Update README.md

README.md

@@ -12,7 +12,7 @@ pinned: false
 
 ## Model Description
 
-This is a random baseline model for the Frugal AI Challenge 2024, specifically for the text classification task of identifying climate disinformation. The model serves as a performance floor, randomly assigning labels to text inputs without any learning.
+After getting the embeddings of the quotes by using an embedding model , a basic Neural Network has been trained for the classification part.
 
 ### Intended Use
 
@@ -24,7 +24,7 @@ This is a random baseline model for the Frugal AI Challenge 2024, specifically f
 
 The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
 - Size: ~6000 examples
-- Split: 80% train, 20% test
+- Split: 70% train, 30% test
 - 8 categories of climate disinformation claims
 
 ### Labels
@@ -40,13 +40,13 @@ The model uses the QuotaClimat/frugalaichallenge-text-train dataset:
 ## Performance
 
 ### Metrics
-- **Accuracy**: ~12.5% (random chance with 8 classes)
+- **Accuracy**: ~78.5% 
 - **Environmental Impact**:
   - Emissions tracked in gCO2eq
   - Energy consumption tracked in Wh
 
 ### Model Architecture
-The model implements a random choice between the 8 possible labels, serving as the simplest possible baseline.
+The model implements a Neural Network between the 8 possible labels, serving as a first baseline.
 
 ## Environmental Impact
 
@@ -57,11 +57,7 @@ Environmental impact is tracked using CodeCarbon, measuring:
 This tracking helps establish a baseline for the environmental impact of model deployment and inference.
 
 ## Limitations
-- Makes completely random predictions
-- No learning or pattern recognition
-- No consideration of input text
 - Serves only as a baseline reference
-- Not suitable for any real-world applications
 
 ## Ethical Considerations