-
Idea:
- If folder "koboldcpp_userscripts" exists,
- insert code from all files inside it to user web interface.
This allow user to adjust web interface for it's own needs: for example, make trans…
-
I had to manually set the thread count in the default_threads variable. I don't know if it's something that can be set with an argument and I like it because it helps with stability, but I should be a…
-
Hello. I trying to launch on Ubuntu-22.04
```bash
gpt@gpt:~/koboldcpp$ make LLAMA_OPENBLAS=1
I llama.cpp build info:
I UNAME_S: Linux
I UNAME_P: x86_64
I UNAME_M: x86_64
I CFLAGS: -I. …
-
I've found that with certain models, especially OpenAssistant ones, generation seems to get cut off prematurely if I don't use the --ignore-eos flag, or at least this is my perception. Answers seem to…
-
I have issue in getting openblas/clblast working on macos in version above 1.10. I have both installed through homebrew. When I start server, i get error "Warning: OpenBLAS library file not found. Non…
-
I know that sooner or later it will be done. But I just wanted to play with the model in a convenient interface. And my calculator without speed boost thinks for a very long time.
Maybe it's because…
-
Ubuntu 22.04.2 LTS with Nvidia 3060 ti GPU. CUDA version given by
```
/usr/local/cuda/bin/nvcc --version
nvcc: NVIDIA (R) Cuda compiler driver
Copyright (c) 2005-2022 NVIDIA Corporation
Built on …
-
_This is a feature from llama.cpp that kobold.cpp currently does not support._
The recently released [Bluemoon RP model](https://huggingface.co/reeducator/bluemoonrp-13b) was trained for 4K context…
-
I was able to follow your instructions to download and install this. But how do I use it? Do I need to re-download everything every time I want to use it? Does it only run in the Termux terminal, or i…
-
When launched with `--port [port]` argument, the port number is ignored and the default port 5001 is used instead:
```text
$ ./koboldcpp.exe --port 9000 --stream
[omitted]
Starting Kobold HTTP Se…