Update README.md

README.md

@@ -24,6 +24,15 @@ Made with exllamav2 0.2.7 with the default dataset. Granite3 models require 0.2.
 Exl2 models can be used with TabbyAPI, Text-Generation-WebUI and some others.  
 Exl2 models require Nvidia RTX on Windows or Nvidia RTX or AMD ROCm GPUs on Linux.  
 
+Just in case if you downloaded the model and it answers only Yes/No, it's [intended behavior](https://github.com/ibm-granite/granite-guardian/tree/main#scope-of-use).  
+It's hardcoded in the model's Jinja2 template that can be viewed in tokenizer_config.json file.  
+By default in chat mode it evaluates if user's or assistant's message is harmful in general sense according to the model's risk definitions.  
+But it allows to choose a different predefined option, to set custom harm definitions or detect risks in RAG or function calling pipelines.  
+If you're using TabbyAPI you can either set risk_name or risk_definition via [template variables](https://github.com/theroyallab/tabbyAPI/wiki/04.-Chat-Completions#template-variables).  
+For example, you can switch to violence detection by adding: ``"template_vars": {"guardian_config": {"risk_name": "violence"}}`` to v1/chat/completions request.  
+For more information refer to Granite Guardian [documentation](https://github.com/ibm-granite/granite-guardian) and its Jinja2 template.
+
+# Original model card
 # Granite Guardian 3.1 2B
 
 ## Model Summary