Updates the default branch from master to main (#16326)

* Updates the default branch from master to main

* Links from `master` to `main`

* Typo

* Update examples/flax/README.md
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>

scripts/tatoeba/README.md

@@ -48,7 +48,7 @@ resolver.convert_models(['heb-eng', 'eng-heb'])
 
 
 ### Upload converted models
-Since version v3.5.0, the model sharing workflow is switched to git-based system . Refer to [model sharing doc](https://huggingface.co/transformers/master/model_sharing.html#model-sharing-and-uploading) for more details.
+Since version v3.5.0, the model sharing workflow is switched to git-based system . Refer to [model sharing doc](https://huggingface.co/transformers/main/model_sharing.html#model-sharing-and-uploading) for more details.
 
 To upload all converted models, 
 

setup.py

@@ -13,7 +13,7 @@
 # limitations under the License.
 
 """
-Simple check list from AllenNLP repo: https://github.com/allenai/allennlp/blob/master/setup.py
+Simple check list from AllenNLP repo: https://github.com/allenai/allennlp/blob/main/setup.py
 
 To create the package for pypi.
 
@@ -26,10 +26,10 @@ To create the package for pypi.
 
 4. Commit these changes with the message: "Release: <VERSION>" and push.
 
-5. Wait for the tests on master to be completed and be green (otherwise revert and fix bugs)
+5. Wait for the tests on main to be completed and be green (otherwise revert and fix bugs)
 
 6. Add a tag in git to mark the release: "git tag v<VERSION> -m 'Adds tag v<VERSION> for pypi' "
-   Push the tag to git: git push --tags origin master
+   Push the tag to git: git push --tags origin main
 
 7. Build both the sources and the wheel. Do not change anything in setup.py between
    creating the wheel and the source distribution (obviously).
@@ -60,7 +60,7 @@ To create the package for pypi.
 10. Copy the release notes from RELEASE.md to the tag in github once everything is looking hunky-dory.
 
 11. Run `make post-release` (or, for a patch release, `make post-patch`). If you were on a branch for the release,
-    you need to go back to master before executing this.
+    you need to go back to main before executing this.
 """
 
 import os

src/transformers/data/datasets/glue.py

@@ -87,7 +87,7 @@ class GlueDataset(Dataset):
         warnings.warn(
             "This dataset will be removed from the library soon, preprocessing should be handled with the 🤗 Datasets "
             "library. You can have a look at this example script for pointers: "
-            "https://github.com/huggingface/transformers/blob/master/examples/pytorch/text-classification/run_glue.py",
+            "https://github.com/huggingface/transformers/blob/main/examples/pytorch/text-classification/run_glue.py",
             FutureWarning,
         )
         self.args = args

src/transformers/data/datasets/language_modeling.py

@@ -53,7 +53,7 @@ class TextDataset(Dataset):
     ):
         warnings.warn(
             DEPRECATION_WARNING.format(
-                "https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_mlm.py"
+                "https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_mlm.py"
             ),
             FutureWarning,
         )
@@ -120,7 +120,7 @@ class LineByLineTextDataset(Dataset):
     def __init__(self, tokenizer: PreTrainedTokenizer, file_path: str, block_size: int):
         warnings.warn(
             DEPRECATION_WARNING.format(
-                "https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_mlm.py"
+                "https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_mlm.py"
             ),
             FutureWarning,
         )
@@ -153,7 +153,7 @@ class LineByLineWithRefDataset(Dataset):
     def __init__(self, tokenizer: PreTrainedTokenizer, file_path: str, block_size: int, ref_path: str):
         warnings.warn(
             DEPRECATION_WARNING.format(
-                "https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_mlm_wwm.py"
+                "https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_mlm_wwm.py"
             ),
             FutureWarning,
         )
@@ -201,7 +201,7 @@ class LineByLineWithSOPTextDataset(Dataset):
     def __init__(self, tokenizer: PreTrainedTokenizer, file_dir: str, block_size: int):
         warnings.warn(
             DEPRECATION_WARNING.format(
-                "https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_mlm.py"
+                "https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_mlm.py"
             ),
             FutureWarning,
         )
@@ -361,7 +361,7 @@ class TextDatasetForNextSentencePrediction(Dataset):
     ):
         warnings.warn(
             DEPRECATION_WARNING.format(
-                "https://github.com/huggingface/transformers/blob/master/examples/pytorch/language-modeling/run_mlm.py"
+                "https://github.com/huggingface/transformers/blob/main/examples/pytorch/language-modeling/run_mlm.py"
             ),
             FutureWarning,
         )

