Instructions to use SIRIS-Lab/actytode with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use SIRIS-Lab/actytode with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="SIRIS-Lab/actytode")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("SIRIS-Lab/actytode") model = AutoModelForSequenceClassification.from_pretrained("SIRIS-Lab/actytode", device_map="auto") - Notebooks
- Google Colab
- Kaggle
| license: mit | |
| datasets: | |
| - SIRIS-Lab/actytode | |
| # ACTYTODE (ACtivity TYpe TO DEtect) | |
| This repository provides a `bert-base-multilingual-uncased` model finetuned for ACTYTODE task based on ACTYTODE dataset, which aims at predicting organisation activity type based on the organisation legal status of the European Commission. | |
| The activity type status for organisations are: | |
| * PUB --> Public entity (excluding research and education) | |
| * HES --> Higher education entity | |
| * REC --> Research entity | |
| * PRC --> Private company | |
| * OTH --> Other | |
| ## Training data | |
| ## Evaluation |