Update app.py

app.py

@@ -29,7 +29,7 @@ if not torch.cuda.is_available():
 
 if torch.cuda.is_available():
     model_id = "tenyx/Llama3-TenyxChat-70B"
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.float16)
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", torch_dtype=torch.bfloat16)
     # model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False
@@ -121,7 +121,7 @@ chat_interface = gr.ChatInterface(
             minimum=1.0,
             maximum=2.0,
             step=0.05,
-            value=1.,
+            value=1.2,
         ),
     ],
     stop_btn=None,