Update README.md
Browse files
README.md
CHANGED
|
@@ -18,7 +18,11 @@ base_model:
|
|
| 18 |
- FacebookAI/xlm-roberta-large
|
| 19 |
tags:
|
| 20 |
- toxicity
|
|
|
|
| 21 |
---
|
|
|
|
|
|
|
|
|
|
| 22 |
This is an instance of [xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) that was fine-tuned on binary toxicity classification task based on our compiled dataset [textdetox/multilingual_toxicity_dataset](https://huggingface.co/datasets/textdetox/multilingual_toxicity_dataset).
|
| 23 |
|
| 24 |
Firstly, we separated a balanced 20% test set to check the model adequency. Then, the model was fine-tuned on the full data. The results on the test set are the following:
|
|
|
|
| 18 |
- FacebookAI/xlm-roberta-large
|
| 19 |
tags:
|
| 20 |
- toxicity
|
| 21 |
+
new_version: textdetox/xlmr-large-toxicity-classifier-v2
|
| 22 |
---
|
| 23 |
+
|
| 24 |
+
# Multilingual Toxicity Classifier for 9 languages (2024)
|
| 25 |
+
|
| 26 |
This is an instance of [xlm-roberta-large](https://huggingface.co/FacebookAI/xlm-roberta-large) that was fine-tuned on binary toxicity classification task based on our compiled dataset [textdetox/multilingual_toxicity_dataset](https://huggingface.co/datasets/textdetox/multilingual_toxicity_dataset).
|
| 27 |
|
| 28 |
Firstly, we separated a balanced 20% test set to check the model adequency. Then, the model was fine-tuned on the full data. The results on the test set are the following:
|