Update README.md

README.md

@@ -22,7 +22,7 @@ cd graph-preflexor-grpo
 
 Training run ORPO, then Graph-GRPO:
 
-```python
+```bash
 python ./src/run_orpo_graph.py
 --base_model Qwen/Qwen3-8B
 --dataset lamm-mit/graph_reasoning_1K
@@ -37,13 +37,13 @@ python ./src/run_orpo_graph.py
 
 Test warm-start model:
 
-```python
-python ./src/test_model.py --model ./orpo-graph_v40
+```bash
+python ./src/test_model.py --model ./orpo-graph
 ```
 
 Graph-GRPO phase: 
 
-```python
+```bash
 python ./src/run_grpo_graph.py
 --base_model_dir lamm-mit/orpo-graph
 --dataset lamm-mit/graph_reasoning_1K