Update README.md

README.md

@@ -1,18 +1,27 @@
 ---
 license: openrail++
+datasets:
+- ukr-detect/ukr-toxicity-dataset
+language:
+- uk
 ---
 
-Labels:
+## Binary toxicity classifier for Ukrainian
 
-LABEL_1 - toxic speech
+This is the fine-tuned on the [Ukrainian toxicity classification dataset](https://huggingface.co/datasets/ukr-detect/ukr-toxicity-dataset) ["xlm-roberta-base"](https://huggingface.co/xlm-roberta-base) instance. 
 
-LABEL_0 - non-toxic speech
+The evaluation metrics for binary toxicity classification on a test set are: 
 
-How to use: 
+**Precision**: 0.9?
+**Recall**: 0.9?
+**F1**: 0.9?
+
+
+## How to use: 
 
 ```
 from transformers import pipeline
 
 classifier = pipeline("text-classification",
-                       model="ukr-detect/toxicspeech-ukr")
+                       model="ukr-detect/ukr-toxicity-classifier")
 ```