Summarization
Transformers
PyTorch
bart
text2text-generation
Generated from Trainer
Eval Results (legacy)
Instructions to use cs608/billsum-full-data with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use cs608/billsum-full-data 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="cs608/billsum-full-data")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("cs608/billsum-full-data") model = AutoModelForSeq2SeqLM.from_pretrained("cs608/billsum-full-data", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Download training_args.bin from cs608/billsum-full-data: direct link, hf CLI and curl.
- Browser
- Download file 4.03 kB
-
https://huggingface.co/cs608/billsum-full-data/resolve/main/training_args.bin
- Command line
-
hf download hf://cs608/billsum-full-data/training_args.bin
-
curl -L -o training_args.bin https://huggingface.co/cs608/billsum-full-data/resolve/main/training_args.bin
4.03 kB
- Xet hash:
- 7efc4652d44a39d43ac9ba6d67fbe9e19444cef13eaf817d05ce2ed55f5ab945
- Size of remote file:
- 4.03 kB
- SHA256:
- 7dadfe14e31b03cfe1f390cded739653ca1c176136a7561caa39bd9eacd48ae8
·
Xet efficiently stores Large Files inside Git, intelligently splitting files into unique chunks and accelerating uploads and downloads. More info.