IndustrialOne

CPU t/s regression from GPT4All 2.6.1 -> 2.6.2

11

On my old 4-core computer, I got roughly 2.1 t/s with openorca-chat model. When I upgraded to a 6-core PC, the speed doubled. Other models got the same speed increase....

Question about automated posting

1

Hey mbruel, great program, I love it, but I need a way to resume my uploading after closing the program. I noticed that drag-dropping all my files with the quick...

How to change these dark theme colors on Save As window?

5

Windows Version: **Question** How do I change these grey colors? How it looks now:  How it should look:  **Things you already tried** I searched for a property or...

How to change text of dialog box?

4

*Windows Version*: **Question** How do I change the text in the dialog box? In the theme I have it is black but it should be white. **Things you already tried**...

Bug: Speed regression from early this year

7

### What happened? https://github.com/nomic-ai/gpt4all/issues/2204 Since I upgraded to gpt4all 2.6.2 (which updated llama.cpp) my speed dropped from 3-4 t/s to 1 t/s. I am getting 1/3 the speed across all...

Can't get this to work

2

OS: Win10 Pro x64 Python: 3.13.2 I copy-pasted the code you guys provided but got a **AssertionError: Torch not compiled with CUDA enabled** error so I modified the code to...

[Feature Request] Queueing and appending name of model to filename

1

UVR should queue processing requests because I often need to process the same sample with 10 different models before one of them turns up a good result and it's annoying...

VVenC demands .yuv output so I intend to use avs2yuv to use AVS scripts with VVenC. The problem is VVenC requires an "-i input.yuv" so what do I type for...