Update app.py

app.py

@@ -1,70 +1,27 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-
-def respond(
-    message,
-    history: list[dict[str, str]],
-    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="openai/gpt-oss-20b")
-
-    messages = [{"role": "system", "content": system_message}]
-
-    messages.extend(history)
-
-    messages.append({"role": "user", "content": message})
-
-    response = ""
-
-    for message in client.chat_completion(
-        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
-
-        response += token
-        yield response
-
-
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
-chatbot = gr.ChatInterface(
-    respond,
-    type="messages",
-    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)",
-        ),
-    ],
-)
-
-with gr.Blocks() as demo:
-    with gr.Sidebar():
-        gr.LoginButton()
-    chatbot.render()
-
+from transformers import pipeline
+import torch
+
+# Загрузка русской модели (Saiga для чата на русском)
+generator = pipeline("text-generation", model="IlyaGusev/saiga_llama3_8b", torch_dtype=torch.float16)
+
+def chat(message, history):
+    # Промпт для стиля ChatGPT
+    prompt = f"Ты полезный ассистент на русском языке. Отвечай кратко, точно и дружелюбно. Пользователь: {message}\nАссистент:"
+    response = generator(prompt, max_length=200, num_return_sequences=1, temperature=0.7)[0]['generated_text']
+    # Извлекаем ответ
+    ai_reply = response.split("Ассистент:")[-1].strip()
+    history.append((message, ai_reply))
+    return history, ""
+
+# Интерфейс чата
+with gr.Blocks(title="Русский Чат-Бот") as demo:
+    gr.Markdown("# Бесплатный ИИ-Чат на русском\nСпрашивай что угодно!")
+    chatbot = gr.Chatbot(height=400)
+    msg = gr.Textbox(placeholder="Напиши сообщение на русском...")
+    clear = gr.Button("Очистить")
+    msg.submit(chat, [msg, chatbot], [chatbot, msg])
+    clear.click(lambda: None, None, chatbot, queue=False)
 
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()