added zerogpu support

app.py

@@ -15,6 +15,7 @@ from src.data.transforms import transform_test
 
 from transformers import StoppingCriteria, StoppingCriteriaList, TextIteratorStreamer
 import gradio as gr
+import spaces
 
 from langchain_core.output_parsers import StrOutputParser
 from langchain_core.prompts import ChatPromptTemplate
@@ -26,7 +27,7 @@ GROQ_API_KEY = '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'
 os.environ["GROQ_API_KEY"] = GROQ_API_KEY
 
 # Initialize LLM
-llm = ChatGroq(model="llama-3.1-70b-versatile", temperature=0, max_tokens=1024, max_retries=2)
+llm = ChatGroq(model="llama-3.1-8b-instant", temperature=0, max_tokens=1024, max_retries=2)
 
 # QA system prompt and chain
 qa_system_prompt = """
@@ -179,9 +180,10 @@ custom_css = """
 }
 """
 
-
+@spaces.GPU
 def respond_to_user(image, message):
     # Process the image and message here
+    device = torch.device("cuda" if torch.cuda.is_available() else "cpu")
     chat = Chat(model,transform,df,tar_img_feats, device)
     chat.encode_image(image)
     data = chat.ask()