Ai2 OLMoE

Our app is intended to help researchers better explore how to make on-device intelligence better and to enable developers to quickly prototype new AI experiences – all with no cloud connectivity required.

The Ai2 OLMoE app can be used to:

• Experience which real-world tasks state-of-the-art local models are capable of
• Research how to improve small AI models
• Test your own models locally using our open-source codebase
• Integrate OLMoE into other iOS applications

Best of all, interactions with OLMoE are fully private. Unless you decide to share a conversation, your conversations never leave your device.

Features:

• Efficiency: OLMoE is a highly efficient mixture-of-experts version of the Ai2 OLMo family of models
• Performance: OLMoE is trained with the fully open, state-of-the-art Tülu 3 recipe
• Privacy: The Ai2 OLMoE app provides privacy and security by operating completely on-device
• Shareable: Easily share the output of your conversations with friends or colleagues
• Truly open: The OLMoE model and the application code are fully open-source

OLMoE is proudly offered by Ai2 as a powerful research tool to help the community better understand how LLMs are created and how they operate. When interacting with OMLoE, always use your best judgment, fact-check important information, and consider the context when interpreting content generated in this app.

Open source code repository available at: https://github.com/allenai/OLMoE.swift

Terms of service: https://allenai.org/terms/2024-09-25 Privacy policy: https://allenai.org/privacy-policy/2022-07-21