src/transformers/data/metrics/__init__.py

@@ -28,7 +28,7 @@ if is_sklearn_available():
 DEPRECATION_WARNING = (
     "This metric will be removed from the library soon, metrics should be handled with the 🤗 Datasets "
     "library. You can have a look at this example script for pointers: "
-    "https://github.com/huggingface/transformers/blob/master/examples/pytorch/text-classification/run_glue.py"
+    "https://github.com/huggingface/transformers/blob/main/examples/pytorch/text-classification/run_glue.py"
 )
 
 

src/transformers/data/processors/glue.py

@@ -35,7 +35,7 @@ logger = logging.get_logger(__name__)
 DEPRECATION_WARNING = (
     "This {0} will be removed from the library soon, preprocessing should be handled with the 🤗 Datasets "
     "library. You can have a look at this example script for pointers: "
-    "https://github.com/huggingface/transformers/blob/master/examples/pytorch/text-classification/run_glue.py"
+    "https://github.com/huggingface/transformers/blob/main/examples/pytorch/text-classification/run_glue.py"
 )
 
 

src/transformers/models/rag/modeling_tf_rag.py

@@ -598,7 +598,7 @@ class TFRagModel(TFRagPreTrainedModel):
                 question_enc_outputs = self.question_encoder(
                     input_ids, attention_mask=attention_mask, return_dict=True, training=training
                 )
-                # see https://github.com/huggingface/transformers/blob/master/src/transformers/models/dpr/modeling_tf_dpr.py#L91
+                # see https://github.com/huggingface/transformers/blob/main/src/transformers/models/dpr/modeling_tf_dpr.py#L91
                 question_encoder_last_hidden_state = question_enc_outputs[
                     0
                 ]  # hidden states of question encoder => pooler_output
@@ -748,7 +748,7 @@ class TFRagTokenForGeneration(TFRagPreTrainedModel, TFCausalLanguageModelingLoss
     def set_retriever(self, retriever: RagRetriever):
         self.rag.retriever = retriever
 
-    # Adapted from https://github.com/huggingface/transformers/blob/master/src/transformers/modeling_tf_bart.py
+    # Adapted from https://github.com/huggingface/transformers/blob/main/src/transformers/modeling_tf_bart.py
     def prepare_inputs_for_generation(
         self,
         decoder_input_ids,

src/transformers/trainer_tf.py

@@ -109,7 +109,7 @@ class TFTrainer:
             "The class `TFTrainer` is deprecated and will be removed in version 5 of Transformers. "
             "We recommend using native Keras instead, by calling methods like `fit()` and `predict()` "
             "directly on the model object. Detailed examples of the Keras style can be found in our "
-            "examples at https://github.com/huggingface/transformers/tree/master/examples/tensorflow",
+            "examples at https://github.com/huggingface/transformers/tree/main/examples/tensorflow",
             FutureWarning,
         )
 

src/transformers/training_args.py

@@ -101,16 +101,16 @@ class TrainingArguments:
         do_train (`bool`, *optional*, defaults to `False`):
             Whether to run training or not. This argument is not directly used by [`Trainer`], it's intended to be used
             by your training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         do_eval (`bool`, *optional*):
             Whether to run evaluation on the validation set or not. Will be set to `True` if `evaluation_strategy` is
             different from `"no"`. This argument is not directly used by [`Trainer`], it's intended to be used by your
             training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         do_predict (`bool`, *optional*, defaults to `False`):
             Whether to run predictions on the test set or not. This argument is not directly used by [`Trainer`], it's
             intended to be used by your training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         evaluation_strategy (`str` or [`~trainer_utils.IntervalStrategy`], *optional*, defaults to `"no"`):
             The evaluation strategy to adopt during training. Possible values are:
 
@@ -385,7 +385,7 @@ class TrainingArguments:
         resume_from_checkpoint (`str`, *optional*):
             The path to a folder with a valid checkpoint for your model. This argument is not directly used by
             [`Trainer`], it's intended to be used by your training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         hub_model_id (`str`, *optional*):
             The name of the repository to keep in sync with the local *output_dir*. It can be a simple model ID in
             which case the model will be pushed in your namespace. Otherwise it should be the whole repository name,

src/transformers/training_args_tf.py

@@ -46,16 +46,16 @@ class TFTrainingArguments(TrainingArguments):
         do_train (`bool`, *optional*, defaults to `False`):
             Whether to run training or not. This argument is not directly used by [`Trainer`], it's intended to be used
             by your training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         do_eval (`bool`, *optional*):
             Whether to run evaluation on the validation set or not. Will be set to `True` if `evaluation_strategy` is
             different from `"no"`. This argument is not directly used by [`Trainer`], it's intended to be used by your
             training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         do_predict (`bool`, *optional*, defaults to `False`):
             Whether to run predictions on the test set or not. This argument is not directly used by [`Trainer`], it's
             intended to be used by your training/evaluation scripts instead. See the [example
-            scripts](https://github.com/huggingface/transformers/tree/master/examples) for more details.
+            scripts](https://github.com/huggingface/transformers/tree/main/examples) for more details.
         evaluation_strategy (`str` or [`~trainer_utils.IntervalStrategy`], *optional*, defaults to `"no"`):
             The evaluation strategy to adopt during training. Possible values are:
 

src/transformers/utils/versions.py

@@ -116,5 +116,5 @@ def require_version(requirement: str, hint: Optional[str] = None) -> None:
 
 def require_version_core(requirement):
     """require_version wrapper which emits a core-specific hint on failure"""
-    hint = "Try: pip install transformers -U or pip install -e '.[dev]' if you're working with git master"
+    hint = "Try: pip install transformers -U or pip install -e '.[dev]' if you're working with git main"
     return require_version(requirement, hint)

templates/adding_a_new_model/ADD_NEW_MODEL_PROPOSAL_TEMPLATE.md

@@ -562,12 +562,12 @@ Cookiecutter!
 **Use the Cookiecutter to automatically generate the model's code**
 
 To begin with head over to the [🤗 Transformers
-templates](https://github.com/huggingface/transformers/tree/master/templates/adding_a_new_model)
+templates](https://github.com/huggingface/transformers/tree/main/templates/adding_a_new_model)
 to make use of our `cookiecutter` implementation to automatically
 generate all the relevant files for your model. Again, we recommend only
 adding the PyTorch version of the model at first. Make sure you follow
 the instructions of the `README.md` on the [🤗 Transformers
-templates](https://github.com/huggingface/transformers/tree/master/templates/adding_a_new_model)
+templates](https://github.com/huggingface/transformers/tree/main/templates/adding_a_new_model)
 carefully.
 
 **Open a Pull Request on the main huggingface/transformers repo**
@@ -580,7 +580,7 @@ Transformers.
 
 You should do the following:
 
-1.  Create a branch with a descriptive name from your master branch
+1.  Create a branch with a descriptive name from your main branch
 
 ```
     git checkout -b add_[lowercase name of model]
@@ -593,11 +593,11 @@ You should do the following:
     git commit
 ```
 
-3.  Fetch and rebase to current master
+3.  Fetch and rebase to current main
 
 ```
     git fetch upstream
-    git rebase upstream/master
+    git rebase upstream/main
 ```
 
 4.  Push the changes to your account using:
@@ -617,10 +617,10 @@ You should do the following:
 In the following, whenever you have done some progress, don't forget to
 commit your work and push it to your account so that it shows in the
 pull request. Additionally, you should make sure to update your work
-with the current master from time to time by doing:
+with the current main from time to time by doing:
 
     git fetch upstream
-    git merge upstream/master
+    git merge upstream/main
 
 In general, all questions you might have regarding the model or your
 implementation should be asked in your PR and discussed/solved in the
@@ -703,7 +703,7 @@ similar already existing conversion script for your model.
     [here](https://github.com/huggingface/transformers/blob/7acfa95afb8194f8f9c1f4d2c6028224dbed35a2/src/transformers/models/bert/modeling_bert.py#L91)
 -   If you are porting a model from PyTorch to PyTorch, a good starting
     point might be BART's conversion script
-    [here](https://github.com/huggingface/transformers/blob/master/src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py)
+    [here](https://github.com/huggingface/transformers/blob/main/src/transformers/models/bart/convert_bart_original_pytorch_checkpoint_to_pytorch.py)
 
