C00reNUT
C00reNUT
> The latest version of Transformers now explicitly has Python exporting, which removes one of the annoying parts: https://huggingface.co/transformers/serialization.html#onnx-onnxruntime > > However, a bunch of generation is tied explicitly to...
> Your total tokens number in positive and negative prompt must be less than 75, or else you get this. I'm not sure that's the problem, I have done some...
There are definitely more of them. For me even basic {cat|dog} switching didn't function well when using https://github.com/ThereforeGames/unprompted
Same issue with Neko-Institute-of-Science_LLaMA-13B-4bit-128g on Ubuntu and Nvidia. Regardless of the settings the model produces repetitive random noise.
https://github.com/tarepan/SpeechMOS
@a-r-r-o-w Do you think this would work with xl models?
Thank you for the clarification. Just one more thing, I am asking because I would like to use the train_ voices > This repo comes with several pre-packaged voices. Voices...
> FYI: LibriTTS and HiFiTTS datasets were used to train Tortoise. If you are looking for license-free voices that will work very well with this program, use one of those....
> The PEFT code needs to be adapted to make better use of accelerate. I think there are some examples of how to do it in the [huggingface/peft repo](https://github.com/huggingface/peft) but...
I get the same error, while following the install instructions and running any of `python RPG.py --demo` or `python RPG.py --user_prompt 'A blonde hair girl with black suit and white...