#ondevice

Hacker Newsh4ckernews
2025-06-01
2025-01-31

💥 ObjectBox 4.1 for Java & Kotlin
* JWT authentication for Data Sync 🔒
* Advanced query conditions for map properties 🗺️
* "Geo" distance for Vector Search 🌍

github.com/objectbox/objectbox

#java #kotlin #database #vectordatabase #ondevice #edge

卡拉今天看了什麼ai_workspace@social.mikala.one
2024-07-10

GitHub - facebookresearch/MobileLLM: MobileLLM Optimizing Sub-billion Parameter Language Models for On-Device Use Cases. In ICML 2024.

Link
Summary:
MobileLLM是一個針對移動設備優化的語言模型,具有不到十億個參數。它使用了SwiGLU激活函數、深度和薄的架構、嵌入共享和分組查詢注意機制。MobileLLM-125M/350M在零樣本常識推理任務中取得了卓越的2.7%/4.3%準確性提升。在更新的版本中,證明了設計理念在更大的模型中也有效,提供了SoTA結果,包括MobileLLM-600M/1B/1.5B。該模型的權重仍在法律審查中,但研究人員可以通過電子郵件與作者聯繫。

Key Points:
- MobileLLM是一個針對移動設備優化的語言模型,具有不到十億個參數。
- 使用了SwiGLU激活函數、深度和薄的架構、嵌入共享和分組查詢注意機制。
- MobileLLM-125M/350M在零樣本常識推理任務中取得了卓越的2.7%/4.3%準確性提升。
- 更新的版本證明了設計理念在更大的模型中也有效,提供了SoTA結果,包括MobileLLM-600M/1B/1.5B。
- 該模型的權重仍在法律審查中。
- 研究人員可以通過電子郵件與作者聯繫。

Keywords:
#MobileLLM #DeepLearning #AI #NeuralNetwork #On-Device #LLM #ZeroShotCommonSenseReasoning #ICML2024

Techopolis Online Solutionstechopolis@techopolis.social
2024-07-02

💬 Question of the Day 💬

Hey everyone! We want to hear from you: Do you prefer AI to be available on device or in the cloud? 🤔

Share your thoughts in the comments below and let’s get the conversation started! ⌨️💭

#TechTalk #AI #OnDevice #CloudComputing #QuestionOfTheDay #EngageWithUs #TechCommunity

Mela News :verified:MelaNews@mastodon.uno
2024-04-22

📱 Siri potrebbe diventare ancora più smart? Apple lavora a un grande modello linguistico direttamente sull'iPhone. Potenzierà AI e privacy. 🤔 #Apple #AI #LLM #Siri #OnDevice

2018-12-24

Interesting approach to change the way data will be handled with the aim for a better use of it by AI.

Some points in this can be debatable but on the whole it seems like an interesting and somehow kind of realistic change.

#ai #privacy #ondevice #data

thecloudfall.com/?utm_source=d

Client Info

Server: https://mastodon.social
Version: 2025.04
Repository: https://github.com/cyevgeniy/lmst