supportend

It's the same on my 8 core system, 6 threads result in more speed. I think, this is normal.

See in the upper right of the web gui, there you should be able to set the threads,

``` ./main --help --log-disable Disable trace logs --log-file Specify a log filename (without extension) ```

Under Linux you could create an alias: `alias llama='./yourdirectory/main --log-disable'` But i never tried it. A script in the llama.cpp directory could do the same. And sure, you could change...

For any commandline program i look for possible options and adjust them to my needs, because the defaults are optimal not often for my use cases. Sometimes i disable logging,...

I got these _mm256_fmadd_ps errors in VirtualBox too. In my case i changed this in the Makefile: ``` ifeq ($(UNAME_M),$(filter $(UNAME_M),x86_64 i686 amd64)) # Use all CPU extensions that are...

I tested 13B and 30B without problems. Just download the models and start the program with the correct file, e.g.: `-m ggml-alpaca-30b-q4.bin`

Download of the 30B Model: https://huggingface.co/Pi3141/alpaca-lora-30B-ggml/tree/main 4_1 does not work for me, i use the ggml-model-q4_0.bin file and renamed it to ggml-alpaca-30b-q4.bin. It's the same file, that was downloaded inside...

I think, this is it: https://huggingface.co/Pi3141/alpaca-lora-13B-ggml/tree/main again 4_0 file. There is a native version too on the site. But i dit not download a 4_1 file or the.