metaai·lightalo unofficial · independent
Universe / Language & LLMs / LLaMA
Language & LLMs · 2023

LLaMA

LLaMA (original)

The leak that started the open-weight revolution

open source superseded 7B / 13B / 33B / 65B params

Latest: LLaMA 65B (Feb 2023; superseded by Llama 2+)

FAIR's first large language model family (7B-65B), released Feb 24, 2023 to researchers under a non-commercial license. LLaMA-13B outperformed GPT-3 175B on many benchmarks, proving smaller models trained on more tokens could win — and kickstarting the open-weights era.

Why it matters

LLaMA proved a 13B model trained on more tokens could beat GPT-3's 175B, overturning 'bigger is better' scaling assumptions. When its weights leaked a week after release, it seeded llama.cpp and the entire local-LLM movement — the open-weight era that Meta then made official strategy with Llama 2.

Facts

Try it yourself

Lineage

Descends fromOPT-175B
Led toLlama 2

See the whole family tree →

Sources

More in Language & LLMs

Code LlamaLlama 3 / 3.1 / 3.2 / 3.3GalacticaLarge Concept ModelsByte Latent TransformerLlama Stack

Read the Language & LLMs story on the sky →

✦ Open on the map Explore Language & LLMs Quiz me