Update README.md

README.md

@@ -1,3 +1,34 @@
 ---
 license: openrail++
+language:
+- uk
+widget:
+- text: "Ти неймовірна!"
 ---
+
+## Binary toxicity classifier for Ukrainian
+
+This is the fine-tuned on the downstream task ["xlm-roberta-large"](https://huggingface.co/xlm-roberta-large) instance.
+
+The evaluation metrics for binary toxicity classification are: 
+
+**Precision**: 0.9468
+**Recall**: 0.9465
+**F1**: 0.9465
+
+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-large-uk-toxicity')
+model = AutoModelForSequenceClassification.from_pretrained('dardem/xlm-roberta-large-uk-toxicity')
+
+# prepare the input
+batch = tokenizer.encode('Ти неймовірна!', return_tensors='pt')
+
+# inference
+model(batch)
+```