Spaces:
Runtime error
Runtime error
Wikidepia
commited on
Commit
•
654d2fa
0
Parent(s):
Initial commit
Browse files- .gitattributes +27 -0
- README.md +9 -0
- app/__init__.py +0 -0
- app/app.py +56 -0
- requirements.txt +1 -0
.gitattributes
ADDED
@@ -0,0 +1,27 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
*.7z filter=lfs diff=lfs merge=lfs -text
|
2 |
+
*.arrow filter=lfs diff=lfs merge=lfs -text
|
3 |
+
*.bin filter=lfs diff=lfs merge=lfs -text
|
4 |
+
*.bin.* filter=lfs diff=lfs merge=lfs -text
|
5 |
+
*.bz2 filter=lfs diff=lfs merge=lfs -text
|
6 |
+
*.ftz filter=lfs diff=lfs merge=lfs -text
|
7 |
+
*.gz filter=lfs diff=lfs merge=lfs -text
|
8 |
+
*.h5 filter=lfs diff=lfs merge=lfs -text
|
9 |
+
*.joblib filter=lfs diff=lfs merge=lfs -text
|
10 |
+
*.lfs.* filter=lfs diff=lfs merge=lfs -text
|
11 |
+
*.model filter=lfs diff=lfs merge=lfs -text
|
12 |
+
*.msgpack filter=lfs diff=lfs merge=lfs -text
|
13 |
+
*.onnx filter=lfs diff=lfs merge=lfs -text
|
14 |
+
*.ot filter=lfs diff=lfs merge=lfs -text
|
15 |
+
*.parquet filter=lfs diff=lfs merge=lfs -text
|
16 |
+
*.pb filter=lfs diff=lfs merge=lfs -text
|
17 |
+
*.pt filter=lfs diff=lfs merge=lfs -text
|
18 |
+
*.pth filter=lfs diff=lfs merge=lfs -text
|
19 |
+
*.rar filter=lfs diff=lfs merge=lfs -text
|
20 |
+
saved_model/**/* filter=lfs diff=lfs merge=lfs -text
|
21 |
+
*.tar.* filter=lfs diff=lfs merge=lfs -text
|
22 |
+
*.tflite filter=lfs diff=lfs merge=lfs -text
|
23 |
+
*.tgz filter=lfs diff=lfs merge=lfs -text
|
24 |
+
*.xz filter=lfs diff=lfs merge=lfs -text
|
25 |
+
*.zip filter=lfs diff=lfs merge=lfs -text
|
26 |
+
*.zstandard filter=lfs diff=lfs merge=lfs -text
|
27 |
+
*tfevents* filter=lfs diff=lfs merge=lfs -text
|
README.md
ADDED
@@ -0,0 +1,9 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
---
|
2 |
+
title: Indonesian Paraphrase Generation
|
3 |
+
emoji: 🧬
|
4 |
+
colorFrom: blue
|
5 |
+
colorTo: red
|
6 |
+
sdk: streamlit
|
7 |
+
app_file: app/app.py
|
8 |
+
pinned: true
|
9 |
+
---
|
app/__init__.py
ADDED
File without changes
|
app/app.py
ADDED
@@ -0,0 +1,56 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
1 |
+
import os
|
2 |
+
from typing import List
|
3 |
+
|
4 |
+
import streamlit as st
|
5 |
+
from transformers import AutoModelForSeq2SeqLM, AutoTokenizer
|
6 |
+
|
7 |
+
os.environ["TOKENIZERS_PARALLELISM"] = "false"
|
8 |
+
|
9 |
+
|
10 |
+
@st.cache(allow_output_mutation=True)
|
11 |
+
def load_model(model_name):
|
12 |
+
tokenizer = AutoTokenizer.from_pretrained(model_name)
|
13 |
+
model = AutoModelForSeq2SeqLM.from_pretrained(model_name)
|
14 |
+
return model, tokenizer
|
15 |
+
|
16 |
+
|
17 |
+
def paraphrase(model, encoding, top_k=120, top_p=0.95, max_len=120) -> List[str]:
|
18 |
+
outputs = model.generate(
|
19 |
+
input_ids=encoding["input_ids"],
|
20 |
+
attention_mask=encoding["attention_mask"],
|
21 |
+
do_sample=True,
|
22 |
+
top_k=top_k,
|
23 |
+
top_p=top_p,
|
24 |
+
max_length=max_len,
|
25 |
+
early_stopping=True,
|
26 |
+
num_return_sequences=5,
|
27 |
+
)
|
28 |
+
return [
|
29 |
+
tokenizer.decode(
|
30 |
+
output, skip_special_tokens=True, clean_up_tokenization_spaces=True
|
31 |
+
)
|
32 |
+
for output in outputs
|
33 |
+
]
|
34 |
+
|
35 |
+
|
36 |
+
if __name__ == "__main__":
|
37 |
+
st.header("Indonesian Paraphrase Generation")
|
38 |
+
user_input = st.text_area("Original Sentence", "", height=30)
|
39 |
+
|
40 |
+
# Slider for max_len
|
41 |
+
st.sidebar.header("Decoding Settings")
|
42 |
+
max_len = st.sidebar.slider("Max-Length", 0, 512, 256)
|
43 |
+
top_k = st.sidebar.slider("Top-K", 0, 512, 200)
|
44 |
+
top_p = st.sidebar.slider("Top-P", 0.0, 1.0, 0.95)
|
45 |
+
|
46 |
+
if st.button("Paraphrase") or user_input:
|
47 |
+
with st.spinner("T5 is processing your text..."):
|
48 |
+
model, tokenizer = load_model("Wikidepia/IndoT5-base-paraphrase")
|
49 |
+
text = "paraphrase: " + user_input + " </s>"
|
50 |
+
encode_id = tokenizer(text, return_tensors="pt")
|
51 |
+
outputs = paraphrase(
|
52 |
+
model, encode_id, top_k=top_k, top_p=top_p, max_len=max_len
|
53 |
+
)
|
54 |
+
st.markdown("### Hasil Parafrase")
|
55 |
+
for i, output in enumerate(outputs):
|
56 |
+
st.markdown(f"- {output}")
|
requirements.txt
ADDED
@@ -0,0 +1 @@
|
|
|
|
|
1 |
+
streamlit==0.80.0
|