Update app.py

app.py

@@ -1,55 +1,39 @@
 import gradio as gr
-from llama_cpp import Llama
+from ctransformers import AutoModelForCausalLM
 
-model_path = "Llight.Q8_0.gguf"
-
-llm = Llama(model_path=model_path)
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-
-    prompt = system_message + "\n"
-    
-    for user_input, bot_response in history:
-        if user_input:
-            prompt += f"User: {user_input}\n"
-        if bot_response:
-            prompt += f"Assistant: {bot_response}\n"
-    
-    prompt += f"User: {message}\nAssistant:"
-
-    response = llm(
-        prompt,
-        max_tokens=max_tokens,
-        temperature=temperature,
-        top_p=top_p,
+def load_model():
+    model = AutoModelForCausalLM.from_pretrained(
+        "Llight.Q8_0.gguf",
+        model_type="llama",
+        gpu_layers=0
     )
-
-    generated_text = response["choices"][0]["text"]
-    yield generated_text
-
-# Gradio интерфейс
-demo = gr.ChatInterface(
-    respond,
-    additional_inputs=[
-        gr.Textbox(value="Ты дружелюбный чатбот.", 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(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
+    return model
+
+def generate_response(prompt, max_tokens=128, temperature=0.7):
+    try:
+        model = load_model()
+        response = model(
+            prompt,
+            max_tokens=max_tokens,
+            temperature=temperature
+        )
+        return response
+    except Exception as e:
+        return f"Произошла ошибка: {str(e)}"
+
+# Создаем интерфейс
+demo = gr.Interface(
+    fn=generate_response,
+    inputs=[
+        gr.Textbox(label="Введите ваш запрос", lines=3),
+        gr.Slider(minimum=1, maximum=512, value=128, label="Max Tokens"),
+        gr.Slider(minimum=0.1, maximum=2.0, value=0.7, label="Temperature"),
     ],
+    outputs=gr.Textbox(label="Ответ модели", lines=5),
+    title="LLight Model Demo",
+    description="Демонстрация работы GGUF модели"
 )
 
+# Запускаем приложение
 if __name__ == "__main__":
     demo.launch()