metadata

license: apache-2.0
language:
  - zh
metrics:
  - bleu
pipeline_tag: translation

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("安世字子孺，少以父任为郎。", 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))