Update app.py

app.py

@@ -5,14 +5,14 @@ import requests
 
 app = Flask(__name__)
 
-# === Model setup ===
-MODEL_URL = "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf?download=true"
+# Correct model URL and filename
+MODEL_URL = "https://huggingface.co/TheBloke/TinyLlama-1.1B-Chat-v1.0-GGUF/resolve/main/TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf"
 MODEL_PATH = "TinyLlama-1.1B-Chat-v1.0.Q4_K_M.gguf"
 
-# Download the model if it doesn’t exist yet
+# Download model if missing or incomplete
 if not os.path.exists(MODEL_PATH) or os.path.getsize(MODEL_PATH) < 1000000:
-    print("Downloading TinyLlama model... (this happens once)")
-    headers = {"User-Agent": "Mozilla/5.0"}  # prevent HuggingFace HTML redirect
+    print("📦 Downloading TinyLlama model... (this happens once)")
+    headers = {"User-Agent": "Mozilla/5.0"}
     r = requests.get(MODEL_URL, headers=headers, stream=True)
     if r.status_code != 200:
         raise ValueError(f"Failed to download model! HTTP {r.status_code}")
@@ -22,13 +22,10 @@ if not os.path.exists(MODEL_PATH) or os.path.getsize(MODEL_PATH) < 1000000:
                 f.write(chunk)
     print("✅ Model downloaded!")
 
-# Initialize Llama model
-print("Loading TinyLlama model...")
+print("🦙 Loading TinyLlama model...")
 llm = Llama(model_path=MODEL_PATH)
 print("✅ TinyLlama is ready!")
 
-
-# === API Endpoint ===
 @app.route("/api/ask", methods=["POST"])
 def ask():
     data = request.get_json()
@@ -44,10 +41,8 @@ def ask():
         top_p=0.9,
         stop=["User:", "TinyLlama:"],
     )
-
     reply = output["choices"][0]["text"].strip()
     return jsonify({"reply": reply})
 
-
 if __name__ == "__main__":
     app.run(host="0.0.0.0", port=7860)