Update README.md

README.md

@@ -9,14 +9,13 @@ tags:
 - merge
 ---
 
-
 # Neuro-Orchestrator-8B
 
 <div align="center">
 
 ![Mergekit](https://img.shields.io/badge/Mergekit-TIES-blue)
 ![License](https://img.shields.io/badge/License-Apache%202.0-green)
-![Parameters](https://img.shields.io/badge/Parameters-8B-yellow)
+![Architecture](https://img.shields.io/badge/Architecture-Qwen2.5-blue)
 ![Dtype](https://img.shields.io/badge/Dtype-bfloat16-purple)
 
 **The Autonomous Adaptive Research Engine**  
@@ -26,7 +25,7 @@ tags:
 
 ## 🧠 Model Overview
 
-**Neuro-Orchestrator-8B** is a specialized agentic merge designed to solve the "always-on" reasoning problem. Unlike standard models, this model utilizes a **hybrid gating mechanism** derived from merging three distinct architectures:
+**Neuro-Orchestrator-8B** is a state-of-the-art agentic merge built on the **Qwen architecture**. It is designed to solve the "always-on" reasoning problem by utilizing a **hybrid gating mechanism** derived from merging three distinct Qwen-based fine-tunes:
 
 1.  **Analyzes** the complexity of the user request first (HiPO Influence).
 2.  **Decides** whether to answer immediately or enter a deep reasoning loop.
@@ -42,8 +41,7 @@ It was created using the **TIES-Merging** method on the following base models:
 
 ## 💻 Usage Code (Bfloat16)
 
-This model is optimized to run in `bfloat16` precision for maximum reasoning capability.
-*Note: This configuration requires a GPU with sufficient VRAM (approx. 16GB+).*
+This model is optimized to run in `bfloat16` precision. It uses the specific **ChatML** prompt template native to Qwen models.
 
 ### Installation
 ```bash
@@ -70,7 +68,7 @@ print("Model loaded successfully!")
 
 # --- INFERENCE FUNCTION ---
 def run_neuro_agent(prompt):
-    # ChatML Format triggers the Orchestrator personality
+    # Qwen/ChatML Format triggers the Orchestrator personality
     full_prompt = (
         f"<|im_start|>system\n"
         f"You are Neuro-Orchestrator. Analyze the request complexity, plan, and execute.<|im_end|>\n"
@@ -202,7 +200,7 @@ Both a pound of feathers and a pound of lead weigh exactly the same... However,
 
 ## 📜 License
 
-This model is a merge of models with Apache 2.0  licenses. Users should comply with the licenses of the constituent models:
+This model is a merge of Qwen-based models. Users should comply with the Apache 2.0 license and the specific terms of the constituent models:
 *   [MiroThinker-v1.0-8B](https://huggingface.co/miromind-ai/MiroThinker-v1.0-8B)
 *   [Nemotron-Orchestrator-8B](https://huggingface.co/nvidia/Nemotron-Orchestrator-8B)
 *   [HiPO-8B](https://huggingface.co/Kwaipilot/HiPO-8B)