Transformer model: Difference between revisions
(Added Knowledge Graph section) |
(Fix: remove --- horizontal lines (7 removed)) |
||
| Line 18: | Line 18: | ||
* 언제 사용하는가? - 서버 구성, 성능 튜닝, 문제 해결 시 | * 언제 사용하는가? - 서버 구성, 성능 튜닝, 문제 해결 시 | ||
== Purpose == | == Purpose == | ||
| Line 28: | Line 27: | ||
* Non-goals: 다른 주제로의 확장 | * Non-goals: 다른 주제로의 확장 | ||
== Key Concepts == | == Key Concepts == | ||
| Line 42: | Line 40: | ||
|} | |} | ||
== Detailed Explanation == | == Detailed Explanation == | ||
| Line 52: | Line 49: | ||
<references /> | <references /> | ||
== Best Practices == | == Best Practices == | ||
| Line 60: | Line 56: | ||
* 테스트 환경에서 먼저 검증 | * 테스트 환경에서 먼저 검증 | ||
== References == | == References == | ||
| Line 66: | Line 61: | ||
* [https://wiki.hpcmate.com Transformer model] | * [https://wiki.hpcmate.com Transformer model] | ||
== Related Pages == | == Related Pages == | ||
| Line 75: | Line 69: | ||
* [[Network]] | * [[Network]] | ||
[[Category:Server]] | [[Category:Server]] | ||
Latest revision as of 11:31, 17 July 2026
Overview
Transformer model에 대한 기술 문서입니다.
Summary
- 무엇인가? - Transformer model
- 왜 필요한가? - HPC 및 서버 환경에서 필수 개념
- 언제 사용하는가? - 서버 구성, 성능 튜닝, 문제 해결 시
Purpose
이 문서가 존재하는 이유
- Goal: Transformer model에 대한 기술 정보 제공
- Scope: Transformer model의 개념, 사용법, 설정
- Non-goals: 다른 주제로의 확장
Key Concepts
| Concept | Description | Related |
|---|---|---|
| Transformer model | HPC/서버 환경에서 중요한 기술 개념 | Linux, Server |
Detailed Explanation
A transformer model is a type of deep learning model that was introduced in 2017 paper called "Attention is All You Need" by Ashish Vaswani, a team at Google Brain, and a group from the University of Toronto. and now now used in applications such as training LLMs. [1][2] Transformers have the advantage of having no recurrent units such as recurrent neural networks (RNNs) or convolutional neural networks (CNNs), and thus requires less training time than recurrent neural architectures, such as long short-term memory (LSTM), and its later variation has been prevalently adopted for training large language models (LLM) on large (language) datasets. Transformers process input sequences in parallel, making it highly efficient for training and inference. So Transformer models need less training time than previous recurrent neural network architectures. Transformer models can translate text and speech in near-real-time. OpenAI’s popular ChatGPT text generation tool makes use of transformer architectures for prediction, summarization, question answering and more, because they allow the model to focus on the most relevant segments of input text. The “GPT” seen in the tool’s various versions (e.g. GPT-2, GPT-3) stands for “generative pre-trained transformer.” Text-based generative AI tools such as ChatGPT benefit from transformer models because they can more readily predict the next word in a sequence of text, based on a large, complex data sets. This page describes Transformer architectues and its work process.
Best Practices
- 최신 버전 사용 권장
- 공식 문서 참고
- 테스트 환경에서 먼저 검증
References
Related Pages
Knowledge Graph
Related