readme : simplify server command

Based on https://github.com/ggml-org/llama.cpp/discussions/15396#discussioncomment-14154375 we can simply omit this CLI arg - it defaults to `auto`

README.md

@@ -7,7 +7,7 @@ base_model:
 Recommended way to run this model:
 
 ```sh
-llama-server -hf ggml-org/gpt-oss-20b-GGUF -c 0 -fa --jinja --reasoning-format auto
+llama-server -hf ggml-org/gpt-oss-20b-GGUF -c 0 -fa --jinja
 
 # Then, access http://localhost:8080
 ```