Update README.md

README.md

@@ -23,9 +23,9 @@ Throughout the alignment process, we relied on only approximately 20K human-anno
 This results in a model that is aligned for human chat preferences, improvements in mathematical reasoning, coding and instruction-following, and is capable of generating high quality synthetic data for a variety of use cases.
 
 Under the NVIDIA Open Model License, NVIDIA confirms: 
-Models are commercially usable. 
-You are free to create and distribute Derivative Models. 
-NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
+- Models are commercially usable. 
+- You are free to create and distribute Derivative Models. 
+- NVIDIA does not claim ownership to any outputs generated using the Models or Derivative Models.
 
 ### License: 
 
@@ -309,9 +309,9 @@ Evaluated using the CantTalkAboutThis Dataset as introduced in the [CantTalkAbou
 ### Adversarial Testing and Red Teaming Efforts 
 
 The Nemotron-4 340B-Instruct model underwent extensive safety evaluation including adversarial testing via three distinct methods: 
-[Garak](https://docs.garak.ai/garak), is an automated LLM vulnerability scanner that probes for common weaknesses, including prompt injection and data leakage. 
-[AEGIS](https://arxiv.org/pdf/2404.05993), is a content safety evaluation dataset and LLM based content safety classifier model, that adheres to a broad taxonomy of 13 categories of critical risks in human-LLM interactions.
-Human Content Red Teaming leveraging human interaction and evaluation of the models' responses.
+- [Garak](https://docs.garak.ai/garak), is an automated LLM vulnerability scanner that probes for common weaknesses, including prompt injection and data leakage. 
+- [AEGIS](https://arxiv.org/pdf/2404.05993), is a content safety evaluation dataset and LLM based content safety classifier model, that adheres to a broad taxonomy of 13 categories of critical risks in human-LLM interactions.
+- Human Content Red Teaming leveraging human interaction and evaluation of the models' responses.
 
 ### Limitations