Upload README.md with huggingface_hub

README.md

@@ -6,18 +6,17 @@ tags:
 - sentiment-analysis
 - modernbert
 - financial-nlp
-- unsloth
 datasets:
 - neoyipeng/financial_reasoning_aggregated
 metrics:
 - accuracy
 widget:
-- text: The company reported strong quarterly earnings with revenue beating expectations.
-  example_title: Positive Example
-- text: Stock prices fell sharply following disappointing guidance from management.
-  example_title: Negative Example
-- text: The merger is expected to close in Q3 pending regulatory approval.
-  example_title: Neutral Example
+- text: "The company reported strong quarterly earnings with revenue beating expectations."
+  example_title: "Positive Example"
+- text: "Stock prices fell sharply following disappointing guidance from management."
+  example_title: "Negative Example"
+- text: "The merger is expected to close in Q3 pending regulatory approval."
+  example_title: "Neutral Example"
 ---
 
 # ModernFinBERT: Financial Sentiment Analysis
@@ -28,18 +27,29 @@ ModernFinBERT is a financial sentiment analysis model based on the ModernBERT ar
 
 - **Base Model**: answerdotai/ModernBERT-base
 - **Task**: 3-class sentiment classification (Negative, Neutral, Positive)
-- **Training Data**: Financial text from multiple sources (including FinancialPhraseBank)
+- **Training Data**: Vanilla sentiment tasks from multiple sources (including FinancialPhraseBank)
 - **Parameters**: 149,607,171
 
 ## Performance
 
-### Validation/Test Accuracy on Various Financial Datasets (neoyipeng/financial_reasoning_aggregated)
+### Overall Accuracy
 
-Average: 84.6% / 82.7%
+| Split | Accuracy |
+|-------|----------|
+| Validation | 85.3% |
+| Test | 83.1% |
 
+### Test Accuracy by Source
 
-## Usage
+| Source | Accuracy | Correct/Total |
+|--------|----------|---------------|
+| 4.0 | 89.5% | 77/86 |
+| 9.0 | 88.0% | 205/233 |
+| 5.0 | 84.4% | 205/243 |
+| 3.0 | 80.0% | 20/25 |
+| 8.0 | 69.1% | 94/136 |
 
+## Usage
 ```python
 from transformers import AutoTokenizer, AutoModelForSequenceClassification
 import torch
@@ -71,7 +81,6 @@ print(f"Sentiment: {predicted_class} ({confidence:.2f})")
 ## Citation
 
 If you use this model, please cite:
-
 ```bibtex
 @misc{modernfinbert2025,
   title={ModernFinBERT: A Modern Approach to Financial Sentiment Analysis},