Skip to content
AI-LinkMO

Class: LargeLanguageModel

A large language model (LLM) is an AI model which supports a range of language-related tasks such as generation, summarization, classification, among others. A LLM is implemented as an artificial neural networks using a transformer architecture.

URI: nexus:LargeLanguageModel

 classDiagram
    class LargeLanguageModel
    click LargeLanguageModel href "../LargeLanguageModel/"
      AiModel <|-- LargeLanguageModel
        click AiModel href "../AiModel/"
      

      LargeLanguageModel <|-- Adapter
        click Adapter href "../Adapter/"
      

      LargeLanguageModel : architecture
        
      LargeLanguageModel : broad_mappings
        
          
    
        
        
        LargeLanguageModel --> "*" Any : broad_mappings
        click Any href "../Any/"
    

        
      LargeLanguageModel : carbon_emitted
        
      LargeLanguageModel : close_mappings
        
          
    
        
        
        LargeLanguageModel --> "*" Any : close_mappings
        click Any href "../Any/"
    

        
      LargeLanguageModel : contextWindowSize
        
      LargeLanguageModel : dateCreated
        
      LargeLanguageModel : dateModified
        
      LargeLanguageModel : description
        
      LargeLanguageModel : exact_mappings
        
          
    
        
        
        LargeLanguageModel --> "*" Any : exact_mappings
        click Any href "../Any/"
    

        
      LargeLanguageModel : fine_tuning
        
      LargeLanguageModel : gpu_hours
        
      LargeLanguageModel : hasDocumentation
        
          
    
        
        
        LargeLanguageModel --> "*" Documentation : hasDocumentation
        click Documentation href "../Documentation/"
    

        
      LargeLanguageModel : hasEvaluation
        
          
    
        
        
        LargeLanguageModel --> "*" AiEvalResult : hasEvaluation
        click AiEvalResult href "../AiEvalResult/"
    

        
      LargeLanguageModel : hasInputModality
        
          
    
        
        
        LargeLanguageModel --> "*" Modality : hasInputModality
        click Modality href "../Modality/"
    

        
      LargeLanguageModel : hasLicense
        
          
    
        
        
        LargeLanguageModel --> "0..1" License : hasLicense
        click License href "../License/"
    

        
      LargeLanguageModel : hasLifecycleStatus
        
          
    
        
        
        LargeLanguageModel --> "0..1" LifecycleStatus : hasLifecycleStatus
        click LifecycleStatus href "../LifecycleStatus/"
    

        
      LargeLanguageModel : hasModelCard
        
      LargeLanguageModel : hasOutputModality
        
          
    
        
        
        LargeLanguageModel --> "*" Modality : hasOutputModality
        click Modality href "../Modality/"
    

        
      LargeLanguageModel : hasRiskControl
        
          
    
        
        
        LargeLanguageModel --> "*" RiskControl : hasRiskControl
        click RiskControl href "../RiskControl/"
    

        
      LargeLanguageModel : hasTrainingData
        
          
    
        
        
        LargeLanguageModel --> "*" Dataset : hasTrainingData
        click Dataset href "../Dataset/"
    

        
      LargeLanguageModel : id
        
      LargeLanguageModel : isCategorizedAs
        
          
    
        
        
        LargeLanguageModel --> "*" Any : isCategorizedAs
        click Any href "../Any/"
    

        
      LargeLanguageModel : isPartOf
        
          
    
        
        
        LargeLanguageModel --> "0..1" LargeLanguageModelFamily : isPartOf
        click LargeLanguageModelFamily href "../LargeLanguageModelFamily/"
    

        
      LargeLanguageModel : isProducedBy
        
          
    
        
        
        LargeLanguageModel --> "0..1" Organization : isProducedBy
        click Organization href "../Organization/"
    

        
      LargeLanguageModel : isProvidedBy
        
          
    
        
        
        LargeLanguageModel --> "0..1" Organization : isProvidedBy
        click Organization href "../Organization/"
    

