Update app.py

app.py

@@ -2,15 +2,14 @@ import gradio as gr
 from huggingface_hub import InferenceClient
 from llama_cpp import Llama
 
-# Initialize the Llama model
+# Initialize the InferenceClient
+client = InferenceClient()
+
 llm = Llama.from_pretrained(
     repo_id="bartowski/Ministral-8B-Instruct-2410-GGUF",
     filename="Ministral-8B-Instruct-2410-Q4_K_M.gguf",
 )
 
-# Initialize the inference client
-client = InferenceClient(model="bartowski/Ministral-8B-Instruct-2410-GGUF")
-
 def respond(
     message,
     history: list[tuple[str, str]],
@@ -29,29 +28,24 @@ def respond(
 
     messages.append({"role": "user", "content": message})
 
-    # Use llm for chat completion
-    response = llm.create_chat_completion(
-        messages=messages,
+    response = ""
+
+    # Use the client to get the chat completion
+    for message in client.chat_completion(
+        messages,
         max_tokens=max_tokens,
+        stream=True,
         temperature=temperature,
         top_p=top_p,
-        stream=True,
-    )
-
-    for token in response:
-        # Print the token to debug the structure
-        print(token)
-        # Adjust based on the actual structure of the response
-        if 'choices' in token and len(token['choices']) > 0:
-            content = token['choices'][0].get('delta', {}).get('content', '')
-            yield content
-        else:
-            yield "No valid response received."
+    ):
+        token = message['choices'][0]['delta']['content']
+        response += token
+        yield response
 
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly, conversational chatbot who utilizes relevant information and emojis to build efficient conversations.", label="System message"),
+        gr.Textbox(value="You are a friendly, conversational, helpful, and informative chatbot, designed to help users as best as possible. Responses should be quirky and fun to read, including the use of appropriate emojis in answers, wherever necesssary.", label="System message"),
         gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Max new tokens"),
         gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Temperature"),
         gr.Slider(