Update README.md

README.md

@@ -14,9 +14,7 @@ tags:
 - reasoning
 - mathematical-reasoning
 datasets:
-- piqa
-- ai2_arc
-- gsm8k
+- HuggingFaceH4/ultrachat_200k
 base_model:
 - mistralai/Ministral-3-3B-Base-2512
 library_name: transformers
@@ -57,7 +55,7 @@ model-index:
     metrics:
     - type: accuracy
       name: Accuracy
-      value: 24.0
+      value: 24
 ---
 
 # RubiNet
@@ -157,4 +155,4 @@ RubiNet is a fine-tuned conversational adaptation derived from `mistralai/Minist
 
 ## Repository Notes
 
-If you publish this repository publicly, keep the model title as **RubiNet** and place extra technical details such as benchmark scores, language coverage, and architecture hints in the tags and description rather than in the title.
+If you publish this repository publicly, keep the model title as **RubiNet** and place extra technical details such as benchmark scores, language coverage, and architecture hints in the tags and description rather than in the title.