Update app.py

app.py

@@ -4,7 +4,8 @@ import torch
 # Load your model and tokenizer
 model_name = "midrees2806/2Krows_uoe_edu"
 tokenizer = LlamaTokenizer.from_pretrained(model_name)
-model = LlamaForCausalLM.from_pretrained(model_name,torch_dtype=torch.float16)
+model = LlamaForCausalLM.from_pretrained(model_name,torch_dtype=torch.float16,device_map="auto",
+    load_in_4bit=True)
 
 # Define the pipeline
 pipe = pipeline(task="text-generation", model=model, tokenizer=tokenizer)