BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension
Paper • 1910.13461 • Published • 6
# pip install -U transformers accelerate
# Load model directly
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("philipp-zettl/bart-large-cnn")
model = AutoModelForSeq2SeqLM.from_pretrained("philipp-zettl/bart-large-cnn", device_map="auto")Quick Links
Model Card for philipp-zettl/bart-large-cnn
Model Details
Model Description
ONNX optimized version of facebook/bart-large-cnn
- Developed by: facebook
- Optimized from model: facebook/bart-large-cnn
Model Sources
- Repository: facebook/bart-large-cnn
- Paper: 1910.13461
- Downloads last month
- 28
Model tree for philipp-zettl/bart-large-cnn
Base model
facebook/bart-large-cnn
# 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="philipp-zettl/bart-large-cnn")