Instructions to use binwang/RSE-BERT-large-10-relations with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use binwang/RSE-BERT-large-10-relations with Transformers:
# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, BertForRSE tokenizer = AutoTokenizer.from_pretrained("binwang/RSE-BERT-large-10-relations") model = BertForRSE.from_pretrained("binwang/RSE-BERT-large-10-relations", device_map="auto") - Notebooks
- Google Colab
- Kaggle
|
Download README.md from binwang/RSE-BERT-large-10-relations: direct link, hf CLI and curl.
- Browser
- Download file 853 Bytes
-
https://huggingface.co/binwang/RSE-BERT-large-10-relations/resolve/main/README.md
- Command line
-
hf download hf://binwang/RSE-BERT-large-10-relations/README.md
-
curl -L -o README.md https://huggingface.co/binwang/RSE-BERT-large-10-relations/resolve/main/README.md
853 Bytes
metadata
tags:
- historical-research
- rse
Historical research checkpoint — RSE
No longer actively maintained. Retained for reproducibility of the original work.
This repository contains one variant of the RSE research models. The repository name identifies the backbone (BERT or RoBERTa), model size (base or large), and experiment variant (STS, USEB, Transfer, or 10-relations). Refer to the original description below for this checkpoint's configuration.
Original model description
The RSE-BERT-large-10-rel is trained with 10 relations including:
- entailment
- contradiction
- neutral
- duplicate_question
- non_duplicate_question
- paraphrase
- same_caption
- qa_entailment
- qa_not_entailment
- same_sent
The BERT-large-uncased model is used as initialization.
It can be used to infer all ten different relations.