1

app.py

@@ -2,7 +2,7 @@ import os
 import gradio as gr
 from huggingface_hub import InferenceClient
 
-# Получаем токен из переменных окружения
+# Инициализация клиента с токеном
 client = InferenceClient(os.getenv("HUGGINGFACE_TOKEN"))
 
 def respond(
@@ -25,23 +25,28 @@ def respond(
 
     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
+    try:
+        for message in client.chat_completion(
+            model="sambanovasystems/SambaLingo-Russian-Chat",
+            messages=messages,
+            max_tokens=max_tokens,
+            stream=True,
+            temperature=temperature,
+            top_p=top_p,
+        ):
+            token = message.choices[0].delta.content
+            response += token
+            yield response
+    except Exception as e:
+        print(f"Error: {e}")
+        yield "Произошла ошибка при обработке вашего запроса."
 
 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.Textbox(value="Ты дружелюбный чат-бот.", label="Системное сообщение"),
+        gr.Slider(minimum=1, maximum=2048, value=512, step=1, label="Максимум новых токенов"),
+        gr.Slider(minimum=0.1, maximum=4.0, value=0.7, step=0.1, label="Температура"),
         gr.Slider(
             minimum=0.1,
             maximum=1.0,