Update app.py

app.py

@@ -12,14 +12,14 @@ llm = Llama(
     #     repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
     #     filename="Phi-3-mini-4k-instruct-q4.gguf",
     # ),
-    model_path=hf_hub_download(
-        repo_id="Ankitajadhav/Phi-3-mini-4k-instruct-q4.gguf",
-        filename="Phi-3-mini-4k-instruct-q4.gguf",
-    ),
     # model_path=hf_hub_download(
-    #     repo_id="TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF",
-    #     filename="capybarahermes-2.5-mistral-7b.Q2_K.gguf",
+    #     repo_id="Ankitajadhav/Phi-3-mini-4k-instruct-q4.gguf",
+    #     filename="Phi-3-mini-4k-instruct-q4.gguf",
     # ),
+    model_path=hf_hub_download(
+        repo_id="TheBloke/CapybaraHermes-2.5-Mistral-7B-GGUF",
+        filename="capybarahermes-2.5-mistral-7b.Q2_K.gguf",
+    ),
     n_ctx=2048,
     n_gpu_layers=50,  # Adjust based on your VRAM
 )