Downloads · 30 days
120
11% of all-time downloads
Erya4FT
RUCAIBox/Erya4FT
Erya4FT is a translation model from RUCAIBox. Use it when you need text moved from one language to another. It is set up for transformers. The card lists the license as apache-2.0.
Erya4FT is based on Erya and further fine-tuned on our Dataset, enhancing the ability to translate ancient Chinese into Modern Chinese.
All-time downloads
1.1K
Public
Repo size
2.1 GB
Likes
4
Public
Repo makeup
Click a slice to open those files.
.bin1.1 GB · 100%
At a glance
- Task
- Translation
- Library
- transformers
- License
- apache-2.0
- Model type
- bart
- Access
- Public
- Created
- Jul 29, 2023
- Updated
- Aug 3, 2023
- SHA
- 528d958e
Try a prompt
Model card
From the Hugging Face model README
Model Description
Erya4FT is based on Erya and further fine-tuned on our Dataset, enhancing the ability to translate ancient Chinese into Modern Chinese.
Example
>>> from transformers import BertTokenizer, CPTForConditionalGeneration
>>> tokenizer = BertTokenizer.from_pretrained("RUCAIBox/Erya4FT")
>>> model = CPTForConditionalGeneration.from_pretrained("RUCAIBox/Erya4FT")
>>> input_ids = tokenizer("竖子不足与谋。", return_tensors='pt')
>>> input_ids.pop("token_type_ids")
>>> pred_ids = model.generate(max_new_tokens=256, **input_ids)
>>> print(tokenizer.batch_decode(pred_ids, skip_special_tokens=True))
['这 小 子 不 值 得 与 他 商 量 。']
- Task
- Translation
- Library
- transformers
- Type
- bart
- License
- apache-2.0
- Languages
- zh
- Created
- Jul 29, 2023
- Updated
- Aug 3, 2023