Transformers
BART
Introduced by Lewis et al. in BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and ComprehensionBART is a denoising autoencoder for pretraining sequence-to-sequence models. It is trained by (1) corrupting text with an arbitrary noising function, and (2) learning a model to reconstruct the original text. It uses a standard Transformer-based neural machine translation architecture. It uses a standard seq2seq/NMT architecture with a bidirectional encoder (like BERT) and a left-to-right decoder (like GPT). This means the encoder's attention mask is fully visible, like BERT, and the decoder's attention mask is causal, like GPT2.
Source: BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| RAG | 468 | 30.08% |
| Retrieval | 342 | 21.98% |
| Question Answering | 104 | 6.68% |
| Language Modelling | 52 | 3.34% |
| Large Language Model | 44 | 2.83% |
| Language Modeling | 42 | 2.70% |
| Information Retrieval | 39 | 2.51% |
| Text Generation | 26 | 1.67% |
| Prompt Engineering | 18 | 1.16% |
Adam
BPE
Dense Connections
Dropout
GELU
Layer Normalization
Multi-Head Attention
Residual Connection
Scaled Dot-Product Attention
Softmax
