linformer 6 transformer 5 attention-mechanism 4 deep-learning 3 performer 2 llm 2 pytorch 2 attention 1 vision 1 layer-scale 1 low-rank-approximation 1 prenormalization 1 pretraining 1 runpod 1 text-classification 1 text-generation 1 training 1 deep-neural-networks 1 language-model 1 llms 1 nlp-library 1 seq2seq 1 seq2seq-model 1 attention-is-all-you-need 1 awesome 1 longformer 1 multihead-attention 1 reformer 1 self-attention 1 transformer-network 1 detr 1 linear-multihead-attention 1 artificial-intelligence 1 machine-learning 1 paper 1 classification 1 efficient 1 gpu-computing 1 image 1 nystrom 1