Summarization
Transformers
PyTorch
TensorFlow
JAX
Rust
Safetensors
English
bart
text2text-generation
Eval Results (legacy)
Instructions to use facebook/bart-large-cnn with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use facebook/bart-large-cnn 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="facebook/bart-large-cnn")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("facebook/bart-large-cnn") model = AutoModelForSeq2SeqLM.from_pretrained("facebook/bart-large-cnn") - Inference
- Notebooks
- Google Colab
- Kaggle
Will this act as an abstractive summarizer? (because giving a\extractive results)
#27
by sumanth11 - opened
I came across multiple repositories using this to create a abstractive text summarizer , and I have also tried on multiple datasets. but Its totally performing like a extractive summarizer, no new words or new sentences but just extracting sentences.
Is this normal or am I doing something wrong.
notebook link: https://colab.research.google.com/drive/1SzFTU9u_Xn0yu7m_xgF6GbB3XJdfQuwN?usp=sharing
I am very new to this please help.
I agree with you - had the same challenge so switched to a different model for "Abstractive" summarization.