Show HN: We made a 2.5GB Offline disaster AI assistant [video]

Posted by inlandrookie on Thursday August 14, 2025 @01:54PM
from the show-hn dept.

https://www.youtube.com/watch?v=VfJikuZMR4E

It is a prototype for Gemma 3n Impact Challenge hosted by DeepMind. We don't have experience on local LLM before, so it is a pretty fun learning experience. Hope to see more lightweight llm model in the future!

( 4 comments | 3 points | on HN )

Re:Show HN: We made a 2.5GB Offline disaster AI assistant [v... by inlandrookie on Thursday August 14, 2025 @02:21PM (#44903822)

Source Code: https://github.com/Aurora-yang-git/MAZU-Offline_Disaster_Ass...

[ Parent | on HN ]

Re:Show HN: We made a 2.5GB Offline disaster AI assistant [v... by habedi0 on Thursday August 14, 2025 @02:11PM (#44903724)

Looks like a great (offline) use case for small language models. Are you going to share the source code for your implementation?

[ Parent | on HN ]

Re:Show HN: We made a 2.5GB Offline disaster AI assistant [v... by inlandrookie on Thursday August 14, 2025 @02:22PM (#44903834)

https://github.com/Aurora-yang-git/MAZU-Offline_Disaster_Ass...

[ Parent | on HN ]

Re:Show HN: We made a 2.5GB Offline disaster AI assistant [v... by habedi0 on Thursday August 14, 2025 @02:52PM (#44904164)

Thanks for the share.

[ Parent | on HN ]