你即將離開本站

並前往https://arxiv.org/abs/1910.01108

DistilBERT, a distilled version of BERT: smaller, faster ... - arXiv

... possible to reduce the size of a BERT model by 40%, while retaining 97% of its language understanding capabilities and being 60% faster.

確定！ 回上一頁

查詢 「BERT huggingface」的人也找了：

  1. HuggingFace BERT
    2.
  2. Huggingface model
    3.
  3. Huggingface
    4.
  4. huggingface教學
    5.
  5. Huggingface pipeline
    6.
  6. HuggingFace dataset
    7.
  7. bert-base-uncased
    8.
  8. Huggingface tokenizer
    9.