        
      LargeLanguageModel : name
        
      LargeLanguageModel : narrow_mappings
        
          
    
        
        
        LargeLanguageModel --> "*" Any : narrow_mappings
        click Any href "../Any/"
    

        
      LargeLanguageModel : notes
        
      LargeLanguageModel : numParameters
        
      LargeLanguageModel : numTrainingTokens
        
      LargeLanguageModel : performsTask
        
          
    
        
        
        LargeLanguageModel --> "*" AiTask : performsTask
        click AiTask href "../AiTask/"
    

        
      LargeLanguageModel : power_consumption_w
        
      LargeLanguageModel : related_mappings
        
          
    
        
        
        LargeLanguageModel --> "*" Any : related_mappings
        click Any href "../Any/"
    

        
      LargeLanguageModel : requiresCapability
        
          
    
        
        
        LargeLanguageModel --> "*" Any : requiresCapability
        click Any href "../Any/"
    

        
      LargeLanguageModel : supported_languages
        
      LargeLanguageModel : url

Inheritance

Section titled “Inheritance”

Class Properties

Section titled “Class Properties”
Property Value
Mixin Yes

Slots

Section titled “Slots”
Name Cardinality and Range Description Inheritance
numParameters 0..1
Integer		 A property indicating the number of parameters in a LLM direct
numTrainingTokens 0..1
Integer		 The number of tokens a AI model was trained on direct
contextWindowSize 0..1
Integer		 The total length, in bytes, of an AI model’s context window direct
hasInputModality *
Modality		 A relationship indicating the input modalities supported by an AI component direct
hasOutputModality *
Modality		 A relationship indicating the output modalities supported by an AI component direct
hasTrainingData *
Dataset		 A relationship indicating the datasets an AI model was trained on direct
fine_tuning 0..1
String		 A description of the fine-tuning mechanism(s) applied to a model direct
supported_languages *
String		 A list of languages, expressed as ISO two letter codes direct
isPartOf 0..1
LargeLanguageModelFamily		 Annotation that a Large Language model is part of a family of models direct
requiresCapability *
Any		 Indicates that this entry requires a specific capability direct
hasEvaluation *
AiEvalResult		 A relationship indicating that an entity has an AI evaluation result AiModel
architecture 0..1
String		 A description of the architecture of an AI such as ‘Decoder-only’ AiModel
gpu_hours 0..1
Integer		 GPU consumption in terms of hours AiModel
power_consumption_w 0..1
Integer		 power consumption in Watts AiModel
carbon_emitted 0..1
Float		 The number of tons of carbon dioxide equivalent that are emitted during train… AiModel
hasRiskControl *
RiskControl		 Indicates the control measures associated with a system or component to modif… AiModel
isProducedBy 0..1
Organization		 A relationship to the Organization instance which produces this instance BaseAi
hasModelCard *
String		 A relationship to model card references BaseAi
hasDocumentation *
Documentation		 Indicates documentation associated with an entity BaseAi
hasLicense 0..1
License		 Indicates licenses associated with a resource BaseAi
performsTask *
AiTask		 relationship indicating the AI tasks an AI model can perform BaseAi
isProvidedBy 0..1
Organization		 A relationship to the Organization instance that provides this instance BaseAi
id 1
String		 A unique identifier to this instance of the model element Entity
name 0..1
String		 A text name of this instance Entity
description 0..1
String		 The description of an entity Entity
url 0..1
Uri		 An optional URL associated with this instance Entity
dateCreated 0..1
Date		 The date on which the entity was created Entity
dateModified 0..1
Date		 The date on which the entity was most recently modified Entity
exact_mappings *
Any		 The property is used to link two concepts, indicating a high degree of confid… Entity
close_mappings *
Any		 The property is used to link two concepts that are sufficiently similar that … Entity
related_mappings *
Any		 The property skos:relatedMatch is used to state an associative mapping link b… Entity
narrow_mappings *
Any		 The property is used to state a hierarchical mapping link between two concept… Entity
broad_mappings *
Any		 The property is used to state a hierarchical mapping link between two concept… Entity
isCategorizedAs *
Any		 A relationship where an entity has been deemed to be categorized Entity
hasLifecycleStatus 0..1
LifecycleStatus		 The editorial / publication lifecycle state of this entity Entity
notes *
String		 Free-text editorial notes, source breadcrumbs, or build-time provenance that … Entity

