YAML Metadata
Warning:
empty or missing yaml metadata in repo card
(https://huggingface.co/docs/hub/model-cards#model-card-metadata)
English-Simile-Generation is a seq2seq paraphrase model which can transform sentence A to sentence B containing figurative or simile expression.
A: Now I feel sad to see your scientific research progress is so slow.
B: Now I feel sad to see your scientific research progress is as slow as snail.
**To our knowledge, our model have better performance,diversity and practicability compared to EMNLP21 paper (Generating similes effortlessly like a Pro: A Style Transfer Approach for Simile Generation). **
from transformers import AutoTokenizer, AutoModelForSeq2SeqLM
tokenizer = AutoTokenizer.from_pretrained("figurative-nlp/English-Simile-Generation")
model = AutoModelForSeq2SeqLM.from_pretrained("figurative-nlp/Ehinese-Simile-Generation")
input_ids = tokenizer(
"Adrenaline shot through him powerful", return_tensors="pt"
).input_ids
outputs = model.generate(input_ids,num_beams = 5,max_length = 64)
result = tokenizer.decode(outputs[0], skip_special_tokens=True)
print(result)
#result : Adrenaline shot through him like an electric current
- Downloads last month
- 10
This model does not have enough activity to be deployed to Inference API (serverless) yet. Increase its social
visibility and check back later, or deploy to Inference Endpoints (dedicated)
instead.