chunked/nltk_chunking/model_doc_bertweet/chunk_7.txt

line = "SC has first two presumptive cases of coronavirus , DHEC confirms HTTPURL via @USER :cry:"
input_ids = torch.tensor([tokenizer.encode(line)])
with torch.no_grad():
     features = bertweet(input_ids)  # Models outputs are now tuples
With TensorFlow 2.0+:
from transformers import TFAutoModel
bertweet = TFAutoModel.from_pretrained("vinai/bertweet-base")

 
This implementation is the same as BERT, except for tokenization method.