File size: 8,413 Bytes
8cef51d 14d6210 8cef51d cd1b02d 8cef51d cd1b02d 8cef51d cd1b02d 8cef51d 7e4c181 8cef51d 5bfad50 f0d994d ec6cd8b 5bfad50 f0d994d cd1b02d f0d994d cd1b02d 14d6210 cd1b02d 14d6210 26a881e 14d6210 cd1b02d 14d6210 cd1b02d 14d6210 a6c81cd 14d6210 cd1b02d f0d994d cd1b02d 14d6210 f0d994d cd1b02d 14d6210 cd1b02d f0d994d 14d6210 f0d994d 14d6210 8cef51d f0d994d 8cef51d f0d994d 8cef51d f0d994d 8cef51d f0d994d 8cef51d f0d994d 8cef51d f0d994d cd1b02d f0d994d cd1b02d f0d994d 8cef51d cd1b02d 8cef51d f0d994d |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 |
import streamlit as st
from transformers import pipeline
from io import StringIO
unmasker = pipeline('fill-mask', model='dsfsi/zabantu-ven-120m')
st.set_page_config(layout="wide")
def fill_mask(sentences):
results = {}
warnings = []
for sentence in sentences:
if "<mask>" in sentence:
unmasked = unmasker(sentence)
results[sentence] = unmasked
else:
warnings.append(f"Warning: No <mask> token found in sentence: {sentence}")
return results, warnings
def replace_mask(sentence, predicted_word):
return sentence.replace("<mask>", f"**{predicted_word}**")
st.write(f"")
img1, img2, img3 = st.columns(3)
with img2:
with st.container(border=False):
st.image("logo_transparent_small.png")
st.markdown("""
<div style='text-align: center;'>
<a href='https://github.com/dsfsi' target='_blank'>Github</a> |
<a href='https://docs.google.com/forms/d/e/1FAIpQLSf7S36dyAUPx2egmXbFpnTBuzoRulhL5Elu-N1eoMhaO7v10w/viewform' target='_blank'>Feedback Form</a> |
<a href='https://huggingface.co./papers/1911.02116' target='_blank'>arxiv</a>
</div>
""", unsafe_allow_html=True)
st.markdown("""
<div style='text-align: center;'>
<h2>Fill Mask | Zabantu-ven-120m</h2>
</div>
""", unsafe_allow_html=True)
st.write(f"")
st.markdown("This is a variant of Zabantu pre-trained on a monolingual dataset of Tshivenda(ven) sentences on a transformer network with 120 million traininable parameters.")
with st.expander("More information about the space"):
st.write('''
Authors: Alexis Conneau, Kartikay Khandelwal, Naman Goyal, Vishrav Chaudhary, Guillaume Wenzek, Francisco Guzmán, Edouard Grave, Myle Ott, Luke Zettlemoyer, Veselin Stoyanov
''')
cit1,cit2 = st.columns(2)
# with cit1:
# with cit2:
col1, col2 = st.columns(2)
if 'text_input' not in st.session_state:
st.session_state['text_input'] = ""
if 'warnings' not in st.session_state:
st.session_state['warnings'] = []
with col1:
with st.container(border=True):
st.markdown("Input :clipboard:")
select_options = ['Choose option', 'Enter text input', 'Upload a file(csv/txt)']
sample_sentence = "Vhana vhane vha kha ḓi bva u bebwa vha kha khombo ya u <mask> nga Listeriosis."