 In the following, we'll quickly explain how PyTorch models store layer
 weights and define layer names. In PyTorch, the name of a layer is
@@ -1122,7 +1122,7 @@ for the community.
 **14. Submit your finished PR**
 
 You're done programming now and can move to the last step, which is
-getting your PR merged into master. Usually, [name of mentor]
+getting your PR merged into main. Usually, [name of mentor]
 should have helped you already at this point, but it is worth taking
 some time to give your finished PR a nice description and eventually add
 comments to your code, if you want to point out certain design choices

templates/adding_a_new_model/open_model_proposals/ADD_BIG_BIRD.md

@@ -254,7 +254,7 @@ You should have understood the following aspects of BigBird by now:
 - BigBird's self-attention layer is composed of three mechanisms: block sparse (local) self-attention, global self-attention, random self-attention
 - BigBird's block sparse (local) self-attention is different from Longformer's local self-attention. How so? Why does that matter? => Can be deployed on TPU much easier this way
 - BigBird can be implemented for both an encoder-only model **and** 
-  for an encoder-decoder model, which means that we can reuse lots of [code from RoBERTa](https://github.com/huggingface/transformers/blob/master/src/transformers/models/roberta/modeling_roberta.py) and [from PEGASUS](https://github.com/huggingface/transformers/blob/master/src/transformers/models/pegasus/modeling_pegasus.py) at a later stage.
+  for an encoder-decoder model, which means that we can reuse lots of [code from RoBERTa](https://github.com/huggingface/transformers/blob/main/src/transformers/models/roberta/modeling_roberta.py) and [from PEGASUS](https://github.com/huggingface/transformers/blob/main/src/transformers/models/pegasus/modeling_pegasus.py) at a later stage.
 
 
 If any of the mentioned aspects above are **not** clear to you, now is a great time to talk to Patrick.
@@ -569,12 +569,12 @@ Cookiecutter!
 **Use the Cookiecutter to automatically generate the model's code**
 
 To begin with head over to the [🤗 Transformers
-templates](https://github.com/huggingface/transformers/tree/master/templates/adding_a_new_model)
+templates](https://github.com/huggingface/transformers/tree/main/templates/adding_a_new_model)
 to make use of our `cookiecutter` implementation to automatically
 generate all the relevant files for your model. Again, we recommend only
 adding the PyTorch version of the model at first. Make sure you follow
 the instructions of the `README.md` on the [🤗 Transformers
-templates](https://github.com/huggingface/transformers/tree/master/templates/adding_a_new_model)
+templates](https://github.com/huggingface/transformers/tree/main/templates/adding_a_new_model)
 carefully.
 Since you will first implement the Encoder-only/RoBERTa-like version of BigBird you should 
 select the `is_encoder_decoder_model = False` option in the cookiecutter. Also, it is recommended
@@ -591,7 +591,7 @@ Transformers.
 
 You should do the following:
 
-1.  Create a branch with a descriptive name from your master branch
+1.  Create a branch with a descriptive name from your main branch
 
 ```
     git checkout -b add_big_bird
@@ -604,11 +604,11 @@ You should do the following:
     git commit
 ```
 
-3.  Fetch and rebase to current master
+3.  Fetch and rebase to current main
 
 ```
     git fetch upstream
-    git rebase upstream/master
+    git rebase upstream/main
 ```
 
 4.  Push the changes to your account using:
@@ -627,10 +627,10 @@ You should do the following:
 In the following, whenever you have done some progress, don't forget to
 commit your work and push it to your account so that it shows in the
 pull request. Additionally, you should make sure to update your work
-with the current master from time to time by doing:
+with the current main from time to time by doing:
 
     git fetch upstream
-    git merge upstream/master
+    git merge upstream/main
 
 In general, all questions you might have regarding the model or your
 implementation should be asked in your PR and discussed/solved in the
@@ -1129,7 +1129,7 @@ for the community.
 **14. Submit your finished PR**
 
