From cb7b77a8a2ee52812c4358817a6a586f19687cda Mon Sep 17 00:00:00 2001 From: VictorSanh Date: Wed, 30 Oct 2019 18:13:52 -0400 Subject: [PATCH] fix some typos --- transformers/tokenization_xlm.py | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/transformers/tokenization_xlm.py b/transformers/tokenization_xlm.py index 01f8721d98..ba994dc356 100644 --- a/transformers/tokenization_xlm.py +++ b/transformers/tokenization_xlm.py @@ -12,7 +12,7 @@ # WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied. # See the License for the specific language governing permissions and # limitations under the License. -"""Tokenization classes for OpenAI GPT.""" +"""Tokenization classes for XLM.""" from __future__ import (absolute_import, division, print_function, unicode_literals) @@ -758,9 +758,9 @@ class XLMTokenizer(PreTrainedTokenizer): """ Build model inputs from a sequence or a pair of sequence for sequence classification tasks by concatenating and adding special tokens. - A RoBERTa sequence has the following format: + A XLM sequence has the following format: single sequence: X - pair of sequences: A B + pair of sequences: A B """ if token_ids_1 is None: return [self.cls_token_id] + token_ids_0 + [self.sep_token_id]