Update app.py

app.py

@@ -3,21 +3,29 @@ import requests
 import streamlit as st
 from llama_cpp import Llama
 
-# ✅ Define model path inside Hugging Face Space
+# ✅ Define model path
 MODEL_PATH = "./Phi-3-mini-4k-instruct-q4.gguf"
 MODEL_URL = "https://huggingface.co/YourModelRepo/Phi-3-mini-4k-instruct-q4.gguf"
 
+# ✅ Get Hugging Face API token from environment variable
+HF_TOKEN = os.getenv("HF_TOKEN")  # Set this securely in your Hugging Face Space
+HEADERS = {"Authorization": f"Bearer {HF_TOKEN}"} if HF_TOKEN else {}
+
 # ✅ Check if model exists, otherwise download
 if not os.path.exists(MODEL_PATH):
     st.info("Downloading the model file. Please wait...")
-    with requests.get(MODEL_URL, stream=True) as response:
-        response.raise_for_status()
-        with open(MODEL_PATH, "wb") as f:
-            for chunk in response.iter_content(chunk_size=8192):
-                f.write(chunk)
-    st.success("Model downloaded successfully!")
-
-# ✅ Load model in session
+    try:
+        with requests.get(MODEL_URL, headers=HEADERS, stream=True) as response:
+            response.raise_for_status()  # Stops the script if download fails
+            with open(MODEL_PATH, "wb") as f:
+                for chunk in response.iter_content(chunk_size=8192):
+                    f.write(chunk)
+        st.success("Model downloaded successfully!")
+    except requests.exceptions.HTTPError as e:
+        st.error(f"🚨 Model download failed: {e}")
+        st.stop()
+
+# ✅ Load model
 if "model" not in st.session_state:
     st.session_state["model"] = Llama(model_path=MODEL_PATH, n_ctx=4096)
 
@@ -54,7 +62,8 @@ if st.button("Send") and user_input:
     st.session_state["messages"].append(("assistant", response))
     st.chat_message("assistant").write(response)
 
-# Run the app with: streamlit run test_phi3.py
+# Run the app with: streamlit run app.py
+