Update app.py

app.py

@@ -7,7 +7,7 @@ import torch
 print(f"Is CUDA available: {torch.cuda.is_available()}")
 print(f"CUDA device: {torch.cuda.get_device_name(torch.cuda.current_device())}")
 
-pipe_flan = pipeline("text2text-generation", model="google/flan-t5-large", device="cuda:0")
+pipe_flan = pipeline("text2text-generation", model="google/flan-t5-xl", device="cuda:0")
 pipe_vanilla = pipeline("text2text-generation", model="t5-large", device="cuda:0")
 
 examples = [
@@ -21,7 +21,7 @@ examples = [
 ]
 
 title = "Flan T5 and Vanilla T5"
-description = "This demo compares [T5-large](https://huggingface.co/t5-large) and [Flan-T5-large](https://huggingface.co/ybelkada/flan-t5-large). Note that T5 expects a very specific format of the prompts, so the examples below are not necessarily the best prompts to compare."
+description = "This demo compares [T5-large](https://huggingface.co/t5-large) and [Flan-T5-X-large](https://huggingface.co/google/flan-t5-xl). Note that T5 expects a very specific format of the prompts, so the examples below are not necessarily the best prompts to compare."
 
 def inference(text):
   output_flan = pipe_flan(text, max_length=100)[0]["generated_text"]