JulianHame
commited on
Commit
•
b5f0ee1
1
Parent(s):
f6fe135
Update app.py
Browse files
app.py
CHANGED
@@ -12,14 +12,14 @@ selection = "N/A"
|
|
12 |
with col1:
|
13 |
selection = st.radio("Pick one of the four pre-trained models below:",
|
14 |
key = "modelChoice",
|
15 |
-
options = ["DistilBERT", "
|
16 |
)
|
17 |
|
18 |
pipe = pipeline('sentiment-analysis')
|
19 |
if selection == "DistilBERT":
|
20 |
pipe = pipeline(model = "distilbert-base-uncased-finetuned-sst-2-english")
|
21 |
-
if selection == "
|
22 |
-
pipe = pipeline(model = "
|
23 |
if selection == "Twitter-roBERTa":
|
24 |
pipe = pipeline(model = "cardiffnlp/twitter-roberta-base-sentiment-latest")
|
25 |
if selection == "SiEBERT":
|
@@ -27,7 +27,7 @@ if selection == "SiEBERT":
|
|
27 |
|
28 |
with col2:
|
29 |
st.caption('DistilBERT - One of the most popular and widely-used language models. Labels text as POSITIVE or NEGATIVE. Developed by Hugging Face.')
|
30 |
-
st.caption('
|
31 |
st.caption('SiEBERT - A model trained on diverse text sources to improve generalization. Labels text as POSITIVE or NEGATIVE. Developed by siebert.')
|
32 |
st.caption('Twitter-roBERTa - A model trained on over 124M tweets. Labels text as POSITIVE, NEGATIVE or NEUTRAL. Developed by cardiffnlp.')
|
33 |
|
|
|
12 |
with col1:
|
13 |
selection = st.radio("Pick one of the four pre-trained models below:",
|
14 |
key = "modelChoice",
|
15 |
+
options = ["DistilBERT", "Toxicity-Classifier", "SiEBERT", "Twitter-roBERTa"],
|
16 |
)
|
17 |
|
18 |
pipe = pipeline('sentiment-analysis')
|
19 |
if selection == "DistilBERT":
|
20 |
pipe = pipeline(model = "distilbert-base-uncased-finetuned-sst-2-english")
|
21 |
+
if selection == "Toxicity-Classifier":
|
22 |
+
pipe = pipeline(model = "JulianHame/toxicity-classifier")
|
23 |
if selection == "Twitter-roBERTa":
|
24 |
pipe = pipeline(model = "cardiffnlp/twitter-roberta-base-sentiment-latest")
|
25 |
if selection == "SiEBERT":
|
|
|
27 |
|
28 |
with col2:
|
29 |
st.caption('DistilBERT - One of the most popular and widely-used language models. Labels text as POSITIVE or NEGATIVE. Developed by Hugging Face.')
|
30 |
+
st.caption('Toxicity-Classifier - A model trained to classify tweets under different toxicity-related categories.')
|
31 |
st.caption('SiEBERT - A model trained on diverse text sources to improve generalization. Labels text as POSITIVE or NEGATIVE. Developed by siebert.')
|
32 |
st.caption('Twitter-roBERTa - A model trained on over 124M tweets. Labels text as POSITIVE, NEGATIVE or NEUTRAL. Developed by cardiffnlp.')
|
33 |
|