Update README.md

README.md

@@ -6,3 +6,20 @@ A Seed-OSS-36B-Instruct (https://huggingface.co/ByteDance-Seed/Seed-OSS-36B-Inst
 **Paper:** Training Proactive and Personalized LLM Agents (https://arxiv.org/pdf/2511.02208)
 
 
+##  Serving with vLLM
+
+This model includes bias terms in attention output projections. To serve correctly:
+
+```bash
+wget https://huggingface.co/sunweiwei/PPP-36B/resolve/main/patch_seed_oss.py
+python -c "import patch_seed_oss" && vllm serve sunweiwei/PPP-36B
+```
+
+Or in Python:
+```python
+import patch_seed_oss  # Load once after downloading
+from vllm import LLM
+
+llm = LLM("sunweiwei/PPP-36B")
+```
+The patch reads the attention_out_bias config parameter to properly initialize the model.