minipasila
minipasila
> > Note that the "Tuned" versions need to be prompted like: > > ``` > > > > (Describe the AI chatbot here) > > > > (Place your...
Does the same thing with emojis as shown [here](https://github.com/oobabooga/text-generation-webui/pull/1846#issuecomment-1537163824).
> I think that his fixes this issue [d183c7d](https://github.com/oobabooga/text-generation-webui/commit/d183c7d29ecd37cb12411aad50d089933dc7387d) (credits to @matatonic for the idea) > > If not please let me know. It seems to work on GPTQ and...
Would it be possible for it to also show the generated text with the voice? Another thing I noticed is that if you use "Impersonate" it will just give the...
--verbose kind of works but it won't show the most recent generation, only the whole prompt that was entered.
Thanks, I managed to somehow make it work.
Basically you have to download these 2 dll files from [here.](https://github.com/DeXtmL/bitsandbytes-win-prebuilt) then you move those files into `anaconda3\env\textgen\Lib\site-packages\bitsandbytes` (assuming you're using conda) after that you have to edit one file...
> torch.cuda.OutOfMemoryError: CUDA out of memory. Tried to allocate 160.00 MiB. GPU 0 has a total capacity of 16.00 GiB of which 0 bytes is free. Of the allocated memory...
> RuntimeError: CUDA error: no kernel image is available for execution on the device Compile with to enable device-side assertions.TORCH_USE_CUDA_DSA Ok this is a different error.. so uhh you probably...
this looks interesting https://github.com/oobabooga/text-generation-webui/discussions/932#discussion-5059588