Update app.py

app.py

@@ -1,12 +1,12 @@
 from vllm import LLM, SamplingParams
 
-# Initialize the LLM (use your correct model ID)
-llm = LLM(model="Tann-dev/sex-chat-dirty-girlfriend")
+# Initialize the LLM with CPU-only mode
+llm = LLM(model="Tann-dev/sex-chat-dirty-girlfriend", device="cpu")
 
-# Set up sampling parameters (you can adjust these as needed)
+# Set up sampling parameters
 sampling_params = SamplingParams(temperature=0.7, max_tokens=50)
 
-# Define a prompt to generate text from
+# Define a prompt to generate text
 prompt = "Hello, how can I help you?"
 
 # Generate text from the model