metaai·lightalo unofficial · independent
Universe / Language & LLMs / Large Concept Models
Language & LLMs · 2024

Large Concept Models

Large Concept Models (LCM)

An AI that predicts the next idea, not the next word

open source 1.6B / 7B params

Latest: LCM 1.6B/7B research release (Dec 2024)

FAIR's bet that the token is the wrong unit of thought: LCMs predict the next sentence-level 'concept' in SONAR embedding space — a language- and modality-agnostic representation covering 200 languages — rather than the next word. Showed strong zero-shot cross-lingual generalization on summarization; training code open-sourced.

Why it matters

LCM challenges the token as the unit of language modeling: it predicts the next sentence-level concept in SONAR's language- and modality-agnostic embedding space covering 200 languages, so one model reasons once and surfaces it in any language. It is FAIR's most explicit architectural bet against the dense next-token transformer.

Facts

Try it yourself

Sources

More in Language & LLMs

Llama 3 / 3.1 / 3.2 / 3.3Byte Latent TransformerLlama StackCoconutMulti-token predictionMemory Layers at Scale

Read the Language & LLMs story on the sky →

✦ Open on the map Explore Language & LLMs Quiz me