Update README.md

README.md

@@ -12,7 +12,9 @@ inference: false
 
 ## Model Description
 
-CyberAgentLM2 is a decoder-only language model pre-trained on the 1.3T tokens of publicly available Japanese and English datasets.
+CyberAgentLM2 is a decoder-only language model pre-trained on the 1.3T tokens of publicly available Japanese and English datasets.  
+
+Variant: [CyberAgentLM2-Chat](https://huggingface.co/cyberagent/calm2-7b-chat)
 
 ## Requirements
 - transformers >= 4.34.1