Ptt 大爆卦 | Train BERT - 前往 https://datascience.stackexchange.com/questions/47406/incrementally-train-bert-with-minimum-qna-records-to-get-improved-results

你即將離開本站

並前往https://datascience.stackexchange.com/questions/47406/incrementally-train-bert-with-minimum-qna-records-to-get-improved-results

Incrementally Train BERT with minimum QnA records

Remember that BERT was first pre-trained using the concatenation of BooksCorpus (800M words) and English Wikipedia (2,500M words).

確定！回上一頁

查詢「Train BERT」的人也找了：

BertForSequenceClassification