how to add a new multi stage model document

Signed-off-by: Rein Yang <ruiruyang2@gmail.com>

Author: R2-Y

docs/contributing/model/README.md

@@ -1,2 +1,20 @@
 # Adding a New Model
-Stay tuned for guidance on how to add a new model on vLLM-Omni!
+
+This section provides comprehensive guidance on how to add a new model to vLLM-Omni.
+
+## Documentation
+
+- **[Adding a New Model Guide](adding_a_new_model.md)**: Complete step-by-step guide using Qwen3-Omni as an example
+
+The guide covers:
+- Directory structure and organization
+- Implementing stage components (thinker, talker, code2wav)
+- Creating the unified model class
+- Model registration
+- Stage configuration
+- Stage input processors
+- Testing strategies
+
+## Quick Start
+
+For a quick reference, see the [Adding a New Model Guide](adding_a_new_model.md) which walks through the complete implementation of Qwen3-Omni, a multi-stage omni-modality model.