update 3 app.py

app.py

@@ -1,58 +1,17 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
+from transformers import pipeline
 
-# Initialize the InferenceClient with the model
-client = InferenceClient("LLM360/K2-Chat")
+# Загрузка модели
+model = pipeline("conversational", model="LLM360/K2-Chat")
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    # Prepare the messages for the model
-    messages = [{"role": "system", "content": system_message}]
+def chat(message, history):
+    history.append((message, ""))
+    response = model(history)
+    history[-1] = (message, response[0]['generated_text'])
+    return history, ""
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Создание интерфейса
+iface = gr.ChatInterface(chat)
 
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    # Generate the response from the model
-    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
-        response += token
-        yield response
-
-# Create a Gradio ChatInterface
-demo = gr.ChatInterface(
-    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.Slider(
-            minimum=0.1,
-            maximum=1.0,
-            value=0.95,
-            step=0.05,
-            label="Top-p (nucleus sampling)",
-        ),
-    ],
-)
-
-if __name__ == "__main__":
-    demo.launch()
+# Запуск интерфейса
+iface.launch()