Update README.md

README.md

@@ -43,6 +43,12 @@ We applied:
 - Filtering to keep only high-quality reasoning traces (correct answers with proper reasoning)
 - STORM-inspired techniques to enhance comprehensive report generation
 
+### Phase 4: Reinforcement Learning
+
+We trained the model using reinforcement learning
+- UsedDataset: MuSiQue (19k samples)
+- Incorporated our in-house search database (containing Wiki data, Fineweb data, and arXiv data)
+
 ## Performance
 
 | **Benchmark** | **Qwen3-4B** | **Jan-4B** | **WebSailor-3B** | **II-Search-4B** |
@@ -74,13 +80,16 @@ II-Search-4B is designed for:
 
 ## Usage
 
-- LMStudio
+```bash
+vllm serve Intelligent-Internet/II-Search-4B --served-model-name II-Search-4B --tensor-parallel-size 8 --enable-reasoning --reasoning-parser deepseek_r1 --rope-scaling '{"rope_type":"yarn","factor":1.5,"original_max_position_embeddings":98304}' --max-model-len 131072
+```
+- Or you can host the [II-4B-Search-MLX ](https://huggingface.co/Intelligent-Internet/II-Search-4B-MLX/) on your Mac then use LMStudio/ Olama Desktop to use it.
 
 ### Recommended Generation Parameters
 
 ```python
 generate_cfg = {
-    'thought_in_content': True,
+    'top_k': 20,
     'top_p': 0.95,
     'temperature': 0.6,
     'repetition_penalty': 1.1,