Subarasheese

Another workaround for this would be some sort of Windows exe hack where it forces the setups to install into a fake location without really rendering the GUI and then...

I can confirm this also happened on my end. 512x512 images, Learning rate 0.000005, HN layer structure 1, 2, 1 . Additionally, when I started to retrain it, I lost...

> Everyone who's getting this, do you have dropout enabled? Would be nice to clarify whether that's the issue. No, it is using the default settings (disabled). I am also...

> I can confirm this also happened on my end. > > 512x512 images, Learning rate 0.000005, HN layer structure 1, 2, 1 . > > Additionally, when I started...

> use another front end like tavern or sillytavern, etc. Is there a guide that tells me how to load a character from CLI parameters? Because I am building a...

On the API code, I am doing something like this: ``` # Generation parameters # Reference: https://huggingface.co/docs/transformers/main_classes/text_generation#transformers.GenerationConfig params = {'max_new_tokens': 1025, 'seed': -1.0, 'temperature': 0.7, 'top_p': 0.5, 'top_k': 40, 'typical_p':...

Yes, the title of the thread is a question since I did not know for sure this feature was possible, it seems it isn't, so I think it's valid to...

@tensiondriven Before closing, can you create an issue suggesting the feature? It is counterproductive to close issues that bring valid discussion points just because they don't fit an expected issue...

Unfortunately, installing scikit-learn and scipy did not fix this problem in my case. ``` Traceback (most recent call last): File "/home/myuser/mms/fairseq/examples/speech_recognition/new/infer.py", line 21, in from examples.speech_recognition.new.decoders.decoder_config import ( File "/home/myuser/mms/fairseq/examples/speech_recognition/__init__.py",...

> @unk1911 but if you do that you won't have the CUDA extension and it will be horribly slow. > > Please try the following. In the line where it...