Update README.md

README.md

@@ -8,7 +8,7 @@ pinned: false
 ---
 
 
-# DistilBERT Model for Climate Disinformation Classification
+# Climate Disinformation Classification using Attention Mechanism
 
 ## Model Description
 
@@ -40,7 +40,7 @@ The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
 ## Performance
 
 ### Metrics
-- **Accuracy**: ~63.5% 
+- **Accuracy**:
 - **Environmental Impact**:
   - Emissions tracked in gCO2eq
   - Energy consumption tracked in Wh
@@ -57,10 +57,10 @@ Environmental impact is tracked using CodeCarbon, measuring:
 This tracking helps establish a baseline for the environmental impact of model deployment and inference.
 
 ## Limitations
-- Makes BERT predictions
+- Text Classification using Attention Mechanism
 - No learning or pattern recognition
 - Input text vectorized/tokenized
-- Serves only as a BERT baseline reference
+- Serves only as baseline reference
 - Not suitable for any real-world applications
 
 ## Ethical Considerations