Instructions to use jordypg/PEGembed with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use jordypg/PEGembed 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="jordypg/PEGembed")# pip install -U transformers accelerate # Load model directly from transformers import AutoModel model = AutoModel.from_pretrained("jordypg/PEGembed", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from jordypg/PEGembed: direct link, hf CLI and curl.
- Browser
- Download file 690 Bytes
-
https://huggingface.co/jordypg/PEGembed/resolve/main/README.md
- Command line
-
hf download hf://jordypg/PEGembed/README.md
-
curl -L -o README.md https://huggingface.co/jordypg/PEGembed/resolve/main/README.md
690 Bytes
metadata
license: apache-2.0
language:
- en
metrics:
- meteor
- bertscore
- rouge
library_name: transformers
pipeline_tag: summarization
tags:
- medical
- biomedical
- scientific_papers
- PEGASUS
Extractive summarization, followed by abstractive summmarization. Extractive summarization performed via Top-K Sentence Cosine, in which the cosine similarity of sentence embeddings are compared. Abstractive summarization comes from the PEGASUS-X model, fine-tuned on Top-K Sentence Cosine summaries of papers from the eLife dataset. See attached paper for further details.
Implemented for graduate course COSC-685 Advanced NLP, in collaboration with Zhiheng Wang, Ahmed Jaafar, and Jiarui Liu.