Electrotechnical and Computer Engineering
Vol. 39 No. 11 (2024): Proceedings of Faculty of Technical Sciences
GPT ARCHITECTURE AND APPLICATION IN THE SOFTWARE INDUSTRY
Abstract
GPT models are general purpose language prediction models. These are computer programs that can analyze, extract, summarize and otherwise use information to generate content. They create human-like text without being explicitly programmed to do so. As a result, they can be tuned for a range of natural language processing tasks, including answering questions, translating languages and summarizing text.
References
[1] https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
[2] https://proceedings.neurips.cc/paper_files/paper/2017/file/3f5ee243547dee91fbd053c1c4a845aa-Paper.pdf
[3] https://arxiv.org/pdf/2311.07361.pdf
[4] https://arxiv.org/pdf/2302.14520.pdf
[5] https://arxiv.org/pdf/2304.01852.pdf
[6] https://aws.amazon.com/what-is/gpt/