Pi
Pi
> Without knowing how the file was converted, it's hard to determine the cause. I followed [this](https://github.com/antimatter15/alpaca.cpp/issues/13#issuecomment-1474125014) method exactly. I made that file. I followed the same instructions as you,...
> > 30B wouldn't run for me. It gave me an error saying that "tok_embeddings.weight" was the wrong size. > I have the same problem, what is your ram size?...
> Sorry I am a noob, so should I just open PowerShell in the release folder You'll need to pull or re-clone the repository first, if you haven't done so...
> The 30B model produces much worse results. It's also a lot slower. > > Example for the prompt `What's the difference between alpacas and lamas?`: > > 7B: `The...
> I'm using these params and I'm getting fairly short responses too. (using your 30B). > > `sampling parameters: temp = 0.900000, top_k = 420, top_p = 0.900000, repeat_last_n =...
> I've heard that the quantization in llama.cpp has been modified to improve the answer quality issue, but I can't confirm this until a ggml file compatible with the current...
llama.cpp's main.exe. it used to be called chat.exe.
Please take a look at the icon color guidelines [here](https://github.com/leonardssh/vscord/blob/main/ADDING_LANGUAGE.md#color)