#OutputProbabilities
LightNews LightNews
mathiastck.bsky.social
"The transformer approach it describes has become the main architecture of a wide variety of AI, such as #LargeLanguageModels"

#OutputProbabilities
#Softmax
Linear
#Add&Norm
#FeedForward
#MultiHead Attention
#MaskedMultiHead Attention
#PositionalEncoding
#OutputEmbedding
#FeedForward
File:The-Transformer-model-architecture.png Output Probabilities Softmax Linear Add&Norm Feed Forward Add&Norm Multi-Head Attention Add&Norm Masked Multi-Head Attention Positional Encoding Output Embedding ↑ Add&Norm Feed Forward Add&Norm Multi-Head Attention Positional Encoding Input Embedding ↑ Input Output (shifted right)
February 24, 2026 at 3:26 PM