Initial clone with modifications

src/about.py

@@ -131,7 +131,7 @@ TITLE = """<h1 align="center" id="space-title">🚀 ECREAM-LLM Leaderboard 🚀<
 
 # What does your leaderboard evaluate?
 INTRODUCTION_TEXT = """
-<br><br><b>The eCream-LLM leaderboard </b>, developed within <a href='https://ecreamproject.eu/'> the eCream Project </a> (enabling Clinical Research in Emergency and Acute care Medicine), is designed to evaluate Large Language Models (LLMs) on two tasks pertaining to the medical domain. Its distinguishing features are:<b> <br> (i) all tasks are implemented for six languages including English, Italian, Slovak, Slovenian, Polish and Greek; <br> (ii) all tasks are generative, thus allowing for a more natural interaction with LLMs; <br> (iii) all tasks are evaluated against multiple prompts, this way mitigating the model sensitivity to specific prompts and allowing a fairer evaluation.</b>
+<br><br><b>The eCream-LLM leaderboard </b>, developed within <a href='https://ecreamproject.eu/'> the eCream Project </a> (enabling Clinical Research in Emergency and Acute care Medicine), is designed to evaluate Large Language Models (LLMs) on several tasks pertaining to the medical domain. Its distinguishing features are:<b> <br> (i) all tasks are implemented for six languages including English, Italian, Slovak, Slovenian, Polish and Greek; <br> (ii) the leaderboard includes generative tasks, allowing for a more natural interaction with LLMs; <br> (iii) all tasks are evaluated against multiple prompts, this way mitigating the model sensitivity to specific prompts and allowing a fairer evaluation.</b>
 <br><br>**<small>Generative tasks:</small>** <small> 🏷️NER (Named Entity Recognition), 🔗REL (Relation Extraction), 😃RML(CRF RML) </small>
 <br>**<small>Multiple-choice task:</small>** <small>   🏥DIA (CRF Diagnosis), 📝HIS (CRF History)  </small>