Update README.md

README.md

@@ -4,6 +4,17 @@ inference: false
 
 # longchat-7b-16k Model Card
 
+Please use load_model from FastChat or LongChat repo to load the model (or chatting API from FastChat). There is a monkey patch needed to use the model.
+Usage referece:
+
+(LongChat) python3 eval.py --model-name-or-path  lmsys/longchat-7b-16k --task topics 
+
+(FastChat) python3 -m fastchat.serve.cli --model-path lmsys/longchat-7b-16k
+
+Under the hood, the monkey patch is added in:
+
+https://github.com/lm-sys/FastChat/blob/da0641e567cf93756b0978ab5a6b092e96f06240/fastchat/model/model_adapter.py#L429
+
 ## Model details
 
 **Model type:**