Update README.md

README.md

@@ -5,7 +5,7 @@ language:
 pipeline_tag: text-generation
 ---
 <p align="left">
-  <img src="https://huggingface.co/Devocean-06/Spam_Filter-gemma/blob/main/skitty.png" width="50%"/>
+  <img src="https://huggingface.co/Devocean-06/Spam_Filter-gemma/resolve/main/skitty.png" width="50%"/>
 </p>
 
 # Devocean-06/Spam_Filter-gemma
@@ -30,37 +30,24 @@ pipeline_tag: text-generation
 **Model Developers**: SK Devoceon-06 On device LLM
 
 ## Model Information
-
-Skitty is an explainable small language model (sLLM) designed to classify various types of spam messages and provide concise reasoning for its decisions.  
-Instead of only labeling text as "spam" or "not spam", the model outputs short natural-language explanations describing why the message was identified as spam.
-
+Skitty is an explainable small language model (sLLM) that classifies spam messages and provides brief reasoning for each decision.
 ---
 
 ## 🧠 Description
 Skitty was trained on an updated 2025 spam message dataset collected through the Smart Police Big Data Platform in South Korea.  
 The model leverages deduplication, curriculum sampling, and off-policy distillation to improve both classification accuracy and interpretability.
 
-### Data and Preprocessing
+## Data and Preprocessing
 - Data source: 2025 Smart Police Big Data Platform spam message dataset  
 - Deduplication: Performed near-duplicate removal using SimHash filtering  
 - Sampling strategy: Applied curriculum-based sampling to control difficulty and improve generalization  
 - Labeling: Trained using hard-label supervision after label confidence refinement
 
-### Training and Distillation
+## Training and Distillation
 - Utilized off-policy distillation to compress the decision process of a large teacher LLM into a smaller student model  
 - Instead of directly mimicking the teacher’s text generation, the model distills the reasoning trace for spam detection  
 - Combined curriculum learning with hard-label distillation to balance accuracy, interpretability, and generalization
 
-### Key Features
-
-| Category | Description |
-|-----------|-------------|
-| Model Type | sLLM (Small Language Model for Spam Classification & Explanation) |
-| Main Function | Spam / Non-spam classification with reasoning |
-| Training Approach | Off-policy knowledge distillation + curriculum sampling |
-| Data Cleaning | SimHash-based deduplication and quality filtering |
-| Objective | Build a model that not only classifies spam but also explains its rationale |
-
 ---
 
 ## 🚀 Quick Start