update README, fixed a minor bug in tokenizer

README.md

@@ -7,20 +7,20 @@ datasets:
 - wikipedia
 ---
 
-# Model Card for Japanese BART V2 large
+# Model Card for Japanese BART large
 
 ## Model description
 
-This is a Japanese BART V2 large model pre-trained on Japanese Wikipedia.
+This is a Japanese BART large model pre-trained on Japanese Wikipedia.
 
 ## How to use
 
 You can use this model as follows:
 
 ```python
-from transformers import XLMRobertaTokenizer, MBartForConditionalGeneration
-tokenizer = XLMRobertaTokenizer.from_pretrained('ku-nlp/bart-v2-large-japanese')
-model = MBartForConditionalGeneration.from_pretrained('ku-nlp/bart-v2-large-japanese')
+from transformers import AutoTokenizer, MBartForConditionalGeneration
+tokenizer = AutoTokenizer.from_pretrained('ku-nlp/bart-large-japanese')
+model = MBartForConditionalGeneration.from_pretrained('ku-nlp/bart-large-japanese')
 sentence = '京都 大学 で 自然 言語 処理 を 専攻 する 。'  # input should be segmented into words by Juman++ in advance
 encoding = tokenizer(sentence, return_tensors='pt')
 ...

tokenizer_config.json

@@ -1,5 +1,6 @@
 {
   "bos_token": "<s>",
+  "clean_up_tokenization_spaces": true,
   "cls_token": "<s>",
   "eos_token": "</s>",
   "mask_token": {
@@ -10,6 +11,7 @@
     "rstrip": false,
     "single_word": false
   },
+  "model_max_length": 1000000000000000019884624838656,
   "pad_token": "<pad>",
   "sep_token": "</s>",
   "sp_model_kwargs": {},