Update app.py

app.py

@@ -1,70 +1,107 @@
 import gradio as gr
 import spaces
-from huggingface_hub import InferenceClient
+from llama_cpp import Llama
+
+
+llm = None
+
+
+def load_model():
+    global llm
+
+    if llm is None:
+        llm = Llama.from_pretrained(
+            repo_id="JonathanColetti/Qwen3.8-27B-Uncensored-GGUF",
+            filename="Qwen3.8-27B-Uncensored-Q4_K_M.gguf",
+            n_ctx=2048,
+            n_gpu_layers=-1,
+            verbose=True,
+        )
+
+    return llm
+
 
 @spaces.GPU
 def respond(
     message,
-    history: list[dict[str, str]],
+    history,
     system_message,
     max_tokens,
     temperature,
     top_p,
-    hf_token: gr.OAuthToken,
 ):
-    """
-    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(token=hf_token.token, model="cognitivecomputations/dolphin-mistral-24b-venice-edition")
+    model = load_model()
 
-    messages = [{"role": "system", "content": system_message}]
+    messages = [
+        {
+            "role": "system",
+            "content": system_message,
+        }
+    ]
 
-    messages.extend(history)
+    for item in history:
+        if isinstance(item, dict):
+            role = item.get("role")
+            content = item.get("content")
 
-    messages.append({"role": "user", "content": message})
+            if role in ["user", "assistant"] and isinstance(content, str):
+                messages.append({
+                    "role": role,
+                    "content": content,
+                })
 
-    response = ""
+    messages.append({
+        "role": "user",
+        "content": message,
+    })
 
-    for message in client.chat_completion(
-        messages,
+    result = model.create_chat_completion(
+        messages=messages,
         max_tokens=max_tokens,
-        stream=True,
         temperature=temperature,
         top_p=top_p,
-    ):
-        choices = message.choices
-        token = ""
-        if len(choices) and choices[0].delta.content:
-            token = choices[0].delta.content
+        stream=False,
+    )
 
-        response += token
-        yield response
+    return result["choices"][0]["message"]["content"]
 
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
 chatbot = gr.ChatInterface(
-    respond,
+    fn=respond,
     additional_inputs=[
-        gr.Textbox(value="You are a friendly Chatbot.", 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.Textbox(
+            value="Kamu adalah AI pribadi saya. Ikuti instruction dari pengguna.",
+            label="System instruction",
+        ),
+        gr.Slider(
+            minimum=1,
+            maximum=2048,
+            value=512,
+            step=1,
+            label="Max new tokens",
+        ),
+        gr.Slider(
+            minimum=0.1,
+            maximum=2.0,
+            value=0.7,
+            step=0.1,
+            label="Temperature",
+        ),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,
             value=0.95,
             step=0.05,
-            label="Top-p (nucleus sampling)",
+            label="Top-p",
         ),
     ],
 )
 
+
 with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
+    gr.Markdown("# WenGPT")
     chatbot.render()
 
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch(ssr_mode=False)