https://arxiv.org/abs/2302.13971
LLaMA: Open and Efficient Foundation Language Models
We 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, witho
arxiv.org
'AI > Paper Analysis' 카테고리의 다른 글
| ChatGPT-1 Paper (0) | 2025.04.02 |
|---|---|
| LoRA Paper (0) | 2025.04.01 |
| LIama 2 Paper Model (0) | 2025.04.01 |