Vrandan
/

Comment-Moderation

@@ -11,7 +11,7 @@ language:
 base_model:
 - distilbert/distilbert-base-uncased
 ---
-# 🛡️ Comment Moderation Model
 [![HuggingFace](https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue)](https://huggingface.co/Vrandan/Comment-Moderation)
 [![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/release/python-312/)
@@ -20,7 +20,7 @@ base_model:
 A powerful, multi-label content moderation system built on **DistilBERT** architecture, designed to detect and classify potentially harmful content in user-generated comments with high accuracy. This model stands out as currently the best in terms of performance based on the provided dataset for text moderation. Additionally, it has the smallest footprint, making it ideal for deployment on edge devices. Currently, it is the only model trained to achieve such high performance while maintaining a minimal size relative to the training data on Hugging Face.
-## 🎯 Key Features
 - Multi-label classification
 - Real-time content analysis
@@ -33,7 +33,7 @@ A powerful, multi-label content moderation system built on **DistilBERT** archit
 - Resource-efficient while maintaining high accuracy
 - Can run on consumer-grade hardware
-## 📊 Content Categories
 The model identifies the following types of potentially harmful content:
@@ -49,7 +49,7 @@ The model identifies the following types of potentially harmful content:
 | Violence/Graphic | `V2` | Violent content that depicts death, violence, or serious physical injury in extreme graphic detail. |
 | Safe Content | `OK` | Appropriate content that doesn't violate any guidelines. |
-## 📈 Performance Metrics
 ```
 Accuracy: 95.4%
@@ -60,7 +60,7 @@ Micro F1 Score: 0.802
 [View detailed performance metrics](#model-performance)
-## 🖥️ Training Details
 The model was trained on an **NVIDIA RTX 3080** GPU in a home setup, demonstrating that effective content moderation models can be developed with consumer-grade hardware. This makes the model development process more accessible to individual developers and smaller organizations.
@@ -73,7 +73,7 @@ Key Training Specifications:
 Despite its relatively compact size **(67M parameters)**, this model achieves impressive performance metrics, making it suitable for deployment across various devices and environments. The model's efficiency-to-performance ratio demonstrates that effective content moderation is possible without requiring extensive computational resources.
-## 🚀 Quick Start
 ### Python Implementation (Local)
@@ -213,7 +213,7 @@ query({"inputs": "Your text here"}).then((response) => {
 });
 ```
-## 📊 Detailed Model Performance <a name="model-performance"></a>
 The model has been extensively evaluated using standard classification metrics:
@@ -242,7 +242,7 @@ The model has been extensively evaluated using standard classification metrics:
 - Potential for false positives
 - Cultural context variations
-## 📚 Dataset Information
 This model was trained on the dataset released by OpenAI, as described in their paper ["A Holistic Approach to Undesired Content Detection"](https://arxiv.org/abs/2208.03274).
@@ -261,7 +261,7 @@ If you use this model or dataset in your research, please cite:
 }
 ```
-## 📧 Contact
 For support or queries, please message me on Slack.

 base_model:
 - distilbert/distilbert-base-uncased
 ---
+# Comment Moderation Model
 [![HuggingFace](https://img.shields.io/badge/🤗%20Hugging%20Face-Spaces-blue)](https://huggingface.co/Vrandan/Comment-Moderation)
 [![Python 3.12+](https://img.shields.io/badge/python-3.12+-blue.svg)](https://www.python.org/downloads/release/python-312/)
 A powerful, multi-label content moderation system built on **DistilBERT** architecture, designed to detect and classify potentially harmful content in user-generated comments with high accuracy. This model stands out as currently the best in terms of performance based on the provided dataset for text moderation. Additionally, it has the smallest footprint, making it ideal for deployment on edge devices. Currently, it is the only model trained to achieve such high performance while maintaining a minimal size relative to the training data on Hugging Face.
+## Key Features
 - Multi-label classification
 - Real-time content analysis
 - Resource-efficient while maintaining high accuracy
 - Can run on consumer-grade hardware
+## Content Categories
 The model identifies the following types of potentially harmful content:
 | Violence/Graphic | `V2` | Violent content that depicts death, violence, or serious physical injury in extreme graphic detail. |
 | Safe Content | `OK` | Appropriate content that doesn't violate any guidelines. |
+## Performance Metrics
 ```
 Accuracy: 95.4%
 [View detailed performance metrics](#model-performance)
+## Training Details
 The model was trained on an **NVIDIA RTX 3080** GPU in a home setup, demonstrating that effective content moderation models can be developed with consumer-grade hardware. This makes the model development process more accessible to individual developers and smaller organizations.
 Despite its relatively compact size **(67M parameters)**, this model achieves impressive performance metrics, making it suitable for deployment across various devices and environments. The model's efficiency-to-performance ratio demonstrates that effective content moderation is possible without requiring extensive computational resources.
+## Quick Start
 ### Python Implementation (Local)
 });
 ```
+## Detailed Model Performance <a name="model-performance"></a>
 The model has been extensively evaluated using standard classification metrics:
 - Potential for false positives
 - Cultural context variations
+## Dataset Information
 This model was trained on the dataset released by OpenAI, as described in their paper ["A Holistic Approach to Undesired Content Detection"](https://arxiv.org/abs/2208.03274).
 }
 ```
+## Contact
 For support or queries, please message me on Slack.