File size: 596 Bytes
422fadf
 
 
 
8cc0de9
f003591
422fadf
f003591
 
e48d20b
8b7fa33
 
1
2
3
4
5
6
7
8
9
10
11
12
13
import streamlit as st
from tokenizers.tools import EncodingVisualizer
from transformers import AutoTokenizer
st.set_page_config(page_title="BigScience Tokenizer", page_icon='👩‍💻', layout="wide")
tokenizer = AutoTokenizer.from_pretrained('bigscience/tokenizer', use_auth_token=st.secrets["AUTH_TOKEN"])
visualizer = EncodingVisualizer(tokenizer=tokenizer._tokenizer, default_to_notebook=False)
text = st.text_area(label="", placeholder="Text to tokenize")
button_clicked = st.button("Tokenize")
if text or button_clicked:
    st.components.v1.html(visualizer(text), height=1500)