Downloads · 30 days
76
32% of all-time downloads
recommendor-bert
adit-negi/recommendor-bert
recommendor-bert is a sentence similarity model from adit-negi. Use it when you need a score for how close two texts are. It is set up for transformers. The card lists the license as openrail.
Recommendor-bert is a pre-trained language model to generate embeddings for research papers. It is pre-trained on a powerful signal of document-level relatedness: Arxiv tags, domains, citations, conferences, and co-au…
All-time downloads
236
Public
Repo size
879 MB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin440 MB · 100%
At a glance
- Task
- Sentence Similarity
- Library
- transformers
- License
- openrail
- Model type
- bert
- Access
- Public
- Created
- Apr 18, 2023
- Updated
- Apr 18, 2023
- SHA
- db452585
Model card
From the Hugging Face model README
Recommendor-bert is a pre-trained language model to generate embeddings for research papers. It is pre-trained on a powerful signal of document-level relatedness: Arxiv tags, domains, citations, conferences, and co-authors. Recommendor-bert is built with the primary motivation of generating recommendations for research papers.
The model is finetuned using allenai/scibert_scivocab_uncased as the base model and a triplet loss function.
dataset: https://www.kaggle.com/datasets/Cornell-University/arxiv
- Task
- Sentence Similarity
- Library
- transformers
- Type
- bert
- License
- openrail
- Languages
- en
- Created
- Apr 18, 2023
- Updated
- Apr 18, 2023