Update app.py

app.py

@@ -1,64 +1,136 @@
-import gradio as gr
-from huggingface_hub import InferenceClient
+# Установка необходимых библиотек:
+# pip install gradio huggingface_hub torch transformers
 
-"""
-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")
+import gradio as gr
+from huggingface_hub import hf_hub_download
+from transformers import GPTJForCausalLM, AutoTokenizer
+import torch
 
+# Путь к модели на Hugging Face
+MODEL_REPO = "EleutherAI/gpt-j-6B"
 
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
+# Загрузка токенизатора
+tokenizer = AutoTokenizer.from_pretrained(MODEL_REPO)
 
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
+# Загрузка модели
+model = GPTJForCausalLM.from_pretrained(
+    MODEL_REPO,
+    revision="float16",
+    torch_dtype=torch.float16,
+    low_cpu_mem_usage=True
+).to("cuda" if torch.cuda.is_available() else "cpu")
 
-    messages.append({"role": "user", "content": message})
+# Функция для генерации ответов
+def generate_response(prompt, history=[]):
+    # Объединение истории в один контекст
+    input_text = "".join([f"User: {item[0]}\nBot: {item[1]}\n" for item in history])
+    input_text += f"User: {prompt}\nBot:"
 
-    response = ""
+    # Токенизация
+    input_ids = tokenizer.encode(input_text, return_tensors="pt").to(model.device)
 
-    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
+    # Генерация
+    with torch.no_grad():
+        output = model.generate(
+            input_ids,
+            max_length=1024,
+            temperature=0.7,
+            top_p=0.9,
+            do_sample=True,
+            pad_token_id=tokenizer.eos_token_id
+        )
 
-        response += token
-        yield response
+    # Декодирование и извлечение ответа
+    response = tokenizer.decode(output[0], skip_special_tokens=True)
+    response = response.split("User:")[-1].split("Bot:")[-1].strip()
 
+    # Обновление истории
+    history.append((prompt, response))
+    return history, history
 
+# Кастомный CSS для интерфейса
+custom_css = """
+body {
+    font-family: 'Segoe UI', Tahoma, Geneva, Verdana, sans-serif;
+    background-color: #f0f2f5;
+    margin: 0;
+    padding: 0;
+}
+#chatbot-container {
+    width: 80%;
+    max-width: 800px;
+    margin: 50px auto;
+    background: #fff;
+    border-radius: 10px;
+    box-shadow: 0 4px 20px rgba(0, 0, 0, 0.1);
+    overflow: hidden;
+    animation: fadeIn 0.5s ease-in-out;
+}
+@keyframes fadeIn {
+    from { opacity: 0; transform: translateY(20px); }
+    to { opacity: 1; transform: translateY(0); }
+}
+.chat-message {
+    display: flex;
+    align-items: flex-start;
+    padding: 15px;
+    border-bottom: 1px solid #f0f0f0;
+    animation: slideIn 0.3s ease-in-out;
+}
+@keyframes slideIn {
+    from { opacity: 0; transform: translateX(-20px); }
+    to { opacity: 1; transform: translateX(0); }
+}
+.chat-message.user .message-content {
+    background-color: #0078d7;
+    color: #fff;
+    border-radius: 15px 15px 0 15px;
+    padding: 10px 15px;
+    max-width: 70%;
+    margin-left: auto;
+}
+.chat-message.bot .message-content {
+    background-color: #e1e1e1;
+    color: #333;
+    border-radius: 15px 15px 15px 0;
+    padding: 10px 15px;
+    max-width: 70%;
+    margin-right: auto;
+}
+input[type="text"] {
+    width: calc(100% - 20px);
+    margin: 10px;
+    padding: 10px;
+    border: 1px solid #ccc;
+    border-radius: 5px;
+    font-size: 16px;
+}
+button {
+    background-color: #0078d7;
+    color: #fff;
+    border: none;
+    padding: 10px 20px;
+    margin: 10px;
+    border-radius: 5px;
+    cursor: pointer;
+    font-size: 16px;
+    transition: background-color 0.3s;
+}
+button:hover {
+    background-color: #005bb5;
+}
 """
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/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)",
-        ),
-    ],
-)
 
+# Интерфейс Gradio
+with gr.Blocks(css=custom_css) as chat_interface:
+    gr.Markdown("# 🧠 Умный Чат с GPT-J-6B")
+    with gr.Box(elem_id="chatbot-container"):
+        chatbot = gr.Chatbot()
+        user_input = gr.Textbox(placeholder="Введите сообщение...")
+        clear_btn = gr.Button("Очистить историю")
+
+    user_input.submit(generate_response, [user_input, chatbot], [chatbot, user_input])
+    clear_btn.click(lambda: None, None, chatbot)
 
-if __name__ == "__main__":
-    demo.launch()
+# Запуск приложения
+chat_interface.launch(debug=True)