Jared Van Bortel

Fails on Arch Linux with ERROR: Error stripping "libzstd.so" : "" (segfault)

2

Here is the end of the output from a failing run of linuxdeployqt: ``` Log: copied: "/usr/lib/libzstd.so.1" Log: to "/home/jared/src/forks/gpt4all/gpt4all-chat/build/_CPack_Packages/Linux/IFW/gpt4all-installer-linux/packages/gpt4all/data/lib///libzstd.so.1" Log: dpkg not found, hence not deploying copyright files ERROR:...

qml: improve chats with missing models and model settings layout

2

| :rocket: | This description was created by [Ellipsis](https://www.ellipsis.dev) for commit ca95bb9ffa4912d4f1592064042ea160da0acca6 | |--------|--------| ### Summary: Improved handling of chats with missing models and enhanced layout of model settings in...

### Feature Request This is part of the solution to dealing with broken models that emit stop tokens that are not specified in their HF configuration (#2167) and is also...

Because current versions of GPT4All select a GPU backend *before* checking which llmodel implementations are supported by a given model file, we fail to load the model when the device...

llamamodel: prevent CUDA OOM crash by allocating VRAM early

2

This is a proposed fix for the issue where CUDA OOM can happen later than expected and crash GPT4All. The question is whether the benefit (falling back early instead of...