Transformers
GPT
Introduced by Radford et al. in Improving Language Understanding by Generative Pre-TrainingGPT is a Transformer-based architecture and training procedure for natural language processing tasks. Training follows a two-stage procedure. First, a language modeling objective is used on the unlabeled data to learn the initial parameters of a neural network model. Subsequently, these parameters are adapted to a target task using the corresponding supervised objective.
Source: Improving Language Understanding by Generative Pre-Training
Papers
| Paper | Code | Results | Date | Stars |
|---|
Tasks
| Task | Papers | Share |
|---|---|---|
| Language Modelling | 84 | 10.62% |
| Large Language Model | 50 | 6.32% |
| Question Answering | 34 | 4.30% |
| Prompt Engineering | 27 | 3.41% |
| Retrieval | 23 | 2.91% |
| Text Generation | 22 | 2.78% |
| In-Context Learning | 21 | 2.65% |
| Decision Making | 20 | 2.53% |
| Sentence | 20 | 2.53% |
Adam
Attention Dropout
BPE
Dense Connections
Discriminative Fine-Tuning
Dropout
GELU
Layer Normalization
Linear Warmup With Cosine Annealing
Multi-Head Attention
Residual Connection
Scaled Dot-Product Attention
Softmax
Weight Decay
