-
Notifications
You must be signed in to change notification settings - Fork 35
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
It crashes #7
Comments
Same issue for me on Samsung S10+, 8gb ram + 8vram. On fresh install: I open the app, load a 7b model, and even enter a prompt. It appears to process for half a second and then force closes. |
On samsung s10, it generates text with prompt, but only with alpaca and llama models. Crashes with other models for no reason. Sometimes it can crash with working models and is very slow. Although the same alpaca in termux works faster. |
How do you do the termux one i followed the guid but i can't find the android ndk but i followed another guid and it generated invisible text then crashed |
I just made the usual make. All in termux without ndk . |
I tried this: +termux-setup-storage+apt update && apt upgrade + pkg update + pkg install git +git clone (the repo) + cd alpaca + make chat + ./chat But it didn't work and crashed while generating, where the commands i used correct? |
maybe because I installed the |
I was also seeing crashes on my Galaxy S10 as soon as the conversation was starting. This was happening because the old version of llama.cpp has a bug where it closes a file descriptor twice. |
It Crashes While Generating A propmt
I am using a s21 fe with 8gb of ram and 8gb vram
The text was updated successfully, but these errors were encountered: