LLaMA

E435872

large language model family

LLaMA is a family of large language models developed by Meta AI, designed for efficient training and inference across a range of natural language processing tasks.

Try in SPARQL Jump to: Surface forms Disambiguation Statements Elicitation Referenced by

All labels observed (21)

Label	Occurrences
LLaMA 2	2
LLaMA 3	2
Llama 3	2
Falcon-7B	1
LLaMA canonical	1
Llama 1	1
Llama 2	1
Llama 2 13B	1
Llama 2 70B	1
Llama 2 7B	1
Llama 3 70B	1
Llama 3 8B	1
Llama 3.1	1
Llama 3.1 405B	1
Llama 3.1 70B	1
Llama 3.1 8B	1
Llama 3.2	1
Llama 3.2 11B	1
Llama 3.2 1B	1
Llama 3.2 3B	1
Llama 3.2 90B	1

How this entity was disambiguated

This entity first appeared as the object of triple T4389199 — resolving that mention is where its identity was fixed. The disambiguator weighed these candidate entities and picked the highlighted one (or “None”, minting a new entity). This is how homonymy is resolved: the same surface form can point to different entities.

NED1 Entity disambiguation (via context triple) gpt-5-mini-2025-08-07

Target entity: LLaMA
Context triple: [Hugging Face Transformers, supportsModelType, LLaMA]

A. LLM
LLM is the ICAO airline designator assigned to Yamal Airlines, a Russian regional carrier.
B. GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
C. GPT-2
GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
D. Hugging Face Transformers
Hugging Face Transformers is a widely used open-source library that provides state-of-the-art transformer-based models and tools for natural language processing and related machine learning tasks.
E. DALL·E
DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
F. None of above. chosen
G. Unsure - the case is ambiguous/there is not enough information to decide.

NED2 Entity disambiguation (via description) gpt-5-mini-2025-08-07

Target entity: LLaMA
Target entity description: LLaMA is a family of large language models developed by Meta AI, designed for efficient training and inference across a range of natural language processing tasks.

A. LLM
LLM is the ICAO airline designator assigned to Yamal Airlines, a Russian regional carrier.
B. GPT-3
GPT-3 is a large-scale autoregressive language model known for generating human-like text and performing a wide range of natural language tasks with minimal fine-tuning.
C. GPT-2
GPT-2 is a large transformer-based language model known for generating coherent, human-like text and sparking widespread discussion about the implications of advanced AI text generation.
D. Hugging Face Transformers
Hugging Face Transformers is a widely used open-source library that provides state-of-the-art transformer-based models and tools for natural language processing and related machine learning tasks.
E. DALL·E
DALL·E is an AI model developed by OpenAI that generates images from natural language descriptions, enabling text-to-image synthesis.
F. None of above. chosen

Statements (47)

Predicate	Object
instanceOf	large language model family ⓘ
abbreviationOf	Large Language Model Meta AI ⓘ linked to: LLM
architectureType	decoder-only transformer ⓘ
basedOn	transformer architecture ⓘ
computingParadigm	deep learning ⓘ
developer	Meta AI ⓘ Meta Platforms ⓘ linked to: Meta Platforms, Inc.
domain	artificial intelligence ⓘ
field	natural language processing ⓘ
hasSuccessor	LLaMA 2 ⓘ linked to: LLaMA LLaMA 3 ⓘ linked to: LLaMA
inspired	LLaMA 2 ⓘ linked to: LLaMA LLaMA 3 ⓘ linked to: LLaMA
language	English ⓘ multilingual text ⓘ
license	research license (original release) ⓘ
notableFor	open research access compared to many contemporaries ⓘ strong performance at smaller parameter scales ⓘ
optimizationGoal	efficient inference ⓘ efficient training ⓘ
organization	Meta AI FAIR (Fundamental AI Research) ⓘ linked to: Meta AI
parameterCountVariant	13B ⓘ 33B ⓘ 65B ⓘ 7B ⓘ
relatedTo	GPT family ⓘ linked to: GPT Mistral ⓘ PaLM ⓘ linked to: PaLM 2
releaseDate	2023-02 ⓘ
supports	few-shot learning ⓘ fine-tuning ⓘ instruction tuning ⓘ prompt-based conditioning ⓘ zero-shot learning ⓘ
task	code generation ⓘ question answering ⓘ summarization ⓘ text completion ⓘ text generation ⓘ translation ⓘ
trainingDataType	Wikipedia ⓘ books ⓘ code ⓘ public web data ⓘ
trainingObjective	causal language modeling ⓘ
uses	downstream NLP applications ⓘ research in large language models ⓘ

How these facts were elicited

Referenced by (24)

Full triples — surface form annotated when it differs from this entity's canonical label.

Hugging Face Transformers → supportsModelType → LLaMA ⓘ

Meta AI assistant → usesModelFamily → Llama 3 ⓘ

linked to: LLaMA

LLaMA → inspired → LLaMA 2 ⓘ

linked to: LLaMA

LLaMA → inspired → LLaMA 3 ⓘ

linked to: LLaMA

LLaMA → hasSuccessor → LLaMA 2 ⓘ

linked to: LLaMA

LLaMA → hasSuccessor → LLaMA 3 ⓘ

linked to: LLaMA

Falcon → hasVersion → Falcon-7B ⓘ

linked to: LLaMA

Llama → hasVersion → Llama 1 ⓘ

linked to: LLaMA

Llama → hasVersion → Llama 2 ⓘ

linked to: LLaMA

Llama → hasVersion → Llama 3 ⓘ

linked to: LLaMA

Llama → hasVersion → Llama 3.1 ⓘ

linked to: LLaMA

Llama → hasVersion → Llama 3.2 ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 2 7B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 2 13B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 2 70B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3 8B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3 70B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.1 8B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.1 70B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.1 405B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.2 1B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.2 3B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.2 11B ⓘ

linked to: LLaMA

Llama → hasSubModel → Llama 3.2 90B ⓘ

linked to: LLaMA

All labels observed (21)

How this entity was disambiguated Show

Statements (47)

How these facts were elicited Show

Referenced by (24)

How this entity was disambiguated

How these facts were elicited