Update space

app.py

@@ -1,10 +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")
+# Настраиваем клиента для работы с моделью lmms-lab/llama3-llava-next-8b
+client = InferenceClient("lmms-lab/llama3-llava-next-8b")
 
 
 def respond(
@@ -27,6 +25,7 @@ def respond(
 
     response = ""
 
+    # Используем модель lmms-lab/llama3-llava-next-8b для генерации ответа
     for message in client.chat_completion(
         messages,
         max_tokens=max_tokens,
@@ -39,9 +38,8 @@ def respond(
         response += token
         yield response
 
-"""
-For information on how to customize the ChatInterface, peruse the gradio docs: https://www.gradio.app/docs/chatinterface
-"""
+
+# Создаем интерфейс Gradio с использованием модели lmms-lab/llama3-llava-next-8b
 demo = gr.ChatInterface(
     respond,
     additional_inputs=[
@@ -58,6 +56,5 @@ demo = gr.ChatInterface(
     ],
 )
 
-
 if __name__ == "__main__":
-    demo.launch()
+    demo.launch()

requirements.txt

@@ -1 +1,2 @@
-huggingface_hub==0.22.2
+huggingface_hub==0.22.2
+gradio