Instructions to use digit82/kobart-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use digit82/kobart-summarization with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("digit82/kobart-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("digit82/kobart-summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download pytorch_model.bin from digit82/kobart-summarization: direct link, hf CLI and curl.
- Browser
- Download file 496 MB
-
https://huggingface.co/digit82/kobart-summarization/resolve/main/pytorch_model.bin
- Command line
-
hf download hf://digit82/kobart-summarization/pytorch_model.bin
-
curl -L -o pytorch_model.bin https://huggingface.co/digit82/kobart-summarization/resolve/main/pytorch_model.bin
496 MB
- Xet hash:
- ab7dde52a9e897043d9002eeb6d1507cef0b22268bd245af0c9308c0799c6114
- Size of remote file:
- 496 MB
- SHA256:
- 88bc3ed20982c5215bd4df35b0046e9a21a62703cecc637d59997137268899f1
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.