Spaces:
Sleeping
Sleeping
Commit
•
8821400
1
Parent(s):
05bfc25
Update QuestionAnswering.py
Browse files- QuestionAnswering.py +74 -74
QuestionAnswering.py
CHANGED
@@ -1,75 +1,75 @@
|
|
1 |
-
from os import path
|
2 |
-
import streamlit as st
|
3 |
-
import tensorflow as tf
|
4 |
-
from transformers import ElectraTokenizerFast, TFElectraForQuestionAnswering
|
5 |
-
|
6 |
-
model_hf = 'nguyennghia0902/bestfailed_electra-small-discriminator_5e-05_16'
|
7 |
-
tokenizer = ElectraTokenizerFast.from_pretrained(model_hf)
|
8 |
-
reload_model = TFElectraForQuestionAnswering.from_pretrained(model_hf)
|
9 |
-
|
10 |
-
@st.cache_resource
|
11 |
-
def predict(question, context):
|
12 |
-
inputs = tokenizer(question, context, return_offsets_mapping=True,return_tensors="tf",max_length=512, truncation=True)
|
13 |
-
offset_mapping = inputs.pop("offset_mapping")
|
14 |
-
outputs = reload_model(**inputs)
|
15 |
-
answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0])
|
16 |
-
answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])
|
17 |
-
start_char = offset_mapping[0][answer_start_index][0]
|
18 |
-
end_char = offset_mapping[0][answer_end_index][1]
|
19 |
-
predicted_answer_text = context[start_char:end_char]
|
20 |
-
|
21 |
-
return predicted_answer_text
|
22 |
-
|
23 |
-
def main():
|
24 |
-
st.set_page_config(page_title="Question Answering", page_icon="📝")
|
25 |
-
|
26 |
-
# giving a title to our page
|
27 |
-
col1, col2 = st.columns([2, 1])
|
28 |
-
col1.title("Question Answering")
|
29 |
-
|
30 |
-
col2.link_button("Explore my model",
|
31 |
-
|
32 |
-
question = st.text_area(
|
33 |
-
"QUESTION: Please enter a question:",
|
34 |
-
placeholder="Enter your question here",
|
35 |
-
height=15,
|
36 |
-
)
|
37 |
-
text = st.text_area(
|
38 |
-
"CONTEXT: Please enter a context:",
|
39 |
-
placeholder="Enter your context here",
|
40 |
-
height=100,
|
41 |
-
)
|
42 |
-
|
43 |
-
prediction = ""
|
44 |
-
|
45 |
-
upload_file = st.file_uploader("CONTEXT: Or upload a file with some contexts", type=["txt"])
|
46 |
-
if upload_file is not None:
|
47 |
-
text = upload_file.read().decode("utf-8")
|
48 |
-
|
49 |
-
for line in text.splitlines():
|
50 |
-
line = line.strip()
|
51 |
-
if not line:
|
52 |
-
continue
|
53 |
-
|
54 |
-
prediction = predict(question, line)
|
55 |
-
|
56 |
-
st.success(line + "\n\n" + prediction)
|
57 |
-
|
58 |
-
|
59 |
-
# Create a prediction button
|
60 |
-
elif st.button("Predict"):
|
61 |
-
prediction = ""
|
62 |
-
stripped_text = text.strip()
|
63 |
-
if not stripped_text:
|
64 |
-
st.error("Please enter a context.")
|
65 |
-
return
|
66 |
-
stripped_question = question.strip()
|
67 |
-
if not stripped_question:
|
68 |
-
st.error("Please enter a question.")
|
69 |
-
return
|
70 |
-
|
71 |
-
prediction = predict(stripped_question, stripped_text)
|
72 |
-
st.success(prediction)
|
73 |
-
|
74 |
-
if __name__ == "__main__":
|
75 |
main()
|
|
|
1 |
+
from os import path
|
2 |
+
import streamlit as st
|
3 |
+
import tensorflow as tf
|
4 |
+
from transformers import ElectraTokenizerFast, TFElectraForQuestionAnswering
|
5 |
+
|
6 |
+
model_hf = 'nguyennghia0902/bestfailed_electra-small-discriminator_5e-05_16'
|
7 |
+
tokenizer = ElectraTokenizerFast.from_pretrained(model_hf)
|
8 |
+
reload_model = TFElectraForQuestionAnswering.from_pretrained(model_hf)
|
9 |
+
|
10 |
+
@st.cache_resource
|
11 |
+
def predict(question, context):
|
12 |
+
inputs = tokenizer(question, context, return_offsets_mapping=True,return_tensors="tf",max_length=512, truncation=True)
|
13 |
+
offset_mapping = inputs.pop("offset_mapping")
|
14 |
+
outputs = reload_model(**inputs)
|
15 |
+
answer_start_index = int(tf.math.argmax(outputs.start_logits, axis=-1)[0])
|
16 |
+
answer_end_index = int(tf.math.argmax(outputs.end_logits, axis=-1)[0])
|
17 |
+
start_char = offset_mapping[0][answer_start_index][0]
|
18 |
+
end_char = offset_mapping[0][answer_end_index][1]
|
19 |
+
predicted_answer_text = context[start_char:end_char]
|
20 |
+
|
21 |
+
return predicted_answer_text
|
22 |
+
|
23 |
+
def main():
|
24 |
+
st.set_page_config(page_title="Question Answering", page_icon="📝")
|
25 |
+
|
26 |
+
# giving a title to our page
|
27 |
+
col1, col2 = st.columns([2, 1])
|
28 |
+
col1.title("Question Answering")
|
29 |
+
|
30 |
+
col2.link_button("Explore my model", 'https://huggingface.co/'+model_hf)
|
31 |
+
|
32 |
+
question = st.text_area(
|
33 |
+
"QUESTION: Please enter a question:",
|
34 |
+
placeholder="Enter your question here",
|
35 |
+
height=15,
|
36 |
+
)
|
37 |
+
text = st.text_area(
|
38 |
+
"CONTEXT: Please enter a context:",
|
39 |
+
placeholder="Enter your context here",
|
40 |
+
height=100,
|
41 |
+
)
|
42 |
+
|
43 |
+
prediction = ""
|
44 |
+
|
45 |
+
upload_file = st.file_uploader("CONTEXT: Or upload a file with some contexts", type=["txt"])
|
46 |
+
if upload_file is not None:
|
47 |
+
text = upload_file.read().decode("utf-8")
|
48 |
+
|
49 |
+
for line in text.splitlines():
|
50 |
+
line = line.strip()
|
51 |
+
if not line:
|
52 |
+
continue
|
53 |
+
|
54 |
+
prediction = predict(question, line)
|
55 |
+
|
56 |
+
st.success(line + "\n\n" + prediction)
|
57 |
+
|
58 |
+
|
59 |
+
# Create a prediction button
|
60 |
+
elif st.button("Predict"):
|
61 |
+
prediction = ""
|
62 |
+
stripped_text = text.strip()
|
63 |
+
if not stripped_text:
|
64 |
+
st.error("Please enter a context.")
|
65 |
+
return
|
66 |
+
stripped_question = question.strip()
|
67 |
+
if not stripped_question:
|
68 |
+
st.error("Please enter a question.")
|
69 |
+
return
|
70 |
+
|
71 |
+
prediction = predict(stripped_question, stripped_text)
|
72 |
+
st.success(prediction)
|
73 |
+
|
74 |
+
if __name__ == "__main__":
|
75 |
main()
|