Instructions to use thors/mt5-base-icelandic-summarization with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use thors/mt5-base-icelandic-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="thors/mt5-base-icelandic-summarization")# Load model directly from transformers import AutoTokenizer, AutoModelForSeq2SeqLM tokenizer = AutoTokenizer.from_pretrained("thors/mt5-base-icelandic-summarization") model = AutoModelForSeq2SeqLM.from_pretrained("thors/mt5-base-icelandic-summarization", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -96,9 +96,11 @@ This is Google's [mT5 base](https://huggingface.co/google/mt5-base) model fine-t
|
|
| 96 |
|
| 97 |
# Citation
|
| 98 |
```
|
| 99 |
-
@inproceedings{
|
| 100 |
title={Abstractive Text Summarization for Icelandic},
|
| 101 |
author={Sverrisson, {\TH}{\'o}r and Einarsson, Hafsteinn},
|
| 102 |
-
booktitle={
|
|
|
|
|
|
|
| 103 |
}
|
| 104 |
```
|
|
|
|
| 96 |
|
| 97 |
# Citation
|
| 98 |
```
|
| 99 |
+
@inproceedings{sverrisson2023abstractive,
|
| 100 |
title={Abstractive Text Summarization for Icelandic},
|
| 101 |
author={Sverrisson, {\TH}{\'o}r and Einarsson, Hafsteinn},
|
| 102 |
+
booktitle={Proceedings of the 24th Nordic Conference on Computational Linguistics (NoDaLiDa)},
|
| 103 |
+
pages={17--31},
|
| 104 |
+
year={2023}
|
| 105 |
}
|
| 106 |
```
|