olivbrau
olivbrau
Yes, I was wrong, it is early stopping. Since there is no early stopping possible with Gradient Tree Boost, I thought that OnlineRegression could let the user to make his...
That would be very nice, and very useful !
Thanks for your answer. Indeed, it is not an issue of your plugin. As you say, I reordered the layers, and it works well, but I'm not sure the best...
In fact, the release of 23 Nov is much bigger than the releases of december. But I've tried and still get another error : > CUDA error: the provided PTX...
Thanks for your answer. I have just discovered this amazing feature (Parser). I will have a look. However, since the textarea is locked during parsing, the Parser must be fast...
Thanks, the perl example is great. However, i wonder if taking the risk of waiting at max 10 sec is dangerous or not. I'm sure that the perl parser is...
I also noticed that, but have not yet found bad result : my images are correct. May be it is only a simple error in % calculation ? (because of...
I've tried both the GPU from the CPU and the NVIDIA GPU, it is the same : on the CPU the image is black and on the GPU the image...
Hi, with quantized files from https://huggingface.co/jayn7/Z-Image-Turbo-GGUF/tree/main it works fine for me ! But the gguf files are much bigger than those proposed by leejet. (+1 GB) Is there a good...
I've tried with a slightly larger negative prompt, and it worked. So I think there is a kind of limit in the nb token before the bug arise.