Tokenizers: ability to load from model subfolder (#8586)

* <small>tiny typo</small>

* Tokenizers: ability to load from model subfolder

* use subfolder for local files as well

* Uniformize model shortcut name => model id

* from s3 => from huggingface.co
Co-authored-by: Quentin Lhoest <lhoest.q@gmail.com>

docs/source/pretrained_models.rst

@@ -3,11 +3,11 @@ Pretrained models
 
 Here is the full list of the currently provided pretrained models together with a short presentation of each model.
 
-For a list that includes community-uploaded models, refer to `https://huggingface.co/models
+For a list that includes all community-uploaded models, refer to `https://huggingface.co/models
 <https://huggingface.co/models>`__.
 
 +--------------------+------------------------------------------------------------+---------------------------------------------------------------------------------------------------------------------------------------+
-| Architecture       | Shortcut name                                              | Details of the model                                                                                                                  |
+| Architecture       | Model id                                                   | Details of the model                                                                                                                  |
 +====================+============================================================+=======================================================================================================================================+
 | BERT               | ``bert-base-uncased``                                      | | 12-layer, 768-hidden, 12-heads, 110M parameters.                                                                                    |
 |                    |                                                            | | Trained on lower-cased English text.                                                                                                |

examples/adversarial/run_hans.py

@@ -57,7 +57,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
 
 

examples/bert-loses-patience/run_glue_with_pabee.py

@@ -476,7 +476,7 @@ def main():
         "--cache_dir",
         default="",
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
     parser.add_argument(
         "--max_seq_length",

examples/bertology/run_bertology.py

@@ -298,7 +298,7 @@ def main():
         "--cache_dir",
         default=None,
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
     parser.add_argument(
         "--data_subset", type=int, default=-1, help="If > 0: limit the data to a subset of data_subset instances."

examples/contrib/legacy/run_language_modeling.py

@@ -81,7 +81,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
 
 

examples/contrib/mm-imdb/run_mmimdb.py

@@ -350,7 +350,7 @@ def main():
         "--cache_dir",
         default=None,
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
     parser.add_argument(
         "--max_seq_length",

examples/deebert/run_glue_deebert.py

@@ -452,7 +452,7 @@ def main():
         "--cache_dir",
         default="",
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
     parser.add_argument(
         "--max_seq_length",

examples/distillation/run_squad_w_distillation.py

@@ -578,7 +578,7 @@ def main():
         "--cache_dir",
         default="",
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
 
     parser.add_argument(

examples/language-modeling/run_clm.py

@@ -76,7 +76,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
     use_fast_tokenizer: bool = field(
         default=True,

examples/language-modeling/run_mlm.py

@@ -74,7 +74,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
     use_fast_tokenizer: bool = field(
         default=True,

examples/language-modeling/run_mlm_wwm.py

@@ -76,7 +76,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
     use_fast_tokenizer: bool = field(
         default=True,

examples/language-modeling/run_plm.py

@@ -64,7 +64,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
     use_fast_tokenizer: bool = field(
         default=True,

examples/lightning_base.py

@@ -236,7 +236,7 @@ class BaseTransformer(pl.LightningModule):
             "--cache_dir",
             default="",
             type=str,
-            help="Where do you want to store the pre-trained models downloaded from s3",
+            help="Where do you want to store the pre-trained models downloaded from huggingface.co",
         )
         parser.add_argument(
             "--encoder_layerdrop",

examples/movement-pruning/masked_run_glue.py

@@ -620,7 +620,7 @@ def main():
         "--cache_dir",
         default="",
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
     parser.add_argument(
         "--max_seq_length",

examples/movement-pruning/masked_run_squad.py

@@ -725,7 +725,7 @@ def main():
         "--cache_dir",
         default="",
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
 
     parser.add_argument(

examples/multiple-choice/run_multiple_choice.py

@@ -61,7 +61,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
 
 

examples/multiple-choice/run_tf_multiple_choice.py

@@ -65,7 +65,8 @@ class ModelArguments:
         default=None, metadata={"help": "Pretrained tokenizer name or path if not the same as model_name"}
     )
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
 
 

examples/question-answering/run_squad.py

@@ -532,7 +532,7 @@ def main():
         "--cache_dir",
         default="",
         type=str,
-        help="Where do you want to store the pre-trained models downloaded from s3",
+        help="Where do you want to store the pre-trained models downloaded from huggingface.co",
     )
 
     parser.add_argument(

examples/question-answering/run_squad_trainer.py

@@ -51,7 +51,8 @@ class ModelArguments:
     # If you want to tweak more attributes on your tokenizer, you should do it in a distinct script,
     # or just modify its tokenizer_config.json.
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )
 
 

examples/question-answering/run_tf_squad.py

@@ -63,7 +63,8 @@ class ModelArguments:
     # If you want to tweak more attributes on your tokenizer, you should do it in a distinct script,
     # or just modify its tokenizer_config.json.
     cache_dir: Optional[str] = field(
-        default=None, metadata={"help": "Where do you want to store the pretrained models downloaded from s3"}
+        default=None,
+        metadata={"help": "Where do you want to store the pretrained models downloaded from huggingface.co"},
     )