Update README.md

README.md

@@ -250,12 +250,23 @@ Minerva-7B-base-v1.0 is a pretrained base model and, therefore, has no moderatio
  -->
 ## The Sapienza NLP Team
 
-* **Riccardo Orlando:** data preprocessing, model training
-* **Pere-Lluis Huguet Cabot:** data preprocessing, vocabulary, evaluation
-* **Luca Moroni:** data curation, data analysis, downstream tasks, evaluation
-* **Simone Conia:** data curation, evaluation, project supervision
-* **Edoardo Barba:** data preprocessing, downstream tasks, project supervision
-* **Roberto Navigli:** project coordinator
+### 🧭 Project Lead and Coordination
+* __Roberto Navigli__: project lead and coordinator of the [FAIR Transversal Project 2](https://fondazione-fair.it/transversal-projects/tp2-vision-language-and-multimodal-challenges/), director of the [Sapienza NLP Group](https://nlp.uniroma1.it), full professor at Sapienza University of Rome; model analysis, evaluation and selection, safety and guardrailing, dialogue.
+
+### 🤖 Model Development
+* __Edoardo Barba__: pre-training, post-training, data analysis, prompt engineering.
+* __Simone Conia__: pre-training, post-training, evaluation, model, and data analysis.
+* __Pere-Lluís Huguet Cabot__: data processing, filtering,g and deduplication, preference modeling.
+* __Luca Moroni__: data analysis, evaluation, post-training.
+* __Riccardo Orlando__: pre-training process and data processing.
+
+#### 👮 Safety and Guardrailing
+* __Stefan Bejgu__: safety and guardrailing.
+* __Federico Martelli__: synthetic prompt generation, model and safety analysis.
+* __Ciro Porcaro__: additional safety prompts.
+* __Alessandro Scirè__: safety and guardrailing.
+* __Simone Stirpe__: additional safety prompts.
+* __Simone Tedeschi__: English dataset for safety evaluation.
 
 ### Special thanks for their support