Summary of Orion-14b: Open-source Multilingual Large Language Models, by Du Chen et al.
Orion-14B: Open-source Multilingual Large Language Models
by Du Chen, Yi Huang, Xiaopu Li, Yongqiang Li, Yongqiang Liu, Haihui Pan, Leichao Xu, Dacheng Zhang, Zhipeng Zhang, Kun Han
First submitted to arxiv on: 20 Jan 2024
Categories
- Main: Computation and Language (cs.CL)
- Secondary: Machine Learning (cs.LG)
GrooveSquid.com Paper Summaries
GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!
| Summary difficulty | Written by | Summary |
|---|---|---|
| High | Paper authors | High Difficulty Summary Read the original abstract here |
| Medium | GrooveSquid.com (original content) | Medium Difficulty Summary A new family of multilingual large language models, Orion-14B, is introduced, featuring 14 billion parameters. A data scheduling approach is used to train a foundational model on a diverse corpus of 2.5 trillion tokens from texts in multiple languages, including English, Chinese, Japanese, Korean, and others. The models are fine-tuned for conversational applications and specific use cases, achieving state-of-the-art performance across various tasks. The Orion-14B model family and its associated code are made publicly accessible to inspire future research and practical applications. |
| Low | GrooveSquid.com (original content) | Low Difficulty Summary Orion-14B is a special group of language models that can understand many languages. These models have 14 billion tiny pieces of information, which helps them learn from lots of texts in different languages like English, Chinese, Japanese, Korean, and more. The researchers used a special way to train the model on huge amounts of text data. They also made smaller versions of the model for specific uses like chatting with people. The models are very good at doing tasks and can help us do things better in the future. |
