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 | 56 | 6.94% |
| Language Modeling | 46 | 5.70% |
| Large Language Model | 41 | 5.08% |
| Retrieval | 27 | 3.35% |
| Question Answering | 24 | 2.97% |
| Text Generation | 24 | 2.97% |
| Prompt Engineering | 23 | 2.85% |
| RAG | 22 | 2.73% |
| Fairness | 16 | 1.98% |
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
