Summarization
Transformers
PyTorch
TensorFlow
JAX
TensorBoard
Italian
t5
text2text-generation
italian
sequence-to-sequence
fanpage
ilpost
text-generation-inference
Instructions to use gsarti/it5-large-news-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use gsarti/it5-large-news-summarization 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="gsarti/it5-large-news-summarization")# pip install -U transformers accelerate # Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("gsarti/it5-large-news-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("gsarti/it5-large-news-summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -74,7 +74,7 @@ thumbnail: https://gsarti.com/publication/it5/featured.png
|
|
| 74 |
---
|
| 75 |
# IT5 Large for News Summarization ✂️🗞️ 🇮🇹
|
| 76 |
|
| 77 |
-
This repository contains the checkpoint for the [IT5 Large](https://huggingface.co/gsarti/it5-large) model fine-tuned on news summarization on the [Fanpage](https://huggingface.co/datasets/ARTeLab/fanpage) and [Il Post](https://huggingface.co/datasets/ARTeLab/ilpost) corpora as part of the experiments of the paper [IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation](https://arxiv.org) by [Gabriele Sarti](https://gsarti.com) and [Malvina Nissim](https://malvinanissim.github.io).
|
| 78 |
|
| 79 |
A comprehensive overview of other released materials is provided in the [gsarti/it5](https://github.com/gsarti/it5) repository. Refer to the paper for additional details concerning the reported scores and the evaluation approach.
|
| 80 |
|
|
@@ -103,10 +103,11 @@ If you use this model in your research, please cite our work as:
|
|
| 103 |
|
| 104 |
```bibtex
|
| 105 |
@article{sarti-nissim-2022-it5,
|
| 106 |
-
title={IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation},
|
| 107 |
author={Sarti, Gabriele and Nissim, Malvina},
|
| 108 |
-
journal={ArXiv preprint
|
| 109 |
-
url={
|
| 110 |
-
year={2022}
|
|
|
|
| 111 |
}
|
| 112 |
```
|
|
|
|
| 74 |
---
|
| 75 |
# IT5 Large for News Summarization ✂️🗞️ 🇮🇹
|
| 76 |
|
| 77 |
+
This repository contains the checkpoint for the [IT5 Large](https://huggingface.co/gsarti/it5-large) model fine-tuned on news summarization on the [Fanpage](https://huggingface.co/datasets/ARTeLab/fanpage) and [Il Post](https://huggingface.co/datasets/ARTeLab/ilpost) corpora as part of the experiments of the paper [IT5: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation](https://arxiv.org/abs/2203.03759) by [Gabriele Sarti](https://gsarti.com) and [Malvina Nissim](https://malvinanissim.github.io).
|
| 78 |
|
| 79 |
A comprehensive overview of other released materials is provided in the [gsarti/it5](https://github.com/gsarti/it5) repository. Refer to the paper for additional details concerning the reported scores and the evaluation approach.
|
| 80 |
|
|
|
|
| 103 |
|
| 104 |
```bibtex
|
| 105 |
@article{sarti-nissim-2022-it5,
|
| 106 |
+
title={{IT5}: Large-scale Text-to-text Pretraining for Italian Language Understanding and Generation},
|
| 107 |
author={Sarti, Gabriele and Nissim, Malvina},
|
| 108 |
+
journal={ArXiv preprint 2203.03759},
|
| 109 |
+
url={https://arxiv.org/abs/2203.03759},
|
| 110 |
+
year={2022},
|
| 111 |
+
month={mar}
|
| 112 |
}
|
| 113 |
```
|