Update app.py

app.py

@@ -9,7 +9,6 @@ from llama_cpp import Llama
 
 app = FastAPI(title="Qwen 2.5 Coder Public Secure Server")
 
-# Enable CORS for local IDE connections
 app.add_middleware(
     CORSMiddleware,
     allow_origins=["*"],
@@ -18,8 +17,7 @@ app.add_middleware(
     allow_headers=["*"],
 )
 
-# 🔐 CHOOSE YOUR CUSTOM API KEY HERE
-# You will type this exact key into Cline / Continue / Claude Code
+# 🔐 YOUR PREFERRED CUSTOM API KEY
 CUSTOM_API_KEY = "varsshancoder"
 
 security = HTTPBearer()
@@ -38,7 +36,7 @@ MODEL_FILE = "qwen2.5-coder-7b-instruct-q4_k_m.gguf"
 print("Checking and downloading Qwen 2.5 Coder 7B GGUF model...")
 model_path = hf_hub_download(repo_id=MODEL_REPO, filename=MODEL_FILE)
 
-print(f"Loading model into RAM from: {model_path}")
+print(f"Loading model into memory from: {model_path}")
 llm = Llama(
     model_path=model_path,
     n_ctx=4096,      
@@ -48,7 +46,6 @@ llm = Llama(
 )
 print("Model loaded successfully and secured!")
 
-# Add the verify_api_key dependency to secure your completions endpoint completely
 @app.post("/v1/chat/completions", dependencies=[Depends(verify_api_key)])
 async def chat_completions(request: Request):
     body = await request.json()
@@ -100,4 +97,3 @@ def index():
         "model": "qwen2.5-coder-7b-instruct-q4_k_m", 
         "endpoint": "/v1/chat/completions"
     }
-