stuff

app.py

@@ -1,61 +1,32 @@
 import os
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-# Получаем токен из секрета
-hf_token = os.environ.get("HUGGINGFACE_TOKEN")
-
-client = InferenceClient("sambanovasystems/SambaLingo-Russian-Chat", token=hf_token)
-
-
-def respond(
-    message,
-    history: list[tuple[str, str]],
-    system_message,
-    max_tokens,
-    temperature,
-    top_p,
-):
-    messages = [{"role": "system", "content": system_message}]
-
-    for val in history:
-        if val[0]:
-            messages.append({"role": "user", "content": val[0]})
-        if val[1]:
-            messages.append({"role": "assistant", "content": val[1]})
-
-    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,
-    ):
-        token = message.choices[0].delta.content
-        response += token
-        yield response
-
-
-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)",
-        ),
-    ],
+from transformers import DistilGPT2Tokenizer, DistilGPT2LMHeadModel
+import torch
+
+# Импортируем токены из переменных окружения
+HUGGINGFACE_TOKEN = os.getenv("HUGGINGFACE_TOKEN")
+TG_TOKEN = os.getenv("TG_TOKEN")
+
+# Загрузка модели и токенизатора с использованием токена
+model_name = "distilgpt2"
+tokenizer = DistilGPT2Tokenizer.from_pretrained(model_name, use_auth_token=HUGGINGFACE_TOKEN)
+model = DistilGPT2LMHeadModel.from_pretrained(model_name, use_auth_token=HUGGINGFACE_TOKEN)
+
+# Функция для ведения диалога
+def chat_with_model(user_input):
+    input_ids = tokenizer.encode(user_input + tokenizer.eos_token, return_tensors='pt')
+    chat_history_ids = model.generate(input_ids, max_length=100, pad_token_id=tokenizer.eos_token_id)
+    bot_response = tokenizer.decode(chat_history_ids[:, input_ids.shape[-1]:][0], skip_special_tokens=True)
+    return bot_response
+
+# Создание интерфейса Gradio
+iface = gr.Interface(
+    fn=chat_with_model,
+    inputs="text",
+    outputs="text",
+    title="Чатбот на DistilGPT",
+    description="Поболтай со своим чатботом!"
 )
 
-
-if __name__ == "__main__":
-    demo.launch()
+# Запуск интерфейса
+iface.launch()

requirements.txt

@@ -1,3 +1,4 @@
 huggingface_hub==0.22.2
 minijinja
-transformers
+transformers
+torch