Update README.md

README.md

@@ -101,6 +101,9 @@ Evaluation considered narrative coherence, contextual relevance, and creativity
 The model was evaluated using ROUGE scores (ROUGE-1, ROUGE-2, and ROUGE-L) to measure n-gram overlap between generated text and reference narratives. Qualitative assessments were also conducted.
 
 ### Results
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/67a7a7c8d5df2eaed85d77fc/zY3UYANWORhqDpv3aKNPT.png)
+
 The model achieved moderate ROUGE scores on test examples (e.g., ROUGE-1 ≈ 0.19, ROUGE-L ≈ 0.09). These scores, along with qualitative feedback, indicate that while the model captures key narrative elements, further refinement may enhance output quality.
 
 #### Summary