Update app.py

app.py

@@ -35,8 +35,8 @@ import subprocess
 
 subprocess.run([
     "huggingface-cli", "download",
-    "TheBloke/Mistral-7B-Instruct-v0.1-GGUF",
-    "mistral-7b-instruct-v0.1.Q2_K.gguf",
+    "microsoft/Phi-3-mini-4k-instruct-gguf",
+    "Phi-3-mini-4k-instruct-gguf",
     "--local-dir", "./models",
     "--local-dir-use-symlinks", "False"
 ], check=True)
@@ -58,7 +58,7 @@ embeddings = HuggingFaceEmbeddings(
 # Load Mistral GGUF via llama.cpp (CPU optimized)
 # ------------------------------
 llm_cpp = Llama(
-    model_path="./models/mistral-7b-instruct-v0.1.Q2_K.gguf",
+    model_path="./models/Phi-3-mini-4k-instruct-gguf",
     n_ctx=2048,
     n_threads=4,  # Adjust based on your CPU cores
     n_gpu_layers=0,  # Force CPU-only