Update app.py

app.py

@@ -36,8 +36,8 @@ if not torch.cuda.is_available():
 
 
 if torch.cuda.is_available():
-    model_id = "meta-llama/Llama-2-13b-chat-hf"
-    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=True)
+    model_id = "appvoid/palmer-003"
+    model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto", load_in_4bit=False)
     tokenizer = AutoTokenizer.from_pretrained(model_id)
     tokenizer.use_default_system_prompt = False