Update model card with pipeline_tag, widget examples, and detailed info

README.md

@@ -1,16 +1,41 @@
 ---
+language: en
+license: mit  # Or choose another like 'apache-2.0', 'cc-by-sa-4.0', etc.
 library_name: transformers
-license: apache-2.0
-base_model: distilbert-base-uncased
 tags:
-- generated_from_keras_callback
+  - text-classification
+  - hate-speech
+  - offensive-language
+  - distilbert
+  - tensorflow
+pipeline_tag: text-classification
+widget:
+  - text: "I love this beautiful day, it's fantastic!"
+    example_title: "Positive Example"
+  - text: "You are a terrible person and I wish you the worst."
+    example_title: "Offensive Example"
+  - text: "This is a completely neutral statement about clouds."
+    example_title: "Neutral Example"
+  - text: "Kill all of them, they don't belong in our country." # Potentially strong hate speech
+    example_title: "Hate Speech Example"
 model-index:
-- name: distilbert-hatespeech-classifier
-  results: []
+  - name: distilbert-hatespeech-classifier # Should match your model name
+    results:
+    - task:
+        type: text-classification
+        name: Text Classification
+      dataset:
+        name: tdavidson/hate_speech_offensive # Or the specific name you used
+        type: hf # Indicates it's from Hugging Face datasets
+      metrics:
+        - name: Validation Accuracy
+          type: accuracy
+          value: 0.7137 # Your best validation accuracy (from Epoch 2)
+        - name: Validation Loss
+          type: loss
+          value: 0.7337 # Your best validation loss (from Epoch 2)
 ---
 
-<!-- This model card has been generated automatically according to the information Keras had access to. You should
-probably proofread and complete it, then remove this comment. -->
 
 # Ethical-Content-Moderation
 Fine-Tuning DistilBERT for Ethical Content Moderation