-
### Environment
Self-Hosted (Bare Metal)
### System
Firefox 118.0.2, EndeavourOS
### Version
1.10.5
### Desktop Information
-Node 20.1.8
-KoboldAI
-Brach release
-Model MLewd-ReMM-L2-Chat-20…
RBNXI updated
2 months ago
-
windows 11 won't start due to outdated vite, solved the problem by installing 4.0.4, this allowed me to start but probably broke everything, An error occurred. Please try again.
```
up to date, …
-
**Describe the Issue**
I cannot get the docker container of koboldcpp to detect my cuda installation on the host Eg. nvidia-smi returns always command not found :(.
I'm trying to set everything up…
-
Sorry for my probably newbie questions.
As I understand with current finetuning we teach how model should answer to our questions based on already present knowledge from basic training.
But wha…
-
### Environment
Self-Hosted (Bare Metal)
### System
Google Chrome 121.0.6167.161. Windows 10 Pro. i7-13700K. 3080ti.
### Version
1.11.2
### Desktop Information
node v21.5.0
Staging
KoboldAI
…
-
Google Dreambooth has come to SD but it currently requires 24gb of vram, making it only accessible to people who pay for a server.
As SD itself runs on even 2gb cards now, wouldn't this be the perfec…
-
## TL;DR
It is an really hard problem, an [NP-hard problem](https://en.wikipedia.org/wiki/NP-hardness)...
> The gist is that neovim is just a C project, therefore doesn't link against C++. How…
-
Model: https://huggingface.co/bartowski/DeepSeek-Coder-V2-Lite-Instruct-GGUF
I tested quant Q5_K_M
At the very default koboldcpp_cu12 v1.68, CuBLAS with 0 layers, no flash attention.
Prompt: (p…
-
Maybe this is a dumb question, but why is the limit 512? The model I'm using has a limit that's much higher (vicuna), if not unlimited. If this something hard-coded in the program or could it be modif…
-
https://github.com/LostRuins/lite.koboldai.net/blob/cf69c2b31031d8ff8b47abda8354d0ebed8527bc/index.html#L10530
The code rolls a 1-100 value from `Math.random()` then compares it to the probability …