Downloads · 30 days
374
1% of all-time downloads
IndoT5-base-paraphrase
Wikidepia/IndoT5-base-paraphrase
IndoT5-base-paraphrase is a machine learning model from Wikidepia. Use it for the machine learning task on the model card, and read the license before you ship it in a product. It is set up for transformers.
All-time downloads
28.7K
Public
Repo size
7 GB
Likes
2
Public
Repo makeup
Click a slice to open those files.
.bin990 MB · 50%
At a glance
- Library
- transformers
- Model type
- t5
- Access
- Public
- Created
- Mar 2, 2022
- Updated
- Sep 4, 2021
- SHA
- 5d591dc3
Model card
From the Hugging Face model README
Paraphrase Generation with IndoT5 Base
IndoT5-base trained on translated PAWS.
Model in action
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("Wikidepia/IndoT5-base-paraphrase")
model = AutoModelForSeq2SeqLM.from_pretrained("Wikidepia/IndoT5-base-paraphrase")
sentence = "Anak anak melakukan piket kelas agar kebersihan kelas terjaga"
text = "paraphrase: " + sentence + " </s>"
encoding = tokenizer(text, padding='longest', return_tensors="pt")
outputs = model.generate(
input_ids=encoding["input_ids"], attention_mask=encoding["attention_mask"],
max_length=512,
do_sample=True,
top_k=200,
top_p=0.95,
early_stopping=True,
num_return_sequences=5
)
Limitations
Sometimes paraphrase contain date which doesnt exists in the original text :/
Acknowledgement
Thanks to Tensorflow Research Cloud for providing TPU v3-8s.
- Library
- transformers
- Type
- t5
- Languages
- id
- Created
- Mar 2, 2022
- Updated
- Sep 4, 2021