Instructions to use hocuf/4bit with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use hocuf/4bit with Transformers:
# Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("hocuf/4bit", device_map="auto") - Notebooks
- Google Colab
- Kaggle
- Local Apps Settings
- Unsloth Desktop
Download tokenizer.json from hocuf/4bit: direct link, hf CLI and curl.
- Browser
- Download file 17.2 MB
-
https://huggingface.co/hocuf/4bit/resolve/main/tokenizer.json
- Command line
-
hf download hf://hocuf/4bit/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/hocuf/4bit/resolve/main/tokenizer.json
17.2 MB
- Xet hash:
- da070f8626ee36c29d81d14f7a18b0a943ba6477aaa86b433d0f865f98bf8392
- Size of remote file:
- 17.2 MB
- SHA256:
- 6b9e4e7fb171f92fd137b777cc2714bf87d11576700a1dcd7a399e7bbe39537b
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.