Annorita commited on
Commit
224f5e0
1 Parent(s): ab98424
Files changed (2) hide show
  1. app.py +5 -2
  2. utils.py +3 -3
app.py CHANGED
@@ -20,9 +20,12 @@ st.sidebar.subheader('Write the input sentence', divider='grey')
20
  input_data = st.sidebar.text_input('Input Sentence', 'Hello world!!!')
21
 
22
 
23
- res = get_res(model_name=model_name, input_sentence=input_data, single_print=False)
24
 
25
  #st.markdown('<style></style>')
26
 
27
  st.subheader('Tokenized result', divider='grey')
28
- st.markdown(res, unsafe_allow_html=True)
 
 
 
 
20
  input_data = st.sidebar.text_input('Input Sentence', 'Hello world!!!')
21
 
22
 
23
+ res, token_num = get_res(model_name=model_name, input_sentence=input_data, single_print=False)
24
 
25
  #st.markdown('<style></style>')
26
 
27
  st.subheader('Tokenized result', divider='grey')
28
+ st.markdown(res, unsafe_allow_html=True)
29
+
30
+ st.subheader('Number of tokens', divider='grey')
31
+ st.write(token_num)
utils.py CHANGED
@@ -17,9 +17,9 @@ def get_res(model_name, input_sentence, single_print=True):
17
  token_num = len(out)
18
 
19
  w = [ f'<span style="background-color:{next(color_iterator)}">{tokenizer.decode(x)}</span>' for x in out ]
20
- res = ''.join(w) + f' {str(token_num)}'
21
  if single_print:
22
- print(res)
23
  else:
24
- return res
25
 
 
17
  token_num = len(out)
18
 
19
  w = [ f'<span style="background-color:{next(color_iterator)}">{tokenizer.decode(x)}</span>' for x in out ]
20
+ res = ''.join(w)
21
  if single_print:
22
+ print(res + str(token_num))
23
  else:
24
+ return res, token_num
25