multi-head-self-attention 6 self-attention 2 attention 2 transformers 2 transformer 2 attention-mechanism 2 temporal-convolutional-network 1 hybrid-features 1 model-interpretation 1 peptide-toxicity 1 bigram 1 gpt-2 1 multi-head 1 multi-head-attention 1 multihead-attention 1 multihead-self-attention 1 pytorch-self-attention 1 transformer-attention 1 transformer-variants 1 motor-imagery 1 eeg 1 convolutional-neural-networks 1 classification 1 residual-connections 1 pytorch 1 python 1 neural-networks 1 llms 1 llm-training 1 layer-normalization 1 large-language-models 1 gpt-3 1 gpt 1 dropout-layers 1 attention-is-all-you-need 1