Modified readme card to reflect the new model

README.md

@@ -14,18 +14,74 @@ datasets:
 - KoalaAI/Text-Moderation-Multilingual
 ---
 
-# Constellation-One-Text-001
+# Constellation One
 
 An experimental text classification model fine-tuned from Microsoft/DeBERTa-V3 base for [Cockatoo](https://cockatoo.dev/)
 
-> [!Caution]
-> Deprecated. New model will be updated soon.
->
-> Model fails evaluation and has problematic labels.
-
 This model is licensed under the `Apache-2.0` license.
 
-**Resources:**
+**Available Labels:**
+
+```json:
+"id2label": {
+    "0": "scam",
+    "1": "violence",
+    "2": "harassment",
+    "3": "hate_speech",
+    "4": "toxicity",
+    "5": "obscenity"
+}
+```
+
+## Performance
+
+Constellation One achieves a near-SOTA levels of performance within its weight class, specifically excelling in detecting scams and harassment.
+
+By default, the model has very high recall values (~0.9) in all categories. After tuning threshold values, recall values will drop to ~0.81, but F1 will increase to ~0.74.
+
+### Evaluation (Untuned Thresholds):
+
+**Thresholds:**
+
+```python
+LABEL_THRESHOLDS = {
+    'scam': 0.5,
+    'violence': 0.5,
+    'harassment': 0.5,
+    'hate_speech': 0.5,
+    'toxicity': 0.5,
+    'obscenity': 0.5
+}
+```
+
+![Recall Metrics](/assets/graphs/untuned/recall_deberta.png)
+![Precision Metrics](/assets/graphs/untuned/precision_deberta.png)
+![F1 Metrics](/assets/graphs/untuned/f1_deberta.png)
+
+---
+
+### Evaluation (Tuned Thresholds):
+
+**Thresholds:**
+
+```python
+LABEL_THRESHOLDS = {
+    'scam': 0.60,
+    'violence': 0.73,
+    'harassment': 0.70,
+    'hate_speech': 0.80,
+    'toxicity': 0.75,
+    'obscenity': 0.85
+}
+```
+
+![Recall Metrics](/assets/graphs/tuned/recall_deberta.png)
+![Precision Metrics](/assets/graphs/tuned/precision_deberta.png)
+![F1 Metrics](/assets/graphs/tuned/f1_deberta.png)
+
+---
+
+## Resources:
 
 Training/Inferencing server: https://github.com/DominicTWHV/Cockatoo_ML_Training/