Instructions to use amd-shark/sdxl-quant-int8 with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use amd-shark/sdxl-quant-int8 with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("amd-shark/sdxl-quant-int8", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download quant_param.json from amd-shark/sdxl-quant-int8: direct link, hf CLI and curl.
- Browser
- Download file 85.1 MB
-
https://huggingface.co/amd-shark/sdxl-quant-int8/resolve/main/quant_param.json
- Command line
-
hf download hf://amd-shark/sdxl-quant-int8/quant_param.json
-
curl -L -o quant_param.json https://huggingface.co/amd-shark/sdxl-quant-int8/resolve/main/quant_param.json
85.1 MB
- Xet hash:
- c99e7ed1045036738725b5823c693e6457a71b8065d14e769f34872f40669004
- Size of remote file:
- 85.1 MB
- SHA256:
- fbc5f010261abb44cf5c149fc1471cb6cfc272d4c5e94cfdbfd80c9f9d52eb39
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.