Update app.py

app.py

@@ -8,11 +8,11 @@ from sentence_transformers import SentenceTransformer
 
 # Initialize the Llama model
 llm = Llama(
-    model_path=hf_hub_download(
-        repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
-        filename="Phi-3-mini-4k-instruct-q4.gguf",
-    ),
-    # model_path = "./models/OpenBioLLM-Llama3-8B-Q5_K_M.gguf",
+    # model_path=hf_hub_download(
+    #     repo_id="microsoft/Phi-3-mini-4k-instruct-gguf",
+    #     filename="Phi-3-mini-4k-instruct-q4.gguf",
+    # ),
+    model_path = "./models/Phi-3-mini-4k-instruct-gguf",
     n_ctx=2048,
     n_gpu_layers=50,  # Adjust based on your VRAM
 )