Added qualitative results

README.md

@@ -15,6 +15,13 @@ license: unknown
 tags:
 - Krutrim
 - language-model
+widget:
+- text: "Category-wise evaluation results"
+  output:
+    url: "images/cumulative_score_category.png"
+- text: "Language-wise evaluation results"
+  output:
+    url: "images/cumulative_score_langauge.png"    
 ---
 # Krutrim-2
 
@@ -93,6 +100,11 @@ After fine-tuning, the model underwent Direct Preference Optimization (DPO) with
 | FloresIN (1-shot, xx-en) (chrf++)       | 50%                        | 54%                | 58%         |
 | FloresIN (1-shot, en-xx) (chrf++)       | 34%                        | 41%                | 46%         |
 
+### Qualitative Results
+Below are the results from manual evaluation of prompt-response pairs across languages and task categories. Scores are between 1-5 (higher the better). Model names were anonymised during the evaluation.
+
+<Gallery />
+
 ## Usage
 To use the model, you can load it with `AutoModelForCausalLM` as follows: