Update app.py

app.py

@@ -15,7 +15,7 @@ llm = None
 llm_model = None
 # hf_hub_download(repo_id="bartowski/dolphin-2.9.1-yi-1.5-34b-GGUF", filename="dolphin-2.9.1-yi-1.5-34b-Q6_K.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="mradermacher/Dolphin3.0-Mistral-24B-GGUF", filename="Dolphin3.0-Mistral-24B.Q8_0.gguf",  local_dir = "./models")
+hf_hub_download(repo_id="mradermacher/Dolphin3.0-Mistral-24B-GGUF", filename="Dolphin3.0-Mistral-24B.Q6_K.gguf",  local_dir = "./models")
 # hf_hub_download(repo_id="kroonen/dolphin-2.9.2-Phi-3-Medium-GGUF", filename="dolphin-2.9.2-Phi-3-Medium-Q6_K.gguf",  local_dir = "./models")
 hf_hub_download(repo_id="cognitivecomputations/dolphin-2.9.2-qwen2-72b-gguf", filename="qwen2-Q3_K_M.gguf",  local_dir = "./models")
 
@@ -84,9 +84,9 @@ demo = gr.ChatInterface(
     respond,
     additional_inputs=[
         gr.Dropdown([
-            'Dolphin3.0-Mistral-24B.Q8_0.gguf',
+            'Dolphin3.0-Mistral-24B.Q6_K.gguf',
             'qwen2-Q3_K_M.gguf'
-        ], value="Dolphin3.0-Mistral-24B.Q8_0.gguf", label="Model"),
+        ], value="Dolphin3.0-Mistral-24B.Q6_K.gguf", label="Model"),
         gr.Slider(minimum=1, maximum=8192, value=8192, step=1, label="Max tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(