 You're done programming now and can move to the last step, which is
-getting your PR merged into master. Usually, Patrick
+getting your PR merged into main. Usually, Patrick
 should have helped you already at this point, but it is worth taking
 some time to give your finished PR a nice description and eventually add
 comments to your code, if you want to point out certain design choices

tests/sagemaker/README.md

@@ -12,7 +12,7 @@ This document explains the testing strategy for releasing the new Hugging Face D
 Before we can run the tests we need to adjust the `requirements.txt` for PyTorch under `/tests/sagemaker/scripts/pytorch` and for TensorFlow under `/tests/sagemaker/scripts/pytorch`. We adjust the branch to the new RC-tag.
 
 ```
-git+https://github.com/huggingface/transformers.git@v4.5.0.rc0 # install master or adjust ist with vX.X.X for installing version specific-transforms
+git+https://github.com/huggingface/transformers.git@v4.5.0.rc0 # install main or adjust ist with vX.X.X for installing version specific-transforms
 ```
 
 After we adjusted the `requirements.txt` we can run Amazon SageMaker tests with:  

tests/sagemaker/scripts/pytorch/requirements.txt

-git+https://github.com/huggingface/transformers.git@master # install master or adjust it with vX.X.X for installing version specific transforms
+git+https://github.com/huggingface/transformers.git@main # install main or adjust it with vX.X.X for installing version specific transforms
 datasets==1.8.0
\ No newline at end of file

tests/sagemaker/scripts/tensorflow/requirements.txt

-git+https://github.com/huggingface/transformers.git@master # install master or adjust ist with vX.X.X for installing version specific transforms
\ No newline at end of file
+git+https://github.com/huggingface/transformers.git@main # install main or adjust ist with vX.X.X for installing version specific transforms
\ No newline at end of file

tests/utils/test_utils_check_copies.py

@@ -125,9 +125,9 @@ class CopyCheckTester(unittest.TestCase):
     def test_convert_to_localized_md(self):
         localized_readme = check_copies.LOCALIZED_READMES["README_zh-hans.md"]
 
-        md_list = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (from Google Research and the Toyota Technological Institute at Chicago) released with the paper [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut.\n1. **[DistilBERT](https://huggingface.co/transformers/model_doc/distilbert.html)** (from HuggingFace), released together with the paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/master/examples/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/master/examples/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/master/examples/distillation) and a German version of DistilBERT.\n1. **[ELECTRA](https://huggingface.co/transformers/model_doc/electra.html)** (from Google Research/Stanford University) released with the paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning."
+        md_list = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (from Google Research and the Toyota Technological Institute at Chicago) released with the paper [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut.\n1. **[DistilBERT](https://huggingface.co/transformers/model_doc/distilbert.html)** (from HuggingFace), released together with the paper [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) by Victor Sanh, Lysandre Debut and Thomas Wolf. The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/distillation) and a German version of DistilBERT.\n1. **[ELECTRA](https://huggingface.co/transformers/model_doc/electra.html)** (from Google Research/Stanford University) released with the paper [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) by Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning."
         localized_md_list = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (来自 Google Research and the Toyota Technological Institute at Chicago) 伴随论文 [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), 由 Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut 发布。\n"
-        converted_md_list_sample = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (来自 Google Research and the Toyota Technological Institute at Chicago) 伴随论文 [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), 由 Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut 发布。\n1. **[DistilBERT](https://huggingface.co/transformers/model_doc/distilbert.html)** (来自 HuggingFace) 伴随论文 [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) 由 Victor Sanh, Lysandre Debut and Thomas Wolf 发布。 The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/master/examples/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/master/examples/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/master/examples/distillation) and a German version of DistilBERT.\n1. **[ELECTRA](https://huggingface.co/transformers/model_doc/electra.html)** (来自 Google Research/Stanford University) 伴随论文 [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) 由 Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning 发布。\n"
+        converted_md_list_sample = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (来自 Google Research and the Toyota Technological Institute at Chicago) 伴随论文 [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), 由 Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut 发布。\n1. **[DistilBERT](https://huggingface.co/transformers/model_doc/distilbert.html)** (来自 HuggingFace) 伴随论文 [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://arxiv.org/abs/1910.01108) 由 Victor Sanh, Lysandre Debut and Thomas Wolf 发布。 The same method has been applied to compress GPT2 into [DistilGPT2](https://github.com/huggingface/transformers/tree/main/examples/distillation), RoBERTa into [DistilRoBERTa](https://github.com/huggingface/transformers/tree/main/examples/distillation), Multilingual BERT into [DistilmBERT](https://github.com/huggingface/transformers/tree/main/examples/distillation) and a German version of DistilBERT.\n1. **[ELECTRA](https://huggingface.co/transformers/model_doc/electra.html)** (来自 Google Research/Stanford University) 伴随论文 [ELECTRA: Pre-training text encoders as discriminators rather than generators](https://arxiv.org/abs/2003.10555) 由 Kevin Clark, Minh-Thang Luong, Quoc V. Le, Christopher D. Manning 发布。\n"
 
