Open eveliao opened 5 years ago
@eveliao We didn't implemented the transfer learning process yet. Cause by issue #32. But you can just load the BERT using torch.load(bert_path) and the model output is similar with lstm output(output embedding per token sequence).
it didn't solved yet i think it's solved.
Could you please give some example code to load in the pre-trained model(i.e. bert.model.ep0 files)? The code might take me a while to understand so I really appreciate it if you can help me.