Corrected endpoint for png in markdown

README.md

@@ -35,7 +35,7 @@ Fine-tuning was made using QLoRA method on Kaggle GPU P100 with 10000 elements f
 
 Training loss, validation loss, SummaC were chosen as evaluation metrics.
 
-![image/png](https://github.com/H1merka/InternVL2_5-4B-QLoRA-LLM-RussianSummarization/blob/main/Charts.png)
+![image/png](https://raw.githubusercontent.com/H1merka/InternVL2_5-4B-QLoRA-LLM-RussianSummarization/main/Charts.png)
 
 ## License