Update app.py

app.py

@@ -9,12 +9,11 @@ import gradio as gr
 title = "Welcome to Tonic's 🐋🐳Orca-2-13B!"
 description = "You can use [🐋🐳microsoft/Orca-2-13b](https://huggingface.co/microsoft/Orca-2-13b) Or clone this space to use it locally or on huggingface! [Join me on Discord to build together](https://discord.gg/VqTxc76K3u)."
 
-os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:24'
+# os.environ['PYTORCH_CUDA_ALLOC_CONF'] = 'max_split_size_mb:24'
 device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
 model_name = "microsoft/Orca-2-13b"
-model = AutoModelForCausalLM.from_pretrained(model_name)
+model = AutoModelForCausalLM.from_pretrained(model_name, device_map='auto')
 tokenizer = AutoTokenizer.from_pretrained(model_name, use_fast=False,)
-model.to(device)
 
 class OrcaChatBot:
     def __init__(self, model, tokenizer, system_message="You are Orca, an AI language model created by Microsoft. You are a cautious assistant. You carefully follow instructions. You are helpful and harmless and you follow ethical guidelines and promote positive behavior."):