switch to flan

main.py

@@ -12,21 +12,20 @@ from transformers import T5Tokenizer, T5ForConditionalGeneration
 token_size_limit = None
 
 # FROM: https://huggingface.co/facebook/blenderbot-400M-distill?text=Hey+my+name+is+Thomas%21+How+are+you%3F
-tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")
-model = AutoModelForSeq2SeqLM.from_pretrained(
-    "facebook/blenderbot-400M-distill")
+# tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-400M-distill")
+# model = AutoModelForSeq2SeqLM.from_pretrained("facebook/blenderbot-400M-distill")
 # tokenizer = AutoTokenizer.from_pretrained("facebook/blenderbot-1B-distill")
 # model = AutoModelForSeq2SeqLM.from_pretrained("facebook/blenderbot-1B-distill")
-token_size_limit = 128
+# token_size_limit = 128
 
 # 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")
-# token_size_limit = 512
+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")