GPT-3 is an autoregressive transformer model with 175 billion parameters. It uses the same architecture/model as GPT-2, including the modified initialization, pre-normalization, and reversible tokenization, with the exception that GPT-3 uses alternating dense and locally banded sparse attention patterns in the layers of the transformer, similar to the Sparse Transformer.
Source: Language Models are Few-Shot LearnersPaper | Code | Results | Date | Stars |
---|
Task | Papers | Share |
---|---|---|
Language Modelling | 81 | 10.77% |
Question Answering | 48 | 6.38% |
Large Language Model | 48 | 6.38% |
Retrieval | 31 | 4.12% |
Prompt Engineering | 29 | 3.86% |
Code Generation | 28 | 3.72% |
In-Context Learning | 28 | 3.72% |
Sentence | 22 | 2.93% |
Text Generation | 18 | 2.39% |