SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Merge pull request #1057 from huggingface/fixes

Browse Source 
Add a few of typos corrections, bugs fixes and small improvements
This commit is contained in:
Thomas Wolf
2019-08-21 01:54:05 +02:00
committed by GitHub
parent 41789c6c3d 43489756ad
commit e4515faf54
13 changed files with 85 additions and 28 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pytorch_transformers/modeling_openai.py
View File

@@ -404,6 +404,8 @@ OPENAI_GPT_START_DOCSTRING = r""" OpenAI GPT model was proposed in
OPENAI_GPT_INPUTS_DOCSTRING = r""" Inputs:
**input_ids**: ``torch.LongTensor`` of shape ``(batch_size, sequence_length)``:
Indices of input sequence tokens in the vocabulary.
GPT is a model with absolute position embeddings so it's usually advised to pad the inputs on
the right rather than the left.
Indices can be obtained using :class:`pytorch_transformers.BPT2Tokenizer`.
See :func:`pytorch_transformers.PreTrainedTokenizer.encode` and
:func:`pytorch_transformers.PreTrainedTokenizer.convert_tokens_to_ids` for details.