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)
 
-download_gguf_model = hf_hub_download(repo_id="bartowski/Einstein-v6.1-Llama3-8B-GGUF", filename="Einstein-v6.1-Llama3-8B-Q5_K_M.gguf",  local_dir = "./models")
+download_gguf_model = hf_hub_download(repo_id="bartowski/Einstein-v6.1-Llama3-8B-GGUF", filename="Einstein-v6.1-Llama3-8B-Q6_K_M.gguf",  local_dir = "./models")
 #hf_hub_download(repo_id="crusoeai/dolphin-2.9.1-llama-3-70b-GGUF", filename="dolphin-2.9.1-llama-3-70b.Q3_K_M.gguf",  local_dir = "./models")
 # hf_hub_download(repo_id="bartowski/dolphin-2.9.1-yi-1.5-9b-GGUF", filename="dolphin-2.9.1-yi-1.5-9b-f32.gguf",  local_dir = "./models")
 # hf_hub_download(repo_id="crusoeai/dolphin-2.9.1-llama-3-8b-GGUF", filename="dolphin-2.9.1-llama-3-8b.Q6_K.gguf",  local_dir = "./models")
@@ -149,7 +149,7 @@ demo = gr.ChatInterface(
             label="Repetition penalty",
         ),
         #models = ['dolphin-2.9.1-yi-1.5-34b-Q6_K.gguf', 'dolphin-2.9.1-llama-3-70b.Q3_K_M.gguf']
-        gr.Dropdown([download_gguf_model], value=download_gguf_model, label="Model"),
+        gr.Dropdown(["Einstein-v6.1-Llama3-8B-Q6_K_M.gguf"], value="Einstein-v6.1-Llama3-8B-Q6_K_M.gguf", label="Model"),
     ],
     theme=gr.themes.Soft(primary_hue="indigo", secondary_hue="blue", neutral_hue="gray",font=[gr.themes.GoogleFont("Exo"), "ui-sans-serif", "system-ui", "sans-serif"]).set(
         body_background_fill_dark="#0f172a",