Update README.md

README.md

@@ -1,16 +1,51 @@
 ---
-pipeline_tag: text-generation
+language: en
+license: mit
 tags:
-- agent
+- moderation
+- safety
+- content-moderation
+- transformer
+- chain-of-thought
+- reasoning
+library_name: pytorch
+pipeline_tag: text-generation
+datasets:
+- OnlyCheeini/greesyguard-3-mini-claude-4.6-sonnet-2000x
+---
+
+# GreesyGuard (GreesyGPT)
+
+GreesyGuard is a lightweight **reasoning-based content moderation model** designed to analyze user messages, evaluate harm potential, and produce structured moderation verdicts.
+
+Unlike traditional classifiers, GreesyGuard performs **step‑by‑step analysis inside `<think>` blocks** before generating the final moderation decision.
+
+This improves transparency and makes moderation decisions easier to audit.
+
 ---
 
-# GreesyGuard
+# Model Overview
 
-Reasoning-based moderation model.
+GreesyGuard is a Transformer model specialized for safety classification tasks such as:
 
-## Model
+- harassment detection
+- hate speech
+- spam detection
+- misinformation identification
+- crisis detection
 
-Transformer moderation model trained to classify:
+Instead of directly outputting a label, the model:
+
+1. Analyzes the message
+2. Evaluates context and intent
+3. Identifies policy violations
+4. Outputs a final moderation verdict
+
+---
+
+# Moderation Labels
+
+The model produces the following moderation categories:
 
 SAFE  
 SPAM  
@@ -20,10 +55,134 @@ HATE_SPEECH
 CRISIS_REFERRAL  
 UNSAFE
 
-## Usage
+Example output:
+
+```
+## Verdict
+**HARASSMENT**
+```
+
+---
+
+# Model Architecture
+
+| Parameter | Value |
+|-----------|------|
+Layers | 12 |
+Heads | 12 |
+Embedding Dimension | 768 |
+Context Window | 12,000 tokens |
+Tokenizer | o200k_base (extended) |
+Vocabulary Size | 8192 |
+
+Key architectural features:
+
+- Transformer decoder architecture
+- Rotary Positional Embeddings (RoPE)
+- KV‑Cache optimized inference
+- Structured chat‑template training
+- Markdown reasoning output
+
+---
+
+# Reasoning Modes
+
+The model supports configurable reasoning budgets:
+
+| Mode | Think Tokens | Purpose |
+|-----|-------------|--------|
+NONE | 200 | Fast moderation |
+LOW | 512 | Balanced reasoning |
+MEDIUM | 1536 | Detailed analysis |
+HIGH | 3072 | Maximum review depth |
+
+Higher modes produce more thorough moderation reasoning but increase latency.
+
+---
+
+# Example Usage
 
 ```python
-from model import GreesyGPT, generate_moderation
+from model import GreesyGPT, generate_moderation, ReasoningMode, OutputFormat
 
 model = GreesyGPT()
-```
+
+result = generate_moderation(
+    model,
+    prompt="You're worthless and nobody likes you.",
+    mode=ReasoningMode.MEDIUM,
+    output_format=OutputFormat.JSON
+)
+
+print(result["verdict_fmt"])
+```
+
+Example structured output:
+
+```
+{
+  "verdict": "HARASSMENT",
+  "severity": 3,
+  "confidence_hint": "medium"
+}
+```
+
+---
+
+# Training Format
+
+Training data follows a structured conversation template:
+
+```
+<|system|>
+moderation instructions
+</|system|>
+
+<|user|>
+message to review
+</|user|>
+
+<|assistant|>
+<think>
+step-by-step reasoning
+</think>
+
+verdict<|endoftext|>
+```
+
+Only assistant tokens contribute to the training loss.
+
+---
+
+# Intended Use
+
+GreesyGuard is designed for:
+
+- social media moderation
+- comment filtering
+- forum safety pipelines
+- research in explainable moderation systems
+
+---
+
+# Limitations
+
+- The reasoning output may appear confident but still be incorrect.
+- Sarcasm and cultural context can be misinterpreted.
+- The model should **not be used for fully automated enforcement** without human oversight.
+
+---
+
+# Safety
+
+Moderation systems should always include **human review for high‑impact actions** such as account suspension or legal escalation.
+
+---
+
+# Authors
+
+Created by the **GreesyGuard Project**
+
+Author: Nicat
+
+GitHub: https://github.com/Nicat-dcw/GreesyGuard