Update app.py

app.py

@@ -3,11 +3,15 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer, StopStringCriteria, StoppingCriteriaList
 import torch
 
-import torch
+import torch._dynamo
+torch._dynamo.config.suppress_errors = True
+
 import os
 os.system("nvidia-smi")
 print("TORCH_CUDA", torch.cuda.is_available())
 
+
+print("loading model")
 # Load the tokenizer and model
 repo_name = "nvidia/Hymba-1.5B-Instruct"