jferments

index 0 is out of range for type 'uvm_gpu_chunk_t *[*]'

1

### What is the issue? I am using Ollama on Ubuntu 24.04, and am getting the following error showing up in dmesg: [ 48.005440] ------------[ cut here ]------------ [ 48.005441]...

When I run the code from the example notebook [Zero_shot_image_segmentation_with_CLIPSeg.ipynb](https://github.com/NielsRogge/Transformers-Tutorials/blob/master/CLIPSeg/Zero_shot_image_segmentation_with_CLIPSeg.ipynb): ``` from PIL import Image import requests from transformers import CLIPSegProcessor, CLIPSegForImageSegmentation url = "https://github.com/timojl/clipseg/blob/master/example_image.jpg?raw=true" image = Image.open(requests.get(url, stream=True).raw) processor...

Add aspect ratio bucketing to training scripts

6

**Is your feature request related to a problem? Please describe.** When fine tuning SDXL, images are required to be a fixed size (1024x1024) which involves a lot of cropping that...

Install fails at last step "Install RAM & Tag2Text"

6

I am following install instructions, and am at last step "Install RAM & Tag2Text": > git clone https://github.com/xinyu1205/recognize-anything.git > pip install -r ./recognize-anything/requirements.txt > pip install -e ./recognize-anything/ And when...

Trying to run with half precision gives error "RuntimeError: "LayerNormKernelImpl" not implemented for 'Half'"

1

I am trying to follow the instructions for bark from the [HuggingFace Bark Docs](https://huggingface.co/docs/transformers/en/model_doc/bark) and I saw the part where it said that I can reduce memory footprint by running...

[Feat]: Utilize multiple GPUs and increase thread count during image captioning

4

### Describe your use-case. I recently was using OneTrainer UI to auto-caption ~750k images using WD14 tagger. I have a dual GPU machine, but it was only utilizing one of...