try base

main.py

@@ -21,13 +21,12 @@ token_size_limit = None
 # T5 model can use "any" sequence lenghth, but memory usage is O(L^2).
 # tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-small")
 # model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-small")
-# tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
-# model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-base")
-tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
-model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
+tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-base")
+model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-base")
+# tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-large")
+# model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-large")
 token_size_limit = 512
 
-
 # Too large for 16GB
 # tokenizer = T5Tokenizer.from_pretrained("google/flan-t5-xl")
 # model = T5ForConditionalGeneration.from_pretrained("google/flan-t5-xl")