Update app.py

app.py

@@ -7,7 +7,7 @@ from huggingface_hub import hf_hub_download
 subprocess.run('pip install llama-cpp-python==0.2.75 --extra-index-url https://abetlen.github.io/llama-cpp-python/whl/cu124', shell=True)
 subprocess.run('pip install llama-cpp-agent==0.2.10', shell=True)
 
-hf_hub_download(repo_id="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF", filename="mixtral-8x7b-instruct-v0.1.Q5_K_M.gguf",  local_dir = "./models")
+hf_hub_download(repo_id="TheBloke/Mixtral-8x7B-Instruct-v0.1-GGUF", filename="mixtral-8x7b-instruct-v0.1.Q6_K.gguf",  local_dir = "./models")
 
 @spaces.GPU(duration=120)
 def respond(
@@ -26,7 +26,7 @@ def respond(
     from llama_cpp_agent.chat_history.messages import Roles
     
     llm = Llama(
-        model_path="models/mixtral-8x7b-instruct-v0.1.Q5_K_M.gguf",
+        model_path="models/mixtral-8x7b-instruct-v0.1.Q6_K.gguf",
         n_gpu_layers=33,
     )
     provider = LlamaCppPythonProvider(llm)