---
license: openrail++
language:
- uk
widget:
- text: "Ти неймовірна!"
---

Binary toxicity classifier for Ukrainian.

This is the fine-tuned on the downstream task ["xlm-roberta-base"](https://huggingface.co/xlm-roberta-base) instance.

The evaluation metrics are: 

**Precision**: 0.9130
**Recall**: 0.9065
**F1**: 0.9061

The training and evaluation data will be clarified later.

## How to use
```python
from transformers import AutoTokenizer, AutoModelForSequenceClassification

# load tokenizer and model weights
tokenizer = AutoTokenizer.from_pretrained('dardem/xlm-roberta-base-uk-toxicity')
model = AutoModelForSequenceClassification.from_pretrained('dardem/xlm-roberta-base-uk-toxicity')

# prepare the input
batch = tokenizer.encode('Ти неймовірна!', return_tensors='pt')

# inference
model(batch)
```