Downloads · 30 days
15
2% of all-time downloads
knight-errant-TST-zh
CO-IR/knight-errant-TST-zh
knight-errant-TST-zh is a machine learning model from CO-IR. 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. The card lists the license as mit.
Knight is a text style transfer model for knight-errant style. This model is for Chinese Knight-errant style transfer.
All-time downloads
895
Public
Repo size
4.9 GB
Likes
0
Public
Repo makeup
Click a slice to open those files.
.bin2.4 GB · 99%
At a glance
- Library
- transformers
- License
- mit
- Model type
- mbart
- Access
- Public
- Created
- Jul 19, 2022
- Updated
- Aug 15, 2022
- SHA
- 6d43f558
Model card
From the Hugging Face model README
Knight-errant
Knight is a text style transfer model for knight-errant style. This model is for Chinese Knight-errant style transfer.
paper link: To be a Knight-errant Novel Master: Knight-errant Style Transfer via Contrastive Learning
#inference
from transformers import MBartForConditionalGeneration, MBart50TokenizerFast
model = MBartForConditionalGeneration.from_pretrained("Anonymous-TST/knight-errant-TST-zh")
tokenizer = MBart50TokenizerFast.from_pretrained("facebook/mbart-large-50", src_lang="zh_CN", tgt_lang="zh_CN")
model.cuda()
model.eval()
article_1 = "jinyong: 接下来会发生什么？"
batch = tokenizer(article_1, return_tensors="pt",return_token_type_ids=False, truncation=True, max_length=64, padding=True).to('cuda')
translated_tokens = model.generate(**batch,max_length=64)
decoded = tokenizer.batch_decode(translated_tokens, skip_special_tokens=True, clean_up_tokenization_spaces=True)
print(decoded)
# 欲知后事如何?
- Library
- transformers
- Type
- mbart
- License
- mit
- Languages
- multilingual, ar, cs, de, en, es
- Created
- Jul 19, 2022
- Updated
- Aug 15, 2022