mirek190

Results 14 issues of mirek190

As above Apps from start menu - Can not make shortcuts on desktop from flatpack apps (EO6) but normal shortcuts from deb apps are ok .

### Description AGiXT - llama.cpp - is not supporting ggmlv2 models or q5_1 ( 5 bit ). Those llama.cpp models ggmlv2 are even obsolete now because llama.cpp has ggmlv3 models...

type | report | bug
needs triage

privateGPT is not supporting ggmlv3 models

bug

I'm testing newest build. I have a stupid question as I added --multiline-input as parameter . How to end of my input now? Pressing enter just invoking a new line....

I am trying to load vicunlocked-65b.ggmlv3.q2_K.bin but nothing happening just quit without any error. The newest build master-5c64a09](https://github.com/ggerganov/llama.cpp/releases/tag/master-5c64a09 PS F:\LLAMA\llama.cpp> build\bin\main --model models/new2/vicunlocked-65b.ggmlv3.q2_K.bin --mlock --color --threads 8 --keep -1 --batch_size...

Are you planning WizardLM 65B model? Just asking ;) Noways running such big models is quite easy with the cheap rtx 3090 and llama.cpp for instance - getting 2 tokens/s

Hello Fooocus version: 2.1.805 - face swap is broken ( doesn't work properly ) if we add refiner for instance SD 1.5 epicrealism_pureEvolutionV5.safetensors

enhancement

Simple question. How to add flatpak package to the iso.

question

![photo_2022-10-09_18-10-50](https://user-images.githubusercontent.com/6817266/194770202-a9da62d5-354c-4401-9fe7-d5e08f349914.jpg)

Hi Linux - ubuntu 22.04 Tested commit 8fac645 - microphone is not passing audio to talk-llama , older builds ( from a month passing microphone audio and transcribe text from...