Instructions to use HiTZ/mdeberta-expl-extraction-multi with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use HiTZ/mdeberta-expl-extraction-multi with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("token-classification", model="HiTZ/mdeberta-expl-extraction-multi")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("HiTZ/mdeberta-expl-extraction-multi") model = AutoModelForQuestionAnswering.from_pretrained("HiTZ/mdeberta-expl-extraction-multi") - Notebooks
- Google Colab
- Kaggle
Update README.md
Browse files
README.md
CHANGED
|
@@ -48,7 +48,7 @@ which includes English, French, Italian and Spanish.
|
|
| 48 |
|
| 49 |
## Performance
|
| 50 |
|
| 51 |
-
The model scores **74.64 F1 partial match** (as defined in [SQuAD extractive QA task](https://huggingface.co/datasets/rajpurkar/squad_v2) averaged across the 4 languages.
|
| 52 |
|
| 53 |
<!--<img src="https://raw.githubusercontent.com/hitz-zentroa/multilingual-abstrct/main/resources/multilingual-abstrct-results.png" style="width: 75%;"> -->
|
| 54 |
|
|
|
|
| 48 |
|
| 49 |
## Performance
|
| 50 |
|
| 51 |
+
The model scores **74.64 F1 partial match** (as defined in [SQuAD extractive QA task](https://huggingface.co/datasets/rajpurkar/squad_v2)) averaged across the 4 languages.
|
| 52 |
|
| 53 |
<!--<img src="https://raw.githubusercontent.com/hitz-zentroa/multilingual-abstrct/main/resources/multilingual-abstrct-results.png" style="width: 75%;"> -->
|
| 54 |
|