Instructions to use Danish-summarisation/DanSumT5-pilot with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Danish-summarisation/DanSumT5-pilot with Transformers:
# Use a pipeline as a high-level helper # Warning: Pipeline type "summarization" is no longer supported in transformers v5. # You must load the model directly (see below) or downgrade to v4.x with: # pip install "transformers<5.0.0" from transformers import pipeline pipe = pipeline("summarization", model="Danish-summarisation/DanSumT5-pilot")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("Danish-summarisation/DanSumT5-pilot") model = AutoModelForSeq2SeqLM.from_pretrained("Danish-summarisation/DanSumT5-pilot", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download tokenizer.json from Danish-summarisation/DanSumT5-pilot: direct link, hf CLI and curl.
- Browser
- Download file 2.21 MB
-
https://huggingface.co/Danish-summarisation/DanSumT5-pilot/resolve/main/tokenizer.json
- Command line
-
hf download hf://Danish-summarisation/DanSumT5-pilot/tokenizer.json
-
curl -L -o tokenizer.json https://huggingface.co/Danish-summarisation/DanSumT5-pilot/resolve/main/tokenizer.json
2.21 MB
File too large to display, you can check the raw version instead.