Downloads · 30 days
5
23% of all-time downloads
Offensive_Darija_MorRoBERTa
otmangi/Offensive_Darija_MorRoBERTa
Offensive_Darija_MorRoBERTa is a machine learning model from otmangi. Use it for the machine learning task on the model card, and read the license before you ship it in a product. The card lists the license as cc.
OffMorRoBERTa is a Transformer-based language model designed to classify comments in the Moroccan dialect as abusive or non-abusive.
All-time downloads
22
Public
Parameters
83.5M
334 MB on disk
Likes
0
Public
Repo makeup
Click a slice to open those files.
.safetensors334 MB · 99%
At a glance
- License
- cc
- Model type
- roberta
- Access
- Public
- Created
- Aug 13, 2025
- Updated
- Aug 14, 2025
- SHA
- 720b4987
Model card
From the Hugging Face model README
Off_MorRoBERTa
Off_MorRoBERTa is a Transformer-based language model designed to classify comments in the Moroccan dialect as abusive or non-abusive.
About Off_MorRoBERTa
Off_MorRoBERTa, developed specifically for the Moroccan dialect, provides an effective approach for detecting abusive content. The model is based on MorRoBERTa, which was fine-tuned on a labeled dataset created for hate speech detection in Moroccan dialect texts.
The dataset used for training was built by aggregating and preprocessing data from publicly available sources, including MDMD, OMCD, and MDOLDD.
Usage
The model weights can be loaded using transformers library by HuggingFace.
from transformers import AutoTokenizer, AutoModel
tokenizer = AutoTokenizer.from_pretrained("otmangi/Offensive_Darija_MorRoBERTa")
model = AutoModel.from_pretrained("otmangi/Offensive_Darija_MorRoBERTa")
Related Paper
For more details about the dataset, methodology, and evaluation, please refer to our paper: https://accentsjournals.org/paperinfo.php?journalPaperId=1809
Contact
For any inquiries, feedback, or requests, please feel free to reach out to :
- Type
- roberta
- License
- cc
- Created
- Aug 13, 2025
- Updated
- Aug 14, 2025