Mixin Usage

Section titled “Mixin Usage”
mixed into description
Adapter Adapter-based methods add extra trainable parameters after the attention and …

Usages

Section titled “Usages”
used by used in type used
Container aimodels range LargeLanguageModel
Adapter adaptsModel range LargeLanguageModel

Aliases

Section titled “Aliases”
  • LLM

Identifier and Mapping Information

Section titled “Identifier and Mapping Information”

Schema Source

Section titled “Schema Source”

Mappings

Section titled “Mappings”
Mapping Type Mapped Value
self nexus:LargeLanguageModel
native nexus:LargeLanguageModel

Examples

Section titled “Examples”

Example: LargeLanguageModel-granite-3.0-2b-base

Section titled “Example: LargeLanguageModel-granite-3.0-2b-base”
id: granite-3.0-2b-base
name: Granite-3.0-2B-Base
description: Granite-3.0-2B-Base is a decoder-only language model to support a variety of text-to-text
  generation tasks.
url: https://github.com/ibm-granite/granite-3.0-language-models
dateCreated: '2024-10-21'
hasModelCard:
- https://huggingface.co/ibm-granite/granite-3.0-2b-instruct
- https://www.ibm.com/docs/en/watsonx/w-and-w/2.1.x?topic=models-granite-30-2b-instruct-model-card
hasDocumentation:
- granite-3.0-paper
hasLicense: license-apache-2.0
performsTask:
- question-answering
- summarization
- text-classification
- text-generation
- code-generation
- code-explanation
- code-editing
isProvidedBy: ibm
hasEvaluation:
- truthfulqa-granite-3-2b-instruct
architecture: Decoder-only
carbon_emitted: 68.1
numParameters: 2500000000
numTrainingTokens: 12000000000000
contextWindowSize: 4094
hasInputModality:
- modality-text
hasOutputModality:
- modality-text
isPartOf: ibm-granite

LinkML Source

Section titled “LinkML Source”

Direct

Section titled “Direct”
name: LargeLanguageModel
description: A large language model (LLM) is an AI model which supports a range of
  language-related tasks such as generation, summarization, classification, among
  others. A LLM is implemented as an artificial neural networks using a transformer
  architecture.
from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
aliases:
- LLM
is_a: AiModel
mixin: true
slots:
- numParameters
- numTrainingTokens
- contextWindowSize
- hasInputModality
- hasOutputModality
- hasTrainingData
- fine_tuning
- supported_languages
- isPartOf
- requiresCapability
slot_usage:
  isPartOf:
    name: isPartOf
    description: Annotation that a Large Language model is part of a family of models
    range: LargeLanguageModelFamily

