Update README.md

commit changes to main

README.md

@@ -9,7 +9,16 @@ metrics:
 - accuracy
 model-index:
 - name: gpt2-toxic-comment-classifier
-  results: []
+  results: 
+  - task:
+      type: text-classification
+    metrics:
+    - name: F1
+      type: f1
+      value: 0.7212
+    - name: Accuracy
+      type: accuracy
+      value: 0.9256
 ---
 
 <!-- This model card has been generated automatically according to the information the Trainer had access to. You
@@ -17,7 +26,7 @@ should probably proofread and complete it, then remove this comment. -->
 
 # gpt2-toxic-comment-classifier
 
-This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the None dataset.
+This model is a fine-tuned version of [gpt2-medium](https://huggingface.co/gpt2-medium) on the [Toxic Comment Classifier](https://www.kaggle.com/c/jigsaw-toxic-comment-classification-challenge/data) dataset.
 It achieves the following results on the evaluation set:
 - Loss: 0.0519
 - F1: 0.7212
@@ -26,11 +35,20 @@ It achieves the following results on the evaluation set:
 
 ## Model description
 
-More information needed
+This is a `gpt2-medium` model fine-tuned for multi-label text classification on the Jigsaw Toxic Comment Classification Challenge dataset. It is designed to identify and categorize different types of toxic language in online comments, including toxic, severe_toxic, obscene, threat, insult, and identity_hate.
 
 ## Intended uses & limitations
 
-More information needed
+This model is intended to be used for content moderation and analysis of online conversations to detect and flag potentially harmful language. It can be used as a tool to help maintain a healthier online environment.
+
+**How to Use:**
+You can use this model directly with a `text-classification` pipeline:
+```python
+from transformers import pipeline
+
+classifier = pipeline("text-classification", model="raavip/gpt2-toxic-comment-classifier")
+results = classifier("This is a horrible comment that is very insulting.")
+print(results)
 
 ## Training and evaluation data