Updade devfinition

added serbian version, add HTML link

app.py

@@ -20,11 +20,18 @@ iface = gr.Interface(
     outputs=[gr.outputs.Label(num_top_classes=3), "text"],
     title="Sentiment Analysis for Serbian",
     description="""
+    Ovaj alat vrši analizu sentimenta na uneseni tekst koristeći model obučen na definicijama srpskog rečnika. 
+    Model je prvobitno bio prethodno obučen na <a href='https://huggingface.co/JeRTeh/sr-gpt2-large' target='_blank'>sr-gpt2-large modelu Mihaila Škorića</a>, 
+    a potom je bio usavršen na odabranim definicijama iz srpskog WordNeta. Molimo vas da ograničite unos na 300 tokena. 
+    Izlazi predstavljaju pozitivne (POS), negativne (NEG) i objektivne (OBJ) ocene sentimenta.
+
     This tool performs sentiment analysis on the input text using a model trained on Serbian dictionary definitions. 
-    The pretrained model [sr-gpt2-large model by Mihailo Škorić](https://huggingface.co/JeRTeh/sr-gpt2-large), 
-    was fine-tuned on selected definitions from the Serbian WordNet. Please limit the input to 300 tokens. 
+    The model was initially pretrained on the <a href='https://huggingface.co/JeRTeh/sr-gpt2-large' target='_blank'>sr-gpt2-large model by Mihailo Škorić</a>, 
+    then fine-tuned on selected definitions from the Serbian WordNet. Please limit the input to 300 tokens. 
     The outputs represent the Positive (POS), Negative (NEG), and Objective (OBJ) sentiment scores.
     """,
+,
+,
     examples=[
         ["osoba koja ne prihvata nove ideje"],
         ["intenzivna ojađenost"],