Induced

Section titled “Induced”
name: LargeLanguageModel
description: A large language model (LLM) is an AI model which supports a range of
  language-related tasks such as generation, summarization, classification, among
  others. A LLM is implemented as an artificial neural networks using a transformer
  architecture.
from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
aliases:
- LLM
is_a: AiModel
mixin: true
slot_usage:
  isPartOf:
    name: isPartOf
    description: Annotation that a Large Language model is part of a family of models
    range: LargeLanguageModelFamily
attributes:
  numParameters:
    name: numParameters
    description: A property indicating the number of parameters in a LLM.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: integer
    minimum_value: 0
  numTrainingTokens:
    name: numTrainingTokens
    description: The number of tokens a AI model was trained on.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: integer
    minimum_value: 0
  contextWindowSize:
    name: contextWindowSize
    description: The total length, in bytes, of an AI model's context window.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: integer
    minimum_value: 0
  hasInputModality:
    name: hasInputModality
    description: A relationship indicating the input modalities supported by an AI
      component. Examples include text, image, video.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: Modality
    multivalued: true
    inlined: false
  hasOutputModality:
    name: hasOutputModality
    description: A relationship indicating the output modalities supported by an AI
      component. Examples include text, image, video.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: Modality
    multivalued: true
    inlined: false
  hasTrainingData:
    name: hasTrainingData
    description: A relationship indicating the datasets an AI model was trained on.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: airo:hasTrainingData
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: Dataset
    multivalued: true
    inlined: false
  fine_tuning:
    name: fine_tuning
    description: A description of the fine-tuning mechanism(s) applied to a model.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: string
  supported_languages:
    name: supported_languages
    description: A list of languages, expressed as ISO two letter codes. For example,
      'jp, fr, en, de'
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - LargeLanguageModel
    range: string
    multivalued: true
    inlined: true
    inlined_as_list: true
  isPartOf:
    name: isPartOf
    description: Annotation that a Large Language model is part of a family of models
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:isPartOf
    owner: LargeLanguageModel
    domain_of:
    - Entry
    - Risk
    - CapabilityGroup
    - LargeLanguageModel
    - AiTaskGroup
    - Stakeholder
    range: LargeLanguageModelFamily
  requiresCapability:
    name: requiresCapability
    description: Indicates that this entry requires a specific capability
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    domain: Any
    owner: LargeLanguageModel
    domain_of:
    - Entry
    - LargeLanguageModel
    - AiTask
    - Adapter
    inverse: requiredByTask
    range: Any
    multivalued: true
    inlined: false
  hasEvaluation:
    name: hasEvaluation
    description: A relationship indicating that an entity has an AI evaluation result.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: dqv:hasQualityMeasurement
    owner: LargeLanguageModel
    domain_of:
    - AiModel
    range: AiEvalResult
    multivalued: true
  architecture:
    name: architecture
    description: A description of the architecture of an AI such as 'Decoder-only'.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - AiModel
    range: string
  gpu_hours:
    name: gpu_hours
    description: GPU consumption in terms of hours
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - AiModel
    range: integer
    minimum_value: 0
  power_consumption_w:
    name: power_consumption_w
    description: power consumption in Watts
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - AiModel
    range: integer
    minimum_value: 0
  carbon_emitted:
    name: carbon_emitted
    description: The number of tons of carbon dioxide equivalent that are emitted
      during training
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - AiModel
    range: float
    minimum_value: 0
    unit:
      symbol: t CO2-eq
      descriptive_name: tons of CO2 equivalent
  hasRiskControl:
    name: hasRiskControl
    description: Indicates the control measures associated with a system or component
      to modify risks.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: airo:hasRiskControl
    owner: LargeLanguageModel
    domain_of:
    - AiModel
    range: RiskControl
    multivalued: true
  isProducedBy:
    name: isProducedBy
    description: A relationship to the Organization instance which produces this instance.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - BaseAi
    range: Organization
  hasModelCard:
    name: hasModelCard
    description: A relationship to model card references.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - BaseAi
    range: string
    multivalued: true
    inlined: true
    inlined_as_list: true
  hasDocumentation:
    name: hasDocumentation
    description: Indicates documentation associated with an entity.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: airo:hasDocumentation
    owner: LargeLanguageModel
    domain_of:
    - Dataset
    - Vocabulary
    - Taxonomy
    - Concept
    - Group
    - Entry
    - Term
    - Principle
    - RiskTaxonomy
    - RiskControlGroupTaxonomy
    - Action
    - BaseAi
    - LargeLanguageModelFamily
    - AiTaskTaxonomy
