Instructions to use Faradaylab/aria-doc with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use Faradaylab/aria-doc with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("question-answering", model="Faradaylab/aria-doc")# Load model directly from transformers import AutoTokenizer, AutoModelForQuestionAnswering tokenizer = AutoTokenizer.from_pretrained("Faradaylab/aria-doc") model = AutoModelForQuestionAnswering.from_pretrained("Faradaylab/aria-doc") - Notebooks
- Google Colab
- Kaggle
| license: gpl | |
| datasets: | |
| - etalab-ia/piaf | |
| language: | |
| - fr | |
| - en | |
| metrics: | |
| - accuracy | |
| pipeline_tag: question-answering | |
| tags: | |
| - biology | |
| - legal | |
| - French | |
| - France | |
| Aria Doc is a model we created for Documents Q/A. It has been trained on a high quality dataset with over 3000 rows of context,question and answers from Etalab. | |
| You can find the dataset used for training here https://huggingface.co/datasets/etalab-ia/piaf . Aria Doc has a great performance in French related Q/A and data extraction in french language. | |
| - | |
| Aria Doc est un modèle que nous avons créé pour l'extraction de données sur des documents et les besoins de questions/réponses sur des données spécifiques. Le modèle a été entraîné sur plus de 3000 exemples fournis par le Dataset PIAF. Les performances d'Aria Doc sont optimales en Français. |