Add accelerate to requirements

app.py

@@ -10,7 +10,7 @@ tokenizer = AutoTokenizer.from_pretrained(MODEL_NAME, trust_remote_code=True)
 model = AutoModelForCausalLM.from_pretrained(
     MODEL_NAME,
     device_map="auto",
-    trust_remote_code=True  # Allow execution of custom code
+    trust_remote_code=True,  # Allow execution of custom code
     low_cpu_mem_usage=True  # Ensures reduced memory usage
 ).to(device)