Thomas2419
Thomas2419
### 🐛 Describe the bug After getting Training working in #2204 The loss value even went down during training but my output after using the sampling script and the default...
### 🐛 Describe the bug This bug occurs when trying to train using the train_collossalai.yaml ─────────────────────────────── Traceback (most recent call last) ────────────────────────────────╮ │ /media/thomas/108E73348E731208/Users/Thoma/Desktop/dndiffusion/ColossalAI/examples/images/diffus │ │ ion/main.py:804 in │ │...
### 🐛 Describe the bug Issue #2204 while the main issue was solved the other that cropped up and was marked closed by pull request #2356 seemed to be a...
### 🐛 Describe the bug The entire training process and everything worked, then i got through installing bitsandbytes, but as i try to sample i get an error message. I've...
Hello! I was finetuning from the pretrained_flant5xl and pretrained_opt2.7b models, much to my surprise the flant5xl model is excelling at creating correct labels, as my captions are actually a string...
I get this error when trying to continue to finetune a classifier model or when trying to use a finetuned classifier model to finetune the main model. main() File "scripts/classifier_train_stable.py",...
### Describe the bug I have a standard huggingface private space built on the template text to image under gradio. I am able to successfully use the new SSE and...
Hello! Thank you for the great work! The title says it all I was wondering if you were open to/ had plans release the checkpoints for the open image trained...
### Description Please let me make links in inline mode without ruining the format when they're to other affine docs using the create linked doc. So when you create a...
I've done some digging, assuming I've read this correctly, static features currently are entirely uninformative and useless. Categoricals get turned into numerics, if said value is the same across the...