Update app.py

app.py

@@ -4,6 +4,7 @@ import gradio as gr
 from transformers import AutoModelForCausalLM, AutoTokenizer
 from threading import Thread
 from transformers import TextIteratorStreamer
+import spaces
 
 model_name = "numfa/numfa_v2-3b"
 model = AutoModelForCausalLM.from_pretrained(model_name,torch_dtype=torch.float16, device_map="auto")
@@ -13,6 +14,7 @@ if tokenizer.pad_token_id is None:
 
 streamer = TextIteratorStreamer(tokenizer, timeout=10.0, skip_prompt=True, skip_special_tokens = True)
 
+@spaces.GPU
 def generate_text(prompt, max_length, top_p, top_k):
     inputs = tokenizer([prompt], return_tensors="pt")
 
@@ -43,4 +45,4 @@ outputs = [gr.Textbox(label="Generated Text")]
 
 demo = gr.Interface(fn=generate_text, inputs=inputs, outputs=outputs, allow_flagging=False, description=description)
 
-demo.launch()
+demo.queue(max_size=20).launch()