TRANSFORMERS & LLMs • 43 / 397
Follow text from characters to tokens, attention, transformers and generation.

Embedding Dimension

Embedding dimension is the number of numeric components in an embedding vector.

Think of it like

Think of Embedding Dimension as part of a very fast reader that repeatedly decides what information matters and what should come next.

Real life

Autocomplete, translation and chat assistants depend on concepts such as Embedding Dimension.

SRE lens

Higher dimensions use more storage and compute in a vector database.

Remember thisEmbedding dimension is the number of numeric components in an embedding vector.
AIForSREJump to a concept
Search is optional. The main journey is simply ↓ Next.