Update README.md

README.md

@@ -25,6 +25,7 @@ llm = Llama.from_pretrained(
   repo_id="abetlen/paligemma-3b-mix-224-gguf",
   filename="*text-model-q4_k_m.gguf",
   chat_handler=chat_handler,
+  n_gpu_layers=-1,
   n_ctx=2048, # n_ctx should be increased to accommodate the image embedding
   n_ubatch=512, # must be large enough to fit image embeddings and text input in a single batch
   n_batch=512