option_selected = st.selectbox(f"Select an input option:", select_options, index=0)
if option_selected == 'Enter text input':
text_input = st.text_area(
"Enter sentences with <mask> token(one sentence per line):",
value=st.session_state['text_input']
)
input_sentences = text_input.split("\n")
if st.button("Submit",use_container_width=True):
result, warnings = fill_mask(input_sentences)
st.session_state['warnings'] = warnings
if option_selected == 'Upload a file(csv/txt)':
uploaded_file = st.file_uploader("Choose a file-(one sentence per line)")
if uploaded_file is not None:
stringio = StringIO(uploaded_file.getvalue().decode("utf-8"))
string_data = stringio.read()
input_sentences = string_data.split("\n")
if st.button("Submit",use_container_width=True):
result, warnings = fill_mask(input_sentences)
st.session_state['warnings'] = warnings
if st.session_state['warnings']:
for warning in st.session_state['warnings']:
st.warning(warning)
st.markdown("Example")
st.code(sample_sentence, wrap_lines=True)
if st.button("Test Example",use_container_width=True):
result, warnings = fill_mask(sample_sentence.split("\n"))
with col2:
with st.container(border=True):
st.markdown("Output :bar_chart:")
if 'result' in locals() and result:
if len(result) == 1:
for sentence, predictions in result.items():
for prediction in predictions:
predicted_word = prediction['token_str']
score = prediction['score'] * 100
st.markdown(f"""
<div class="bar">
<div class="bar-fill" style="width: {score}%;"></div>
</div>
<div class="container">
<div style="align-items: left;">{predicted_word}</div>
<div style="align-items: center;">{score:.2f}%</div>
</div>
""", unsafe_allow_html=True)
else:
index = 0
for sentence, predictions in result.items():
index += 1
if predictions:
top_prediction = predictions[0]
predicted_word = top_prediction['token_str']
score = top_prediction['score'] * 100
st.markdown(f"""
<div class="bar">
<div class="bar-fill" style="width: {score}%;"></div>
</div>
<div class="container">
<div style="align-items: left;">{predicted_word} (line {index})</div>
<div style="align-items: right;">{score:.2f}%</div>
</div>
""", unsafe_allow_html=True)
if 'result' in locals():
if result:
line = 0
for sentence, predictions in result.items():
line += 1
predicted_word = predictions[0]['token_str']
full_sentence = replace_mask(sentence, predicted_word)
st.write(f"**Sentence {line}:** {full_sentence }")
css = """
<style>
footer {display:none !important;}
.gr-button-primary {
z-index: 14;
height: 43px;
width: 130px;
left: 0px;
top: 0px;
padding: 0px;
cursor: pointer !important;
background: none rgb(17, 20, 45) !important;
border: none !important;
text-align: center !important;
font-family: Poppins !important;
font-size: 14px !important;
font-weight: 500 !important;
color: rgb(255, 255, 255) !important;
line-height: 1 !important;
border-radius: 12px !important;
transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
box-shadow: none !important;
}
.gr-button-primary:hover{
z-index: 14;
height: 43px;
width: 130px;
left: 0px;
top: 0px;
padding: 0px;
cursor: pointer !important;
background: none rgb(66, 133, 244) !important;
border: none !important;
text-align: center !important;
font-family: Poppins !important;
font-size: 14px !important;
font-weight: 500 !important;
color: rgb(255, 255, 255) !important;
line-height: 1 !important;
border-radius: 12px !important;
transition: box-shadow 200ms ease 0s, background 200ms ease 0s !important;
box-shadow: rgb(0 0 0 / 23%) 0px 1px 7px 0px !important;
}
.hover\:bg-orange-50:hover {
--tw-bg-opacity: 1 !important;
background-color: rgb(229,225,255) !important;
}
.to-orange-200 {
--tw-gradient-to: rgb(37 56 133 / 37%) !important;
}
.from-orange-400 {
--tw-gradient-from: rgb(17, 20, 45) !important;
--tw-gradient-to: rgb(255 150 51 / 0);
--tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
}
.group-hover\:from-orange-500{
--tw-gradient-from:rgb(17, 20, 45) !important;
--tw-gradient-to: rgb(37 56 133 / 37%);
--tw-gradient-stops: var(--tw-gradient-from), var(--tw-gradient-to) !important;
}
.group:hover .group-hover\:text-orange-500{
--tw-text-opacity: 1 !important;
color:rgb(37 56 133 / var(--tw-text-opacity)) !important;
}
.container {
display: flex;
justify-content: space-between;
align-items: center;
margin-bottom: 5px;
width: 100%;
}
.bar {
# width: 70%;
background-color: #e6e6e6;
border-radius: 12px;
overflow: hidden;
margin-right: 10px;
height: 5px;
}
.bar-fill {
background-color: #17152e;
height: 100%;
border-radius: 12px;
}
</style>
"""
st.markdown(css, unsafe_allow_html=True) |