         num_models_equal, converted_md_list = check_copies.convert_to_localized_md(
             md_list, localized_md_list, localized_readme["format_model_list"]
@@ -144,7 +144,7 @@ class CopyCheckTester(unittest.TestCase):
         self.assertTrue(num_models_equal)
 
         link_changed_md_list = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (from Google Research and the Toyota Technological Institute at Chicago) released with the paper [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), by Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut."
-        link_unchanged_md_list = "1. **[ALBERT](https://huggingface.co/transformers/master/model_doc/albert.html)** (来自 Google Research and the Toyota Technological Institute at Chicago) 伴随论文 [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), 由 Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut 发布。\n"
+        link_unchanged_md_list = "1. **[ALBERT](https://huggingface.co/transformers/main/model_doc/albert.html)** (来自 Google Research and the Toyota Technological Institute at Chicago) 伴随论文 [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), 由 Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut 发布。\n"
         converted_md_list_sample = "1. **[ALBERT](https://huggingface.co/transformers/model_doc/albert.html)** (来自 Google Research and the Toyota Technological Institute at Chicago) 伴随论文 [ALBERT: A Lite BERT for Self-supervised Learning of Language Representations](https://arxiv.org/abs/1909.11942), 由 Zhenzhong Lan, Mingda Chen, Sebastian Goodman, Kevin Gimpel, Piyush Sharma, Radu Soricut 发布。\n"
 
         num_models_equal, converted_md_list = check_copies.convert_to_localized_md(

utils/check_copies.py

@@ -332,7 +332,7 @@ def convert_to_localized_md(model_list, localized_model_list, format_str):
 
 
 def convert_readme_to_index(model_list):
-    model_list = model_list.replace("https://huggingface.co/docs/transformers/master/", "")
+    model_list = model_list.replace("https://huggingface.co/docs/transformers/main/", "")
     return model_list.replace("https://huggingface.co/docs/transformers/", "")
 
 

utils/get_modified_files.py

@@ -24,7 +24,7 @@ import subprocess
 import sys
 
 
-fork_point_sha = subprocess.check_output("git merge-base master HEAD".split()).decode("utf-8")
+fork_point_sha = subprocess.check_output("git merge-base main HEAD".split()).decode("utf-8")
 modified_files = subprocess.check_output(f"git diff --name-only {fork_point_sha}".split()).decode("utf-8").split()
 
 joined_dirs = "|".join(sys.argv[1:])

utils/release.py

@@ -67,7 +67,7 @@ def global_version_update(version, patch=False):
 
 
 def clean_master_ref_in_model_list():
-    """Replace the links from master doc tp stable doc in the model list of the README."""
+    """Replace the links from main doc tp stable doc in the model list of the README."""
     # If the introduction or the conclusion of the list change, the prompts may need to be updated.
     _start_prompt = "🤗 Transformers currently provides the following architectures"
     _end_prompt = "1. Want to contribute a new model?"
@@ -85,7 +85,7 @@ def clean_master_ref_in_model_list():
     while not lines[index].startswith(_end_prompt):
         if lines[index].startswith("1."):
             lines[index] = lines[index].replace(
-                "https://huggingface.co/docs/transformers/master/model_doc",
+                "https://huggingface.co/docs/transformers/main/model_doc",
                 "https://huggingface.co/docs/transformers/model_doc",
             )
         index += 1