randoentity

Now also fixed in the dev branch with https://github.com/oobabooga/text-generation-webui/commit/3e3a7c42501e871fb40077106a55e59d4a3651d3 Eagerly testing :)

> > I unfortunately get a Segmentation fault every time with the new llama_cpp_python .. > > Yeah, same here, and not just on Command-r, so I've reverted llama-cpp-python for...

PSA: the dev branch now has a fix for this. For the gibberish make sure to use the (now default) min_p preset.

@RandomInternetPreson sorry I was probably too eager. I only retested the llama.cpp quants (exl2 was already working fine especially since the min_p update). You are using the full model quantized...

Workaround for people who have a hard time finding the FAQ (I'm not trying to be passive aggressive; just trying to be helpful): https://github.com/nextcloud/notes-android/blob/main/FAQ.md#illegalstateexception-duplicate-key

The workaround worked for me in version 4.1.0. I did not have to revert to a previous version. The error occurred for me about three weeks ago, so I might...

I don't know if this is the same issue as I'm having, namely the app crashing on startup until the app data is deleted, but based on the above I...

I had it a couple of weeks ago. All I had to do was use AppManager to launch an activity (just the main activity IIRC) and it worked normally again....

@oobabooga This is still relevant. On commit a363cdfca117e92967d9a25509146f02fbf63da1 (origin/dev) Date: Mon May 27 15:21:30 2024 +0300 Fixed with cherry-pick 3af2cfbc3c198ddd6b351c27af868287c5eb354d from this PR. One related error is when using --gpu-memory...

Workaround and fix: https://github.com/OpenAccess-AI-Collective/axolotl/issues/1423 Upstream: https://github.com/AutoGPTQ/AutoGPTQ/issues/606