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

max_len_single_sentence & max_len_sentences_pair as attributes so they can be modified

Browse Source
This commit is contained in:
thomwolf
2019-08-23 22:07:26 +02:00
parent ab7bd5ef98
commit 3bcbebd440
8 changed files with 26 additions and 40 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
pytorch_transformers/tokenization_gpt2.py
View File

@@ -108,6 +108,8 @@ class GPT2Tokenizer(PreTrainedTokenizer):
def __init__(self, vocab_file, merges_file, errors='replace', unk_token="<|endoftext|>",
bos_token="<|endoftext|>", eos_token="<|endoftext|>", **kwargs):
super(GPT2Tokenizer, self).__init__(bos_token=bos_token, eos_token=eos_token, unk_token=unk_token, **kwargs)
self.max_len_single_sentence = self.max_len # no default special tokens - you can update this value if you add special tokens
self.max_len_sentences_pair = self.max_len # no default special tokens - you can update this value if you add special tokens
self.encoder = json.load(open(vocab_file))
self.decoder = {v:k for k,v in self.encoder.items()}