Update app.py

app.py

@@ -3,8 +3,8 @@ import time
 from transformers import AutoModelForCausalLM, AutoTokenizer
 import torch
 
-model = AutoModelForCausalLM.from_pretrained("facebook/opt-30b", torch_dtype=torch.float16).cuda()
-tokenizer = AutoTokenizer.from_pretrained("facebook/opt-30b", use_fast=False)
+model = AutoModelForCausalLM.from_pretrained("facebook/opt-13b", torch_dtype=torch.float16).cuda()
+tokenizer = AutoTokenizer.from_pretrained("facebook/opt-13b", use_fast=False)
 
 @st.cache(allow_output_mutation=True)
 def opt_model(prompt, model, tokenizer, num_sequences = 1, max_length = 50):