Update README.md

README.md

@@ -49,7 +49,7 @@ The model demonstrates that learning to critique is more effective than learning
 
 
 ### Training Data
-- Dataset: [WebInstruct-CFT-50K](https://huggingface.co/datasets/TIGER-Lab/WebInstruct-CFT-50K)
+- Dataset: [WebInstruct-CFT-50K](https://huggingface.co/datasets/TIGER-Lab/WebInstruct-CFT)
 - Training format: (input=[query; noisy response], output=critique)
 - Teacher model: GPT-4o for generating critiques
 
@@ -60,6 +60,11 @@ The model demonstrates that learning to critique is more effective than learning
 - Training time: ~1 hour with DeepSpeed Zero-3
 
 
+## Evaluation Results
+
+
+![image/png](https://cdn-uploads.huggingface.co/production/uploads/636a35eff8d9af4aea181608/ifPVcA7-aAdzbxX8U6wat.png)
+
 For more details about the model architecture, methodology, and comprehensive evaluation results, please visit our [project webpage](https://tiger-ai-lab.github.io/CritiqueFineTuning).