Update app.py

app.py

@@ -1,11 +1,8 @@
 import gradio as gr
-from huggingface_hub import InferenceClient
-
-"""
-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")
+from transformers import pipeline
 
+# Загрузка модели Marco-o1
+pipe = pipeline("text-generation", model="AIDC-AI/Marco-o1")
 
 def respond(
     message,
@@ -15,30 +12,31 @@ def respond(
     temperature,
     top_p,
 ):
-    messages = [{"role": "system", "content": system_message}]
-
+    messages = [system_message]
+    
     for val in history:
         if val[0]:
-            messages.append({"role": "user", "content": val[0]})
+            messages.append(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,
+            messages.append(val[1])
+
+    messages.append(message)
+    
+    # Объединяем все сообщения в одну строку для передачи в модель
+    input_text = "\n".join(messages)
+    
+    response = pipe(
+        input_text,
+        max_length=max_tokens + len(input_text),
         temperature=temperature,
         top_p=top_p,
-    ):
-        token = message.choices[0].delta.content
-
-        response += token
-        yield response
-
+        num_return_sequences=1
+    )[0]['generated_text']
+    
+    # Извлекаем новый ответ, исключая входные сообщения
+    new_response = response[len(input_text):].strip()
+    
+    yield new_response
 
 """
 For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
@@ -59,6 +57,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()