Update app_chat.py

app_chat.py

@@ -18,7 +18,7 @@ DESCRIPTION = """\
 """
 
 model_id = "nvidia/Hymba-1.5B-Instruct"
-model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", trust_remote_code=True)
+model = AutoModelForCausalLM.from_pretrained(model_id, device_map="cuda", model_dtype="bfloat16", trust_remote_code=True)
 model.to('cuda')
 model.eval()
 tokenizer = AutoTokenizer.from_pretrained(model_id, trust_remote_code=True)