taka-yamakoshi commited on
Commit
dc80c0d
1 Parent(s): ed9112c

minor update on instructions

Browse files
Files changed (1) hide show
  1. app.py +5 -4
app.py CHANGED
@@ -98,7 +98,8 @@ if __name__=='__main__':
98
  st.markdown(generate_markdown('quick and easy way to explore how tokenizers work',size=24), unsafe_allow_html=True)
99
 
100
  # Select and load the tokenizer
101
- tokenizer_name = st.sidebar.selectbox('1. Choose the tokenizer from below',
 
102
  ('bert-base-uncased','bert-large-cased',
103
  'gpt2','gpt2-large',
104
  'roberta-base','roberta-large',
@@ -106,11 +107,11 @@ if __name__=='__main__':
106
  tokenizer = load_model(tokenizer_name)
107
 
108
  st.sidebar.write('2. Optional settings')
109
- st.sidebar.write(f'"Compare two texts" compares # tokens for two pieces of text '\
110
- +f'and "de-tokenize" converts a list of tokenized indices back to strings.')
111
- st.sidebar.write(f'For "de-tokenize", make sure to type in integers, separated by single spaces')
112
  comparison_mode = st.sidebar.checkbox('Compare two texts')
113
  detokenize = st.sidebar.checkbox('de-tokenize')
 
 
 
114
  if comparison_mode:
115
  sent_cols = st.columns(2)
116
  num_tokens = {}
 
98
  st.markdown(generate_markdown('quick and easy way to explore how tokenizers work',size=24), unsafe_allow_html=True)
99
 
100
  # Select and load the tokenizer
101
+ st.sidebar.write('1. Choose the tokenizer from below')
102
+ tokenizer_name = st.sidebar.selectbox('',
103
  ('bert-base-uncased','bert-large-cased',
104
  'gpt2','gpt2-large',
105
  'roberta-base','roberta-large',
 
107
  tokenizer = load_model(tokenizer_name)
108
 
109
  st.sidebar.write('2. Optional settings')
 
 
 
110
  comparison_mode = st.sidebar.checkbox('Compare two texts')
111
  detokenize = st.sidebar.checkbox('de-tokenize')
112
+ st.sidebar.write(f'"Compare two texts" compares # tokens for two pieces of text '\
113
+ +f'and "de-tokenize" converts a list of tokenized indices back to strings.')
114
+ st.sidebar.write(f'For "de-tokenize", make sure to type in integers, separated by single spaces.')
115
  if comparison_mode:
116
  sent_cols = st.columns(2)
117
  num_tokens = {}