    - AiEval
    - EveryEvalAIResult
    - BenchmarkMetadataCard
    - Adapter
    - LLMIntrinsic
    range: Documentation
    multivalued: true
    inlined: false
  hasLicense:
    name: hasLicense
    description: Indicates licenses associated with a resource
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: airo:hasLicense
    owner: LargeLanguageModel
    domain_of:
    - Dataset
    - Documentation
    - Vocabulary
    - Taxonomy
    - RiskTaxonomy
    - RiskControlGroupTaxonomy
    - BaseAi
    - AiTaskTaxonomy
    - AiEval
    - BenchmarkMetadataCard
    - Adapter
    range: License
  performsTask:
    name: performsTask
    description: relationship indicating the AI tasks an AI model can perform.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    owner: LargeLanguageModel
    domain_of:
    - BaseAi
    range: AiTask
    multivalued: true
    inlined: false
  isProvidedBy:
    name: isProvidedBy
    description: A relationship to the Organization instance that provides this instance.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:provider
    owner: LargeLanguageModel
    domain_of:
    - Dataset
    - BaseAi
    range: Organization
  id:
    name: id
    description: A unique identifier to this instance of the model element. Example
      identifiers include UUID, URI, URN, etc.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:identifier
    identifier: true
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: string
    required: true
  name:
    name: name
    description: A text name of this instance.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:name
    owner: LargeLanguageModel
    domain_of:
    - Entity
    - BenchmarkMetadataCard
    range: string
  description:
    name: description
    description: The description of an entity
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:description
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: string
  url:
    name: url
    description: An optional URL associated with this instance.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:url
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: uri
  dateCreated:
    name: dateCreated
    description: The date on which the entity was created.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:dateCreated
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: date
    required: false
  dateModified:
    name: dateModified
    description: The date on which the entity was most recently modified.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: schema:dateModified
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: date
    required: false
  exact_mappings:
    name: exact_mappings
    description: The property is used to link two concepts, indicating a high degree
      of confidence that the concepts can be used interchangeably across a wide range
      of information retrieval applications
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: skos:exactMatch
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: Any
    multivalued: true
    inlined: false
  close_mappings:
    name: close_mappings
    description: The property is used to link two concepts that are sufficiently similar
      that they can be used interchangeably in some information retrieval applications.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: skos:closeMatch
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: Any
    multivalued: true
    inlined: false
  related_mappings:
    name: related_mappings
    description: The property skos:relatedMatch is used to state an associative mapping
      link between two concepts.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: skos:relatedMatch
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: Any
    multivalued: true
    inlined: false
  narrow_mappings:
    name: narrow_mappings
    description: The property is used to state a hierarchical mapping link between
      two concepts, indicating that the concept linked to, is a narrower concept than
      the originating concept.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: skos:narrowMatch
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: Any
    multivalued: true
    inlined: false
  broad_mappings:
    name: broad_mappings
    description: The property is used to state a hierarchical mapping link between
      two concepts, indicating that the concept linked to, is a broader concept than
      the originating concept.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: skos:broadMatch
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: Any
    multivalued: true
    inlined: false
  isCategorizedAs:
    name: isCategorizedAs
    description: A relationship where an entity has been deemed to be categorized
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: nexus:isCategorizedAs
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: Any
    multivalued: true
    inlined: false
  hasLifecycleStatus:
    name: hasLifecycleStatus
    description: The editorial / publication lifecycle state of this entity. Distinct
      from AiLifecyclePhase, which describes an AI system's runtime evolution rather
      than the editorial workflow of a catalogued entry.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    aliases:
    - lifecycle_status
    - doc_status
    rank: 1000
    slot_uri: adms:status
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: LifecycleStatus
  notes:
    name: notes
    description: Free-text editorial notes, source breadcrumbs, or build-time provenance
      that do not belong in the user-facing description. Opaque to consumers.
    from_schema: https://w3id.org/ai-atlas-nexus/ai-risk-ontology
    rank: 1000
    slot_uri: skos:note
    owner: LargeLanguageModel
    domain_of:
    - Entity
    range: string
    recommended: false
    multivalued: true