updatE

app.py

@@ -6,6 +6,7 @@ from threading import Thread
 
 import av
 import gradio as gr
+import spaces
 import torch
 from transformers import AutoModelForImageTextToText, AutoProcessor
 from transformers.generation.streamers import TextIteratorStreamer
@@ -153,6 +154,7 @@ def process_history(history: list[dict]) -> list[dict]:
     return messages
 
 
+@spaces.GPU()
 @torch.inference_mode()
 def generate(message: dict, history: list[dict], system_prompt: str = "", max_new_tokens: int = 512) -> Iterator[str]:
     if not validate_media_constraints(message):

requirements.txt

@@ -1,4 +1,5 @@
 gradio>=4.0.0
+spaces[huggingface]>=0.28.0
 transformers>=4.35.0
 torch>=2.1.0
 av