Update README.md

README.md

@@ -13,15 +13,17 @@ news articles using a transformer model**.
 ## Usage
 ```python
 from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
-tokenizer = AutoTokenizer.from_pretrained("LukasStankevicius/t5-base-lithuanian-news-summaries-175")
-model = AutoModelForSeq2SeqLM.from_pretrained("LukasStankevicius/t5-base-lithuanian-news-summaries-175")
+name = "LukasStankevicius/t5-base-lithuanian-news-summaries-175"
+tokenizer = AutoTokenizer.from_pretrained(name)
+model = AutoModelForSeq2SeqLM.from_pretrained(name)
 
 def decode(x):
     return tokenizer.decode(x, skip_special_tokens=True)
     
 def summarize(text_, **g_kwargs):
   text_ = ' '.join(text_.strip().split())
-  input_dict = tokenizer(text_,  padding=True, return_tensors="pt", return_attention_mask=True)
+  input_dict = tokenizer(text_,  padding=True, return_tensors="pt", 
+                         return_attention_mask=True)
   output = model.generate(**input_dict, **g_kwargs)
   predicted = list(map(decode, output.tolist()))[0]
   return predicted
@@ -39,7 +41,8 @@ Tarp žaidėjų, kurie sužaidė bent po 50 oficialių rungtynių Lietuvos rinkt
 ```
 The summary can be obtained by:
 ```
-g_kwargs = dict(max_length=512, num_beams=10, no_repeat_ngram_size=2, early_stopping=True)
+g_kwargs = dict(max_length=512, num_beams=10, no_repeat_ngram_size=2, 
+                early_stopping=True)
 summarize(text, **g_kwargs)
 ```
 Output from above would be: