Instructions to use ELiRF/NASES with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use ELiRF/NASES 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="ELiRF/NASES")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("ELiRF/NASES") model = AutoModelForSeq2SeqLM.from_pretrained("ELiRF/NASES", device_map="auto") - Notebooks
- Google Colab
- Kaggle
José Ángel González commited on
Commit ·
0121c8c
1
Parent(s): d9bae58
Update README.md
Browse files
README.md
CHANGED
|
@@ -10,4 +10,4 @@ widget:
|
|
| 10 |
|
| 11 |
News Abstractive Summarization for Spanish (NASES) is a Transformer encoder-decoder model, with the same hyper-parameters than BART, to perform summarization of Spanish news articles. It is pre-trained on a combination of several self-supervised tasks that help to increase the abstractivity of the generated summaries. Four pre-training tasks have been combined: sentence permutation, text infilling, Gap Sentence Generation, and Next Segment Generation. Spanish newspapers, and Wikipedia articles in Spanish were used for pre-training the model (21GB of raw text -8.5 millions of documents-).
|
| 12 |
|
| 13 |
-
NASES is finetuned for the summarization task on 1.802.919
|
|
|
|
| 10 |
|
| 11 |
News Abstractive Summarization for Spanish (NASES) is a Transformer encoder-decoder model, with the same hyper-parameters than BART, to perform summarization of Spanish news articles. It is pre-trained on a combination of several self-supervised tasks that help to increase the abstractivity of the generated summaries. Four pre-training tasks have been combined: sentence permutation, text infilling, Gap Sentence Generation, and Next Segment Generation. Spanish newspapers, and Wikipedia articles in Spanish were used for pre-training the model (21GB of raw text -8.5 millions of documents-).
|
| 12 |
|
| 13 |
+
NASES is finetuned for the summarization task on 1.802.919 (document, summary) pairs from the Dataset for Automatic summarization of Catalan and Spanish newspaper Articles (DACSA).
|