Update app.py

app.py

@@ -78,11 +78,11 @@ tokenizer = AutoTokenizer.from_pretrained(model_name)
 model = AutoModelForCausalLM.from_pretrained(model_name, device_map="auto", trust_remote_code=True)
 
 # Ensure the model is on the GPU
-device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
-model.to(device)
+#device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
+#model.to(device)
 
 # Create Hugging Face Pipeline with the specified model and tokenizer
-hf_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer, device=device)
+hf_pipeline = pipeline("text-generation", model=model, tokenizer=tokenizer)
 
 # LangChain LLM using Hugging Face Pipeline
 llm = HuggingFacePipeline(pipeline=hf_pipeline)