News
ReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior ReleaseReleasesOVHcloud unveils Olala mini, its first in-house LLMChinaA 9B model beats a 1T model on FinQA, trained with Crusoe Managed RLReleasesThe internal metaphysics of an LLMReleasesMapping Language Model Internal Representations to Physical Laws and Scientific ReasoningResearchCan China keep rogue AI in check? Meet the start-up testing the top modelsFrontierMicrosoft aims to challenge OpenAI, Anthropic with cheaper, specialized AI modelsOpen modelsMicrosoft rolls out new first-party models and updates to agentic AI continuous improvementFrontierMicrosoft unveils AI models for coding, cybersecurity as it takes on Anthropic, OpenAIFrontierGoogle is making it easier to opt out of Gemini AI model training – here’s howFrontierOpenAI Unveils New Astra AI Model After Scrapping Prior Release
EveryLLM

Embedding

A list of numbers that stands for a token, word or passage, placed so that similar meanings sit close together.

A diagram drawn by EveryLLM.

Also: vector embedding, word vector

Inside a model, each token is first turned into an embedding: a vector of hundreds or thousands of numbers. During training these vectors are adjusted so that tokens used in similar ways end up near each other, which is why "king" and "queen" are closer than "king" and "carrot". Whole sentences and documents can be embedded too, by dedicated embedding models. Those passage embeddings power semantic search and retrieval-augmented generation, where a question is matched to the passages whose vectors point in nearly the same direction.

See also

Find models that mention Embedding

The weekly digest

Every Monday: the model of the day, new pages on EveryLLM, and the conferences and anniversaries of the week ahead.