Text Classification
Transformers
PyTorch
TensorFlow
ONNX
Safetensors
hn
Bengali
Mongolian
xlm-roberta
Text Classification
text-embeddings-inference
Instructions to use seanbenhur/MuLTiGENBiaS with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use seanbenhur/MuLTiGENBiaS with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="seanbenhur/MuLTiGENBiaS")# Load model directly from transformers import AutoTokenizer, AutoModelForSequenceClassification tokenizer = AutoTokenizer.from_pretrained("seanbenhur/MuLTiGENBiaS") model = AutoModelForSequenceClassification.from_pretrained("seanbenhur/MuLTiGENBiaS", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Commit ·
31beafd
1
Parent(s): b908691
Update README.md
Browse files
README.md
CHANGED
|
@@ -19,7 +19,7 @@ widget:
|
|
| 19 |
|
| 20 |
This is a XLM-Align-Base model trained on CoMMA dataset of 12k samples
|
| 21 |
|
| 22 |
-
- This is an extension from our previous paper: [Hypers at ComMA@ICON: Modelling Aggressiveness, Gender Bias and Communal Bias Identification](https://arxiv.org/abs/2112.15417).
|
| 23 |
|
| 24 |
## Example Usage
|
| 25 |
|
|
@@ -49,4 +49,16 @@ if __name__ == "__main__":
|
|
| 49 |
|
| 50 |
### Some concerns
|
| 51 |
- Note: The model is trained on relatively lower samples (i.e 12k) but with mix of four languages Hindi, Bengali, Meitei, and English. It contains both native on codemixed scripts, So the model might perform poorly on many text samples and might not generalize well.
|
| 52 |
-
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 19 |
|
| 20 |
This is a XLM-Align-Base model trained on CoMMA dataset of 12k samples
|
| 21 |
|
| 22 |
+
- This is an extension work from our previous paper: [Hypers at ComMA@ICON: Modelling Aggressiveness, Gender Bias and Communal Bias Identification](https://arxiv.org/abs/2112.15417).
|
| 23 |
|
| 24 |
## Example Usage
|
| 25 |
|
|
|
|
| 49 |
|
| 50 |
### Some concerns
|
| 51 |
- Note: The model is trained on relatively lower samples (i.e 12k) but with mix of four languages Hindi, Bengali, Meitei, and English. It contains both native on codemixed scripts, So the model might perform poorly on many text samples and might not generalize well.
|
| 52 |
+
|
| 53 |
+
|
| 54 |
+
## Bibtex
|
| 55 |
+
|
| 56 |
+
```
|
| 57 |
+
@article{Benhur2021HypersAC,
|
| 58 |
+
title={Hypers at ComMA@ICON: Modelling Aggressiveness, Gender Bias and Communal Bias Identification},
|
| 59 |
+
author={Sean Benhur and Roshan Nayak and Kanchana Sivanraju and Adeep Hande and Subalalitha Chinnaudayar Navaneethakrishnan and Ruba Priyadharshini and Bharathi Raja Chakravarthi6},
|
| 60 |
+
journal={ArXiv},
|
| 61 |
+
year={2021},
|
| 62 |
+
volume={abs/2112.15417}
|
| 63 |
+
}
|
| 64 |
+
```
|