IRI: https://edrohal.com/llmd#Architecture
IRI: https://edrohal.com/llmd#AttentionLayer
IRI: https://edrohal.com/llmd#CausalAttentionLayer
IRI: http://schema.org/Corporation
IRI: https://edrohal.com/llmd#CrossAttentionLayer
IRI: https://edrohal.com/llmd#DataType
IRI: https://edrohal.com/llmd#DeepLearningModel
IRI: https://edrohal.com/llmd#EmbeddingLayer
IRI: https://edrohal.com/llmd#LanguageModel
IRI: https://edrohal.com/llmd#LanguageProcessingTask
IRI: https://edrohal.com/llmd#LanguageProcessingTrainingTask
IRI: https://edrohal.com/llmd#LanguageSeq2SeqTask
IRI: https://edrohal.com/llmd#LargeLanguageModel
IRI: https://edrohal.com/llmd#MachineLearningModel
IRI: https://edrohal.com/llmd#Mamba
IRI: https://edrohal.com/llmd#Model
IRI: https://edrohal.com/llmd#Module
IRI: https://edrohal.com/llmd#MultiLayerPerceptron
IRI: https://edrohal.com/llmd#NormalizationLayer
IRI: https://edrohal.com/llmd#PositionEmbeddingLayer
IRI: http://schema.org/ResearchOrganisation
IRI: https://edrohal.com/llmd#S4
IRI: https://edrohal.com/llmd#SelfAttentionLayer
IRI: https://edrohal.com/llmd#SingleLayerPerceptron
IRI: https://edrohal.com/llmd#Speech
IRI: https://edrohal.com/llmd#SupervisedTrainingTask
IRI: https://edrohal.com/llmd#Task
IRI: https://edrohal.com/llmd#TokenEmbeddingLayer
IRI: https://edrohal.com/llmd#Tokenizer
IRI: https://edrohal.com/llmd#TrainingTask
IRI: https://edrohal.com/llmd#Transformer
IRI: https://edrohal.com/llmd#TransformerBlock
IRI: https://edrohal.com/llmd#TransformerDecoderBlock
IRI: https://edrohal.com/llmd#TransformerDecoderOnly
IRI: https://edrohal.com/llmd#TransformerEncoderBlock
IRI: https://edrohal.com/llmd#TransformerEncoderDecoder
IRI: https://edrohal.com/llmd#TransformerEncoderOnly
IRI: https://edrohal.com/llmd#UnsupervisedTrainingTask
IRI: https://edrohal.com/llmd#fundedBy
IRI: https://edrohal.com/llmd#hasArchitecture
has characteristics: functional
IRI: https://edrohal.com/llmd#hasInputType
IRI: https://edrohal.com/llmd#hasOutputType
IRI: https://edrohal.com/llmd#hasPublished
IRI: https://edrohal.com/llmd#hasTrainingTask
IRI: https://edrohal.com/llmd#isModuleOf
has characteristics: asymmetric, irreflexive
IRI: https://edrohal.com/llmd#isTransposeLayer
has characteristics: symmetric
IRI: https://edrohal.com/llmd#performsTask
IRI: https://edrohal.com/llmd#publishedBy
has characteristics: functional
IRI: https://edrohal.com/llmd#usesModule
has characteristics: asymmetric, irreflexive
IRI: https://edrohal.com/llmd#usesTokenizer
has characteristics: functional
IRI: https://edrohal.com/llmd#PublishedIn
IRI: https://edrohal.com/llmd#usesCausalMask
has characteristics: functional
IRI: http://swrl.stanford.edu/ontologies/3.3/swrla.owl#isRuleEnabled
IRI: https://edrohal.com/llmd#BERT_ENCODER_ATTENTION_LAYER
IRI: https://edrohal.com/llmd#BERT_ENCODER_BLOCK
IRI: https://edrohal.com/llmd#BERT_ENCODER_MLP
IRI: https://edrohal.com/llmd#BERT_ENCODER_MLP_LAYER_1
IRI: https://edrohal.com/llmd#BERT_ENCODER_MLP_LAYER_2
IRI: https://edrohal.com/llmd#BERT_ENCODER_NORMALIZATION_LAYER
IRI: https://edrohal.com/llmd#BLOOM
IRI: https://edrohal.com/llmd#BLOOM_DECODER_BLOCK
IRI: https://edrohal.com/llmd#BLOOM_DECODER_BLOCK_ALIBI_LAYER
IRI: https://edrohal.com/llmd#BLOOM_DECODER_BLOCK_CAUSAL_ATTENTION_LAYER
IRI: https://edrohal.com/llmd#BLOOM_DESEMBEDDING_LAYER
IRI: https://edrohal.com/llmd#BLOOM_EMBEDDING_LAYER
IRI: https://edrohal.com/llmd#BLOOM_EMBEDDING_LAYER_NORM
IRI: https://edrohal.com/llmd#BLOOM_MODEL
IRI: https://edrohal.com/llmd#BytePairEncodingTokenizer
IRI: https://edrohal.com/llmd#BytePairEncodingWithSpaceTokenizer
IRI: https://edrohal.com/llmd#Google
IRI: https://edrohal.com/llmd#Google_AI
IRI: https://edrohal.com/llmd#GPT_DECODER_BLOCK
IRI: https://edrohal.com/llmd#GPT_DECODER_CAUSAL_ATTENTION
IRI: https://edrohal.com/llmd#GPT_DECODER_MLP
IRI: https://edrohal.com/llmd#GPT_DECODER_MLP_LAYER_1
IRI: https://edrohal.com/llmd#GPT_DECODER_MLP_LAYER_2
IRI: https://edrohal.com/llmd#GPT_DECODER_NORMALIZATION_LAYER
IRI: https://edrohal.com/llmd#GPT_DESEMBEDDING_LAYER
IRI: https://edrohal.com/llmd#GPT_EMBEDDING_LAYER
IRI: https://edrohal.com/llmd#GPT_ABSOLUTE_POSITION_EMBEDDING_LAYER
IRI: https://edrohal.com/llmd#GPT2
IRI: https://edrohal.com/llmd#GPT2_MODEL
IRI: https://edrohal.com/llmd#HuggingFace
IRI: https://edrohal.com/llmd#MaskedLanguageModeling
IRI: https://edrohal.com/llmd#MultiTaskFineTunning
IRI: https://edrohal.com/llmd#NextWordPrediction
IRI: https://edrohal.com/llmd#OpenAI
IRI: https://edrohal.com/llmd#SentencePiece
IRI: https://edrohal.com/llmd#Speech
IRI: https://edrohal.com/llmd#T5
IRI: https://edrohal.com/llmd#T5_DECODER_BLOCK
IRI: https://edrohal.com/llmd#T5_DECODER_CAUSAL_ATTENTION_LAYER
IRI: https://edrohal.com/llmd#T5_DECODER_CROSSATTENTION_LAYER
IRI: https://edrohal.com/llmd#T5_DECODER_MLP
IRI: https://edrohal.com/llmd#T5_DECODER_MLP_LAYER_1
IRI: https://edrohal.com/llmd#T5_DECODER_MLP_LAYER_2
IRI: https://edrohal.com/llmd#T5_DECODER_NORMALIZATION_LAYER
IRI: https://edrohal.com/llmd#T5_DESEMBEDDING_LAYER
IRI: https://edrohal.com/llmd#T5_EMBEDDING_LAYER
IRI: https://edrohal.com/llmd#T5_RELATIVE_POSITION_EMBEDDING
IRI: https://edrohal.com/llmd#T5.11b.model
IRI: https://edrohal.com/llmd#Text
IRI: https://edrohal.com/llmd#TextSummarization
IRI: https://edrohal.com/llmd#TextTranslation
The authors would like to thank Silvio Peroni for developing LODE, a Live OWL Documentation Environment, which is used for representing the Cross Referencing Section of this document and Daniel Garijo for developing Widoco, the program used to create the template used in this documentation.