Back to all models
fill-mask mask_token: <special1>
Query this model
🔥 This model is currently loaded and running on the Inference API. ⚠️ This model could not be loaded by the inference API. ⚠️ This model can be loaded on the Inference API on-demand.
JSON Output
API endpoint
								$ curl -X POST \
Share Copied link to clipboard

Monthly model downloads

moumeneb1/flaubert-base-cased-ecology_crisis moumeneb1/flaubert-base-cased-ecology_crisis
last 30 days



Contributed by

moumeneb1 Boumadane Abdelmoumene
2 models

How to use this model directly from the 🤗/transformers library:

Copy to clipboard
from transformers import AutoTokenizer, AutoModelWithLMHead tokenizer = AutoTokenizer.from_pretrained("moumeneb1/flaubert-base-cased-ecology_crisis") model = AutoModelWithLMHead.from_pretrained("moumeneb1/flaubert-base-cased-ecology_crisis")


An adapted Flaubert/Flaubert_base-cased model Trained further on a Language modeling Task of unlabeled French tweets used to create the CrisisDataset, The intermediate task of masqued language modeling helped us improve the results on our paper compared to the standard flaubert-base-cased model.

If you use this pretrained model on your work, please cite us as follows 🤗

title = "A three-level classification of French tweets in ecological crises",
journal = "Information Processing & Management",
volume = "57",
number = "5",
pages = "102284",
year = "2020",
issn = "0306-4573",
doi = "",
url = "",
author = "Diego Kozlowski and Elisa Lannelongue and Frédéric Saudemont and Farah Benamara and Alda Mari and Véronique Moriceau and Abdelmoumene Boumadane",
keywords = "Crisis response from social media, Machine learning, Natural language processing, Transfer learning",