Update app.py

app.py

@@ -30,7 +30,7 @@ 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.bfloat16)
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_8bit=True)
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False