switch to 400M model

main.py

@@ -12,10 +12,11 @@ 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-1B-distill")
-model = AutoModelForSeq2SeqLM.from_pretrained("facebook/blenderbot-1B-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
 
 # T5 model can use "any" sequence lenghth, but memory usage is O(L^2).