Update app.py

app.py

@@ -1,11 +1,11 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-For more information on `huggingface_hub` Inference API support, please check the docs: https://huggingface.co/docs/huggingface_hub/v0.22.2/en/guides/inference
-"""
-client = InferenceClient("HuggingFaceH4/zephyr-7b-beta")
+from llama_cpp import Llama
 
+# Load the Mistral model
+llm = Llama.from_pretrained(
+    repo_id="bartowski/Mistral-Small-Instruct-2409-GGUF",
+    filename="Mistral-Small-Instruct-2409-IQ2_M.gguf",
+)
 
 def respond(
     message,
@@ -17,31 +17,22 @@ def respond(
 ):
     messages = [{"role": "system", "content": system_message}]
 
+    # Add history to messages
     for val in history:
         if val[0]:
             messages.append({"role": "user", "content": val[0]})
         if val[1]:
             messages.append({"role": "assistant", "content": val[1]})
 
+    # Add the current user message
     messages.append({"role": "user", "content": message})
 
-    response = ""
+    # Generate the response using the Mistral model
+    response = llm.create_chat_completion(messages=messages)
 
-    for message in client.chat_completion(
-        messages,
-        max_tokens=max_tokens,
-        stream=True,
-        temperature=temperature,
-        top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
+    return response["choices"][0]["message"]["content"]  # Adjust based on your model's output format
 
-        response += token
-        yield response
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+# Set up Gradio Chat Interface
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +49,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()