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

[M2M100Tokenizer] fix _build_translation_inputs (#14382)

Browse Source 
* add return_tensors paramter

* fix test

* Apply suggestions from code review

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

* style

Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
This commit is contained in:
Suraj Patil
2021-11-13 20:57:12 +05:30
committed by GitHub
parent 3165930402
commit 2e60276b38
2 changed files with 2 additions and 2 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
src/transformers/models/m2m_100/tokenization_m2m_100.py
View File

@@ -332,7 +332,7 @@ class M2M100Tokenizer(PreTrainedTokenizer):
if src_lang is None or tgt_lang is None:
raise ValueError("Translation requires a `src_lang` and a `tgt_lang` for this model")
self.src_lang = src_lang
inputs = self(raw_inputs, add_special_tokens=True, return_tensors="pt", **extra_kwargs)
inputs = self(raw_inputs, add_special_tokens=True, **extra_kwargs)
tgt_lang_id = self.get_lang_id(tgt_lang)
inputs["forced_bos_token_id"] = tgt_lang_id
return inputs

2
tests/test_tokenization_m2m_100.py
View File

@@ -226,7 +226,7 @@ class M2M100TokenizerIntegrationTest(unittest.TestCase):
@require_torch
def test_tokenizer_translation(self):
inputs = self.tokenizer._build_translation_inputs("A test", src_lang="en", tgt_lang="ar")
inputs = self.tokenizer._build_translation_inputs("A test", return_tensors="pt", src_lang="en", tgt_lang="ar")
self.assertEqual(
nested_simplify(inputs),