목록llama 논문 (1)

My Vision, Computer Vision

[논문 요약/리뷰] LLaMA: Open and Efficient Foundation Language Models

LLaMA: Open and Efficient Foundation Language ModelsWe introduce LLaMA, a collection of foundation language models ranging from 7B to 65B parameters. We train our models on trillions of tokens, and show that it is possible to train state-of-the-art models using publicly available datasets exclusively, withoarxiv.org발행일 : 2023. 02. 27.Meta AIProblem최근, 한정된 컴퓨터 예산(Budget)에서 LLM과 데이터셋 크기에 대한 최적화 연구..
Paper 2025. 2. 18. 13:23
이전 Prev 1 Next 다음