EdinburghNLP/xsum
Viewer • Updated • 227k • 33.8k • 145
How to use praf-choub/bart-mofe-rl-xsum 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="praf-choub/bart-mofe-rl-xsum") # Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("praf-choub/bart-mofe-rl-xsum")
model = AutoModelForSeq2SeqLM.from_pretrained("praf-choub/bart-mofe-rl-xsum")Citation
@article{DBLP:journals/corr/abs-2110-07166,
author = {Prafulla Kumar Choubey and
Jesse Vig and
Wenhao Liu and
Nazneen Fatema Rajani},
title = {MoFE: Mixture of Factual Experts for Controlling Hallucinations in
Abstractive Summarization},
journal = {CoRR},
volume = {abs/2110.07166},
year = {2021},
url = {https://arxiv.org/abs/2110.07166},
eprinttype = {arXiv},
eprint = {2110.07166},
timestamp = {Fri, 22 Oct 2021 13:33:09 +0200},
biburl = {https://dblp.org/rec/journals/corr/abs-2110-07166.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}