Update app.py

app.py

@@ -13,35 +13,20 @@ llm = None
 llm_model = None
 
 hf_hub_download(
-    repo_id="unsloth/Reflection-Llama-3.1-70B-GGUF",
-    filename="Reflection-Llama-3.1-70B.Q3_K_L.gguf",
+    repo_id="TheBloke/Open_Gpt4_8x7B_v0.2-GGUF",
+    filename="open_gpt4_8x7b_v0.2.Q5_K_M.gguf",
     local_dir = "./models"
 )
 
-hf_hub_download(
-    repo_id="jhofseth/Reflection-Llama-3.1-70B-GGUF",
-    filename="Reflection-Llama-3.1-70B-IQ3_XXS.gguf",
-    local_dir = "./models"
-)
-
-hf_hub_download(
-    repo_id="bartowski/Reflection-Llama-3.1-70B-GGUF",
-    filename="Reflection-Llama-3.1-70B.imatrix",
-    local_dir = "./random"
-)
 
 def get_messages_formatter_type(model_name):
-    if "Llama" in model_name:
-        return MessagesFormatterType.LLAMA_3
-    else:
-        raise ValueError(f"Unsupported model: {model_name}")
-
+    return MessagesFormatterType.ALPACA
 
 @spaces.GPU
 def respond(
     message,
     history: list[tuple[str, str]],
-    model,
+    model="open_gpt4_8x7b_v0.2.Q5_K_M.gguf",
     system_message,
     max_tokens,
     temperature,
@@ -108,24 +93,9 @@ def respond(
         outputs += output
         yield outputs
 
-description = """<p><center>
-<a href="https://huggingface.co/mattshumer/ref_70_e3" target="_blank">[Reflection Llama 3.1 70B Correct Weights]</a>
-<a href="https://huggingface.co/mattshumer/Reflection-Llama-3.1-70B" target="_blank">[Old Repo]</a>
-<a href="https://huggingface.co/unsloth/Reflection-Llama-3.1-70B-GGUF" target="_blank">[Reflection-Llama-3.1-70B-GGUF]</a>
-
-</center></p>
-"""
-
 demo = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
-        gr.Dropdown([
-                "Reflection-Llama-3.1-70B.Q3_K_L.gguf",
-                "Reflection-Llama-3.1-70B-IQ3_XXS.gguf"
-            ],
-            value="Reflection-Llama-3.1-70B.Q3_K_L.gguf",
-            label="Model"
-        ),
         gr.Textbox(value="You are a world-class AI system, capable of complex reasoning and reflection. Reason through the query inside <thinking> tags, and then provide your final response inside <output> tags. If you detect that you made a mistake in your reasoning at any point, correct yourself inside <reflection> tags.", label="System message"),
         gr.Slider(minimum=1, maximum=8192, value=2048, step=1, label="Max tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
@@ -168,8 +138,8 @@ demo = gr.ChatInterface(
     undo_btn="Undo",
     clear_btn="Clear",
     submit_btn="Send",
-    title="Reflection Llama-3.1 70B",
-    description=description,
+    title="OpenGPT4",
+    description="Chat with *GPT-4* for free!",
     chatbot=gr.Chatbot(
         scale=1, 
         likeable=False,