트랜스포머(Transformer)란?!

구글이 발표한 논문인 "Attention is all you need"에서 나온 모델로 기존의 seq2seq의 구조인 인코더-디코더를 따르지만, 내부적으로 RNN 레이어 없이, 어텐션(Attention)으로만 구현한 모델

 

•  

🤗 Transformers provides APIs and tools to easily download and train state-of-the-art pretrained models. Using pretrained models can reduce your compute costs, carbon footprint, and save you the time and resources required to train a model from scratch. These models support common tasks in different modalities, such as:

📝 Natural Language Processing: text classification, named entity recognition, question answering, language modeling, summarization, translation, multiple choice, and text generation.
🖼️ Computer Vision: image classification, object detection, and segmentation.
🗣️ Audio: automatic speech recognition and audio classification.
🐙 Multimodal: table question answering, optical character recognition, information extraction from scanned documents, video classification, and visual question answering.