Update README.md

README.md

@@ -67,57 +67,74 @@ You are Morpheus-LLM, an AI "Architect" specialized in Unity Engine and XR techn
 Here is how to load and run Morpheus-LLM in your Python environment:
 
 ```bash
-# @title 🕶️ Run Morpheus-LLM-14B (Fast Install ⚡)
+# @title  Run Morpheus-LLM
 import os
+from huggingface_hub import hf_hub_download
+from llama_cpp import Llama
 
 # --- 1. SETUP ---
-print("⚙️ Installing dependencies (Fast Mode)...")
-
+print(" Installing Morpheus engine (CUDA 12.1)...")
+# Using pre-built wheels to install in seconds
 !pip install llama-cpp-python \
   --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu121 \
-  huggingface_hub
-
-from huggingface_hub import hf_hub_download
-from llama_cpp import Llama
+  huggingface_hub > /dev/null 2>&1
 
 # --- 2. DOWNLOAD MODEL ---
 model_id = "ErenAta00/Morpheus-LLM-14B-Virtual-Reality-Model"
-# Exact filename of the GGUF file in your repo
+# The new, branded filename we just renamed
 filename = "Morpheus-LLM-14B-Virtual-Reality-Model.Q4_K_M.gguf"
 
-print(f"\n  Downloading model: {filename}...")
+print(f"\n Summoning Morpheus from the cloud: {filename}...")
 try:
     model_path = hf_hub_download(
         repo_id=model_id,
         filename=filename,
         local_dir="./models"
     )
-    print(f" Model ready: {model_path}")
+    print(f" Download Complete: {model_path}")
 except Exception as e:
-    print(f" Download Error: File '{filename}' not found. Please check the repo.")
+    print(f" Error: {e}")
     raise e
 
-# --- 3. LOAD MODEL ---
-print("\n Loading Morpheus into GPU...")
+# --- 3. LOAD INTO GPU ---
+print("\n Uploading consciousness to GPU...")
 llm = Llama(
     model_path=model_path,
-    n_gpu_layers=-1,      # -1 = Load ALL layers to GPU (Max Speed)
-    n_ctx=4096,           # Context Window
-    verbose=False         # Silent mode
+    n_gpu_layers=-1,      
+    n_ctx=4096,          
+    verbose=False         
 )
 
-# --- 4. SYSTEM PROMPT & QUERY ---
+# --- 4. SYSTEM PROTOCOL ---
 system_prompt = """You are Morpheus-LLM, an AI "Architect" specialized in Unity Engine and XR technologies.
 Your mission is to help developers build immersive realities.
 Your code must always be performance-oriented, clean, and compliant with the latest XR standards.
 You prefer modern C# approaches (Async/Await) over legacy ones when applicable."""
 
+# Example Query
 user_query = "Write a highly optimized C# script for a Unity VR hand-tracking controller that grabs objects using physics."
 
 print(f"\nUSER: {user_query}\n")
-print(" MORPHEUS IS THINKING...\n" + "-"*30)
+print(" MORPHEUS IS THINKING...\n" + "-"*40)
+
+# --- 5. GENERATE RESPONSE ---
+output = llm.create_chat_completion(
+    messages=[
+        {"role": "system", "content": system_prompt},
+        {"role": "user", "content": user_query}
+    ],
+    max_tokens=2048,
+    temperature=0.7,
+    stream=True
+)
+
+# Stream the output like a hacker terminal
+for chunk in output:
+    delta = chunk['choices'][0]['delta']
+    if 'content' in delta:
+        print(delta['content'], end="", flush=True)
 
-# ---
+print("\n\n" + "-"*40 + "\n SESSION TERMINATED.")
 ```
 
 ## ⚠️ Important Notes & Limitations