Ecosyste.ms: Awesome
An open API service indexing awesome lists of open source software.
https://github.com/togethercomputer/MoA
Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
https://github.com/togethercomputer/MoA
Last synced: 30 days ago
JSON representation
Together Mixture-Of-Agents (MoA) – 65.1% on AlpacaEval with OSS models
- Host: GitHub
- URL: https://github.com/togethercomputer/MoA
- Owner: togethercomputer
- License: apache-2.0
- Created: 2024-06-04T17:23:26.000Z (6 months ago)
- Default Branch: main
- Last Pushed: 2024-10-17T22:20:59.000Z (about 2 months ago)
- Last Synced: 2024-11-04T20:50:21.692Z (about 1 month ago)
- Language: Python
- Homepage:
- Size: 22.2 MB
- Stars: 2,590
- Watchers: 35
- Forks: 352
- Open Issues: 21
-
Metadata Files:
- Readme: README.md
- License: LICENSE
Awesome Lists containing this project
- ai-game-devtools - Mixture of Agents (MoA) - of-Agents Enhances Large Language Model Capabilities. |[arXiv](https://arxiv.org/abs/2406.04692) | | Agent | (<span id="game">Game (Agent)</span> / <span id="tool">Tool (AI LLM)</span>)
- awesome-LLM-resourses - MoA - of-the-art results. (智能体 Agents)
- StarryDivineSky - togethercomputer/MoA - of-Agents (MoA) 是一种利用多个大型语言模型 (LLM) 的集体优势来提高性能的新方法,在 AlpacaEval 2.0上取得了最先进的结果。通过采用分层架构,其中每一层包含多个 LLM 代理,MoA 使用仅开源模型,显著优于 GPT-4 Omni 的 57.5% 的得分,达到了 65.1% 的得分。该项目提供了一个简单的 50 行代码示例,展示了如何使用 MoA,以及一个更高级的示例,展示了如何使用多层 MoA。此外,该项目还提供了一个交互式命令行界面 (CLI) 演示,展示了一个简单的多轮聊天机器人,其中最终响应来自各种参考模型的聚合。用户可以通过输入指令与聊天机器人进行交互,并获得基于多个模型的聚合响应。 (A01_文本生成_文本对话 / 大语言对话模型及数据)
- alan_awesome_llm - MoA - of-the-art results. (Agents)
- alan_awesome_llm - MoA - of-the-art results. (Agents)