Downloads · 30 days
14.7K
0% of all-time downloads
specter
allenai/specter
specter is a feature extraction model from allenai. Use it when you need embeddings to search or compare text. It is set up for transformers. The card lists the license as apache-2.0.
SPECTER is a pre-trained language model to generate document-level embedding of documents. It is pre-trained on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language…
All-time downloads
11.9M
Public
Repo size
2.6 GB
Likes
65
Public
Repo makeup
Click a slice to open those files.
.h5440 MB · 33%
At a glance
- Task
- Feature Extraction
- Library
- transformers
- License
- apache-2.0
- Model type
- bert
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Oct 18, 2023
- SHA
- 81cbfb43
Datasets
Model card
From the Hugging Face model README
SPECTER
SPECTER is a pre-trained language model to generate document-level embedding of documents. It is pre-trained on a powerful signal of document-level relatedness: the citation graph. Unlike existing pretrained language models, SPECTER can be easily applied to downstream applications without task-specific fine-tuning.
If you're coming here because you want to embed papers, SPECTER has now been superceded by SPECTER2. Use that instead.
Paper: SPECTER: Document-level Representation Learning using Citation-informed Transformers
Original Repo: Github
Evaluation Benchmark: SciDocs
Authors: Arman Cohan, Sergey Feldman, Iz Beltagy, Doug Downey, Daniel S. Weld
- Task
- Feature Extraction
- Library
- transformers
- Type
- bert
- License
- apache-2.0
- Languages
- en
- Hf Inference
- live
- Created
- Mar 2, 2022
- Updated
- Oct 18, 2023