Update README.md

README.md

@@ -53,6 +53,7 @@ The **Lumo-DeepSeek-R1-8B** model is a fine-tuned version of DeepSeek-R1-Distill
 ### **Training Workflow**
 The model was fine-tuned using parameter-efficient methods with **LoRA** to adapt to the Solana-specific domain. Below is a visualization of the training process:
 
+```mermaid
 graph TD
     %% Base Model Section
     A[Base Model: DeepSeek-R1-Distill-Llama-8B]
@@ -103,6 +104,7 @@ graph TD
     
     class B,C,D,E config;
     class F highlight;
+```
 
 ### **Dataset Sources**
 The dataset comprises curated documentation, cookbooks, and API references from the following sources: