dsjakupov

Ive got a similar story but with slightly harsher constraints. I also want to build private AI app but for the phone. As you know they have very little RAM per app and I needed to somehow circumvent it. So I picked qwen2.5-0.5B as it was good for the purpose of answering people and keeping the dialog and no overkill + whisper model to add stt feature (437 MB for both). I think that if your app does only one job, you can use smaller model and fine tune it a bit

Oh, I had similar case. First, I used qwen without any ChatML-like syntax and it continued speaking and speaking, then I used <|im_start|>/<|im_end|> to control it somehow

Ha, on Android that wouldn't help you, already tried hahahah

Got it, for me it happened in a day max on my main working account ( not personal )

Yeah, I did it for my app that specializes in privacy. Basically I used qwen2.5 for the mobile use and the case I was solving is user's most private thoughts - smth like a private diary But I am thinking about how can I fine-tune the model on the users' data and keep them private? Maybe like improve the model directly on the phone ahhaha

Same here My build was ready like for a month and all that was stopping me is the requirement for the 12 testers being active for 14 days. When I applied to both stores, I thought apple is gonna be a problem, but google is a bigger unmovable wall