Update app.py

app.py

@@ -111,9 +111,9 @@ def respond(
     print(f"Processor: {uname.processor}")
 
 # GPU Information
-gpu_stats = gpustat.GPUStatCollection.new_query()
-for gpu in gpu_stats:
-    print(f"GPU: {gpu.name}  Mem Free: {get_size(gpu.memory_free)}  Mem Used: {get_size(gpu.memory_used)}  Mem Total: {get_size(gpu.memory_total)}")
+    gpu_stats = gpustat.GPUStatCollection.new_query()
+    for gpu in gpu_stats:
+        print(f"GPU: {gpu.name}  Mem Free: {get_size(gpu.memory_free)}  Mem Used: {get_size(gpu.memory_used)}  Mem Total: {get_size(gpu.memory_total)}")
     messages = [{"role": "user", "content": "Hello, how are you?"}]
     input_ids = tokenizer.apply_chat_template(messages, tokenize=True, add_generation_prompt=True, return_tensors="pt").to('cuda')
 ## <BOS_TOKEN><|START_OF_TURN_TOKEN|><|USER_TOKEN|>Hello, how are you?<|END_OF_TURN_TOKEN|><|START_OF_TURN_TOKEN|><|CHATBOT_TOKEN|>