Android App to run Llama-v2-7B-Chat Quantized INT4 on my Android Device

[taeyeonlee]

Hi,
Could you share the sample Android App to run Llama-v2-7B-Chat Quantized INT4 on my Android Device ?

[mestrona-3]

Hi @taeyeonlee, thank you for the feature request. We have heard this request from many users and have it in our backlog. In the meantime, please reference the demo.py and export.py for Llamav2. Thank you for your patience!

[taeyeonlee]

Hi, @mestrona-3
Could you please share the plan to release the Android sample app with C++ APIs ?

[bhushan23]

Hi @taeyeonlee
We are validating Android App internally and will be releasing it during first half of November.

[YangWang92]

Hi @bhushan23 , thanks for the issue. Do you have any further updates? Thanks.

[mestrona-3]

Hi All, we are still testing the app and are aiming for it to be released in one of upcoming releases. Please join our Slack community for continued updates.

We use Github for bugs and attaching detailed logs. Slack is the go to place for any new feature announcements and release notes.