale of Potion
Side note: the language “decoder” is a vestige from the unique paper, as Transformer was first used for machine translation tasks. You “encode” the source language into embeddings, and “decode” from the embeddings to...
Recent posts
