https://github.com/allenai/OLMoE
OLMoE: Open Mixture-of-Experts Language Models
https://github.com/allenai/OLMoE
Last synced: 12 months ago
JSON representation
OLMoE: Open Mixture-of-Experts Language Models
- Host: GitHub
- URL: https://github.com/allenai/OLMoE
- Owner: allenai
- License: apache-2.0
- Created: 2024-06-22T21:56:46.000Z (over 1 year ago)
- Default Branch: main
- Last Pushed: 2025-03-14T20:55:36.000Z (12 months ago)
- Last Synced: 2025-03-14T21:36:23.930Z (12 months ago)
- Language: Jupyter Notebook
- Homepage: https://arxiv.org/abs/2409.02060
- Size: 61.1 MB
- Stars: 674
- Watchers: 10
- Forks: 56
- Open Issues: 12
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- StarryDivineSky - allenai/OLMoE - of-Expert 语言模型。完全开放、最先进的 Expert 模型混合,具有 13 亿个有效参数和 69 亿个总参数。所有数据、代码和日志均已发布。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
- awesome-repositories - allenai/OLMoE - OLMoE: Open Mixture-of-Experts Language Models (Jupyter Notebook)