Update README.md

README.md

@@ -18,9 +18,14 @@ Rose-2x7B is a Mixure of Experts (MoE) made with the following models using [Mer
 * [maywell/PiVoT-0.1-Starling-LM-RP](https://huggingface.co/maywell/PiVoT-0.1-Starling-LM-RP)
 * [WizardLM/WizardMath-7B-V1.1](https://huggingface.co/WizardLM/WizardMath-7B-V1.1)
 
+```bash
+mergekit-moe mergekit_moe.yaml merge --copy-tokenizer --device cuda --low-cpu-memory
+```
+
 ## 🧩 Configuration
 
-```yamlbase_model: uproai/ros-7b-v1
+```yaml
+base_model: uproai/ros-7b-v1
 experts:
   - source_model: maywell/PiVoT-0.1-Starling-LM-RP
     positive_prompts:
@@ -37,8 +42,7 @@ experts:
     - "solve"
     - "count"
 tokenizer_source: union
-
-#mergekit-moe mergekit_moe.yaml merge --copy-tokenizer --device cuda --low-cpu-memory```
+```
 
 ## 💻 Usage