rixty/KoboldAI-Client
1
1
Fork 0
mirror of https://github.com/KoboldAI/KoboldAI-Client.git synced 2025-06-05 21:59:24 +02:00
Code Issues Projects Releases Wiki Activity

Readme changes

Browse Source
This commit is contained in:
Henk
2023-07-24 01:03:46 +02:00
parent a963c97acb
commit 70d2da55e5
1 changed files with 2 additions and 20 deletions
Download Patch File Download Diff File Expand all files Collapse all files

22
README_GPTQ.md
View File

@@ -2,26 +2,8 @@
(This guide is for both Linux and Windows and assumes user has git installed and a basic grasp of command line use)
#### Installation
In the command prompt/command line navigate to where you want the KoboldAI subfolder to be created.
For Nvidia users everything is automatically installed when you install the requirements, you merely need a compatible GPTQ model for it to show up.
Note: do not run your command prompt as administrator/with elevated priviledges, reports suggest this leads to problems.
`git clone https://github.com/0cc4m/KoboldAI -b latestgptq --recurse-submodules`
`cd KoboldAI`
Next step, (Windows) subfolder mode or B: option doesn't matter choose either
* [if on Windows]
```
install_requirements.bat
```
* if it closes the window when it finishes, reopen a command prompt and navigate back to your KoboldAI directory.
* [if on Linux with Nvidia]
```
./install_requirements.sh
```
* [if on Linux with AMD]
```
./install_requirements.sh rocm
@@ -46,5 +28,5 @@ If you haven't done so already, exit the command prompt/leave KAI's conda env. (
Run `play.bat` [windows], `play.sh` [linux Nvidia], or `play-rocm.sh` [linux AMD]
Switch to UI2, then load your model.
Load your model using Huggingface GPTQ as the backend option (This will show up when a valid GPTQ model is detected).