Update app.py

app.py

@@ -72,7 +72,10 @@ publication_vectorstore = langchain_community.vectorstores.FAISS.load_local(
 #     task="text-generation", model="Qwen/Qwen2.5-7B-Instruct-GPTQ-Int4", device="cuda"
 # )
 llm = llama_cpp.Llama.from_pretrained(
-    repo_id="bartowski/Qwen2.5-7B-Instruct-GGUF", filename="Qwen2.5-7B-Instruct-Q4_K_M.gguf", 
+    repo_id="bartowski/Qwen2.5-7B-Instruct-GGUF", 
+    filename="Qwen2.5-7B-Instruct-Q4_K_M.gguf", 
+    n_gpu_layers=-1,
+    n_ctx=2048,
 )