GPTQ-for-LLaMa VS SillyTavern

git clone https://github.com/oobabooga/GPTQ-for-LLaMa

If you're using the model directly from ehartford, that one hasn't been quantized. Try using the GPTQ quantized version here, and use this fork of GPTQ-for-LLaMa. Load in 4-bit with --wbits 4

This worked for me on Ubuntu. If you want to use the CUDA branch instead of triton, do the same steps except clone this GPTQ-for-LLaMa fork and run python setup_cuda.py install

If you don't have triton and you use AutoGPTQ you're gonna notice a huge slow down compared to the old GPTQ-for-LLaMA cuda branch. For me AutoGPTQ gives me a whopping 1 token per second compared to the old GPTQ that gives me a decent 9 tokens per second.. both times I used a same sized model. (I think the slowdown is due to AutoGPTQ using the newer cuda branch which is much slower than the old one)

Are you using a later version of GPTQ-for-LLaMa? If so, go to ooba's CUDA fork (https://github.com/oobabooga/GPTQ-for-LLaMa). That's what I made it in and it definitely works with that. And that's what's included in the one-click-installers.

This usually happens when using models that conflict with your GPTQ installation. You should be using this fork: https://github.com/oobabooga/GPTQ-for-LLaMa. If you did the manual installation wrong, use the one click installer instead.

cd text-generation-webui # wherever you have it installed mkdir -p repositories cd repositories git clone https://github.com/oobabooga/GPTQ-for-LLaMa -b cuda GPTQ-for-LLaMa cd GPTQ-for-LLaMa python setup_cuda install

I'm on GPTQ for LLaMA folder under repositories says it's pointed at https://github.com/oobabooga/GPTQ-for-LLaMa.git. But I've run through the instructions and also applied the monkey patch to train and apply 4 bit lora which may come into play. No idea.

git clone https://github.com/oobabooga/GPTQ-for-LLaMa.git -b cuda

Right, but it's certainly easier for people who might not even know what "API" stands for, and that's quite nifty. As far as self-hosted frontends go, I can personally recommend SillyTavern[1] in the browser, ChatterUI[2] on mobile, and ShellGPT[3] for CLI. LobeChat looks pretty cool, though! I'll definitely check it out.

[1] https://github.com/SillyTavern/SillyTavern

[2] https://github.com/Vali-98/ChatterUI

[3] https://github.com/TheR1D/shell_gpt

I don't think there is any enumeration for {{char}} macros. Here is some good discussion on the subject.

As for SillyTavern, you need the main SillyTavern frontend and SillyTavern-extras (for TTS, STT, etc.) They're pretty easy to install. SillyTavern connects to oobabooga and SillyTavern-extras via API.

Finally, no matter what backend I use, I need it to be compatible with my power-user frontend, SillyTavern. That way I always use the same UI, with the characters I created and extensions I want, e. g. web search, XTTS text-to-speech and Whisper speech recognition for real-time voice chat - and all of that local!

SillyTavern v1.10.5 frontend (not the latest as I don't want to upgrade mid-test)