Editing LLaMA

{{Distinguish|LLaMA 2}}
{{Infobox model
|title=LLaMA
|date=2023-02-24
|base_model=Base Model
|made_by=[[Meta AI]]
|sizes=7b, 13b, 33b, 65b
|announcement=[[https://arxiv.org/abs/2302.13971]]
|huggingface=[[https://huggingface.co/docs/transformers/main/model_doc/llama]]
|}}
'''LLaMA''' ('''Large Language Model Meta AI''') is a foundational [[large language model]] (LLM) released by [[Meta AI]] in February 2023. It was originally designed primarily for use by researchers. 

Four model sizes were trained: 7, 13, 33 and 65 billion parameters. LLaMA's developers reported that the 13B parameter model's performance on most [[natural language processing|NLP]] benchmarks exceeded that of the much larger [[GPT-3]] (with 175B parameters) and that the largest model was competitive with state of the art models. 

LLaMA was significant at the time of its release for the fact that its model weights were released to the research community under a noncommercial license, rather than being controlled behind an API. Within a week of LLaMA's release, its weights were leaked to the public on [[Wikipedia:4chan|4chan]] via [[Wikipedia:BitTorrent|BitTorrent]].

== Language Support ==
LLaMA primarily supports English.  It should have limited capabilities in a range of other languages including: bg, ca, cs, da, de, es, fr, hr, hu, it, nl, pl, pt, ro, ru, sl, sr, sv, uk.

== Derivative and Related Models ==
Due to general availability of its weights, LLaMA was the basis for a large number of significant derivative models - including:
*[[Alpaca]]
*[[Dolphin]]
*[[Guanaco]]
*[[Orca]]
*[[Vicuna]]

A project is underway to replicate the LLaMA model in a pure [[Open Source]] way, see [[OpenLLaMA]].
== License ==
The LLaMA license restricts its usage to research and prohibits commercial use.  For models distributed on more permissive terms see [[LLaMA 2]] and [[OpenLLaMA]].

== See Also ==
*[[wikipedia:LLaMA|LLaMA model]] on Wikipedia

[[Category:Models]]