Congcong Wang comments

Results 8 comments of


                                            Congcong Wang

Add exp to engine.Value

There is __pow__ method. Why still needs this method? Just curious.

the special tokens of XLNet is different from BERT

Have a look at this. https://huggingface.co/transformers/model_doc/xlnet.html#xlnettokenizer Hope it helps.

How to install allennlp on windows?

Hope this link will help: https://github.com/wangcongcong123/AllenNLPonWins

For drmm model, dense_output should be flipped at dim=-1?

My understand is that query is padded to the left while match_hist is to the right. When calculating the einsum between them, should this be consistent ?

代码生成和代码补全

其实可以考虑character-level的训练，不过那将改变vocabulary，可能要设计到预训练。如果条件允许的话，你可以试着预训练一个gpt2在大量代码数据上。

Not generating required output

Have you tried down-version the transformers?

forward() got an unexpected keyword argument 'masked_lm_labels'

simply change "masked_lm_labels" to "labels" in the latest version

RuntimeError: CUDA error: CUBLAS_STATUS_ALLOC_FAILED when calling `cublasCreate(handle)` (createCublasHandle at /pytorch/aten/src/ATen/cuda/CublasHandlePool.cpp:8)

If you want to use the latest transformers, just change ` original_masked_lm_labels = [-1] * max_seq_length` line 200 in cbert_utils.py to ` original_masked_lm_labels = [-100] * max_seq_